Delete folder lora_adapter with huggingface_hub

lora_adapter/README.md

@@ -1,62 +0,0 @@
----
-base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: peft
-model_name: remasterphantom-v4-lora
-tags:
-- base_model:adapter:unsloth/Llama-3.2-1B-Instruct
-- lora
-- sft
-- transformers
-- trl
-licence: license
-pipeline_tag: text-generation
----
-
-# Model Card for remasterphantom-v4-lora
-
-This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-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 0.21.0
-- TRL: 1.13.0
-- Transformers: 5.17.0
-- Pytorch: 2.14.0
-- Datasets: 5.0.1
-- Tokenizers: 0.23.2
-
-## 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}
-}
-```

lora_adapter/adapter_config.json

@@ -1,51 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.0",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

lora_adapter/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2bdb9bfe9dcb6ee40142abfefeb2050b40d333d04db27c6f4bd7fe8a022e3bf
-size 45118424

lora_adapter/chat_template.jinja

@@ -1,93 +0,0 @@
-{{- 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 %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
-    {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
-    {%- endif %}
-{%- 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 #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\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 %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- 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 %}

lora_adapter/checkpoint-1000/README.md

@@ -1,209 +0,0 @@
----
-base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/Llama-3.2-1B-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 0.21.0

lora_adapter/checkpoint-1000/adapter_config.json

@@ -1,51 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.0",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

lora_adapter/checkpoint-1000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4c341edfdf2d9afbc8810a249898521f31b98fab89e4359d12ec462a50266bb0
-size 45118424

lora_adapter/checkpoint-1000/chat_template.jinja

@@ -1,93 +0,0 @@
-{{- 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 %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
-    {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
-    {%- endif %}
-{%- 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 #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\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 %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- 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 %}

lora_adapter/checkpoint-1000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6d16a2198b296a172c19c9e933f9bd0afe6d17b6865efec41758a003a94075f9
-size 90359883

lora_adapter/checkpoint-1000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
-size 14455

lora_adapter/checkpoint-1000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:671f2e95ff373785663cc994437f3672b9bd8a8ef9d0199bc801e6a9b60e5a0e
-size 1465

lora_adapter/checkpoint-1000/tokenizer.json

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

lora_adapter/checkpoint-1000/tokenizer_config.json

@@ -1,17 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "left",
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null
-}

lora_adapter/checkpoint-1000/trainer_state.json

@@ -1,1045 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.5873015873015874,
-  "eval_steps": 500,
-  "global_step": 1000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 3.2998463183641435,
-      "epoch": 0.015873015873015872,
-      "grad_norm": 5.5954365730285645,
-      "learning_rate": 3e-05,
-      "loss": 4.793289566040039,
-      "mean_token_accuracy": 0.36775660440325736,
-      "num_tokens": 16307.0,
-      "step": 10
-    },
-    {
-      "entropy": 3.745172455906868,
-      "epoch": 0.031746031746031744,
-      "grad_norm": 2.467291831970215,
-      "learning_rate": 6.333333333333333e-05,
-      "loss": 3.7420589447021486,
-      "mean_token_accuracy": 0.43841218277812005,
-      "num_tokens": 32577.0,
-      "step": 20
-    },
-    {
-      "entropy": 3.1654938369989396,
-      "epoch": 0.047619047619047616,
-      "grad_norm": 1.8811299800872803,
-      "learning_rate": 9.666666666666667e-05,
-      "loss": 2.4434362411499024,
-      "mean_token_accuracy": 0.6050871018320322,
-      "num_tokens": 48737.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.9995254769921302,
-      "epoch": 0.06349206349206349,
-      "grad_norm": 1.535879373550415,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.565892219543457,
-      "mean_token_accuracy": 0.7555049300193787,
-      "num_tokens": 64997.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.5211943820118905,
-      "epoch": 0.07936507936507936,
-      "grad_norm": 1.7563194036483765,
-      "learning_rate": 0.00016333333333333334,
-      "loss": 1.1280284881591798,
-      "mean_token_accuracy": 0.812470355629921,
-      "num_tokens": 81080.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.17081895545125,
-      "epoch": 0.09523809523809523,
-      "grad_norm": 1.464584231376648,
-      "learning_rate": 0.00019666666666666666,
-      "loss": 0.8906035423278809,
-      "mean_token_accuracy": 0.8521104611456394,
-      "num_tokens": 97196.0,
-      "step": 60
-    },
-    {
-      "entropy": 0.9356300979852676,
-      "epoch": 0.1111111111111111,
-      "grad_norm": 1.4088091850280762,
-      "learning_rate": 0.00019997224302180006,
-      "loss": 0.670417308807373,
-      "mean_token_accuracy": 0.8883098550140858,
-      "num_tokens": 113569.0,
-      "step": 70
-    },
-    {
-      "entropy": 0.5688819501549005,
-      "epoch": 0.12698412698412698,
-      "grad_norm": 1.340789794921875,
-      "learning_rate": 0.00019987631275635948,
-      "loss": 0.36014580726623535,
-      "mean_token_accuracy": 0.9383806541562081,
-      "num_tokens": 129665.0,
-      "step": 80
-    },
-    {
-      "entropy": 0.5208159729838371,
-      "epoch": 0.14285714285714285,
-      "grad_norm": 1.1698484420776367,
-      "learning_rate": 0.00019971193225508879,
-      "loss": 0.38550715446472167,
-      "mean_token_accuracy": 0.9369473621249199,
-      "num_tokens": 145819.0,
-      "step": 90
-    },
-    {
-      "entropy": 0.35822844561189415,
-      "epoch": 0.15873015873015872,
-      "grad_norm": 1.056837558746338,
-      "learning_rate": 0.00019947921417617267,
-      "loss": 0.24877142906188965,
-      "mean_token_accuracy": 0.9541201412677764,
-      "num_tokens": 162338.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.36921846531331537,
-      "epoch": 0.1746031746031746,
-      "grad_norm": 0.771403431892395,
-      "learning_rate": 0.0001991783180129578,
-      "loss": 0.2972050666809082,
-      "mean_token_accuracy": 0.946565055847168,
-      "num_tokens": 179013.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.4222600903362036,
-      "epoch": 0.19047619047619047,
-      "grad_norm": 0.6926781535148621,
-      "learning_rate": 0.00019880944998464434,
-      "loss": 0.3286353349685669,
-      "mean_token_accuracy": 0.9404827795922757,
-      "num_tokens": 195500.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.23451931905001402,
-      "epoch": 0.20634920634920634,
-      "grad_norm": 1.0064337253570557,
-      "learning_rate": 0.00019837286289495361,
-      "loss": 0.16426128149032593,
-      "mean_token_accuracy": 0.9648101754486561,
-      "num_tokens": 211542.0,
-      "step": 130
-    },
-    {
-      "entropy": 0.26509888684377075,
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.6641770601272583,
-      "learning_rate": 0.0001978688559588688,
-      "loss": 0.1910732865333557,
-      "mean_token_accuracy": 0.9604174040257931,
-      "num_tokens": 227757.0,
-      "step": 140
-    },
-    {
-      "entropy": 0.3036362808197737,
-      "epoch": 0.23809523809523808,
-      "grad_norm": 0.9009377956390381,
-      "learning_rate": 0.0001972977745975682,
-      "loss": 0.24015522003173828,
-      "mean_token_accuracy": 0.9528692953288556,
-      "num_tokens": 244201.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.2707868428900838,
-      "epoch": 0.25396825396825395,
-      "grad_norm": 0.7132826447486877,
-      "learning_rate": 0.00019666001020169073,
-      "loss": 0.21738948822021484,
-      "mean_token_accuracy": 0.9576977901160717,
-      "num_tokens": 260595.0,
-      "step": 160
-    },
-    {
-      "entropy": 0.2235692773014307,
-      "epoch": 0.2698412698412698,
-      "grad_norm": 0.47566577792167664,
-      "learning_rate": 0.00019595599986309628,
-      "loss": 0.1625096917152405,
-      "mean_token_accuracy": 0.9630098052322864,
-      "num_tokens": 276583.0,
-      "step": 170
-    },
-    {
-      "entropy": 0.19970224229618908,
-      "epoch": 0.2857142857142857,
-      "grad_norm": 0.6967102885246277,
-      "learning_rate": 0.0001951862260753048,
-      "loss": 0.1510181427001953,
-      "mean_token_accuracy": 0.9644064873456955,
-      "num_tokens": 292611.0,
-      "step": 180
-    },
-    {
-      "entropy": 0.18911871258169413,
-      "epoch": 0.30158730158730157,
-      "grad_norm": 0.579555869102478,
-      "learning_rate": 0.00019435121640281938,
-      "loss": 0.14125581979751586,
-      "mean_token_accuracy": 0.9668954975903035,
-      "num_tokens": 308945.0,
-      "step": 190
-    },
-    {
-      "entropy": 0.21873050034046174,
-      "epoch": 0.31746031746031744,
-      "grad_norm": 0.6234372854232788,
-      "learning_rate": 0.00019345154311955985,
-      "loss": 0.18390271663665772,
-      "mean_token_accuracy": 0.9605240561068058,
-      "num_tokens": 325018.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.23017035396769642,
-      "epoch": 0.3333333333333333,
-      "grad_norm": 0.5848660469055176,
-      "learning_rate": 0.00019248782281665498,
-      "loss": 0.18674861192703246,
-      "mean_token_accuracy": 0.960551692545414,
-      "num_tokens": 341276.0,
-      "step": 210
-    },
-    {
-      "entropy": 0.23857398927211762,
-      "epoch": 0.3492063492063492,
-      "grad_norm": 0.5835615992546082,
-      "learning_rate": 0.00019146071597986138,
-      "loss": 0.1981763243675232,
-      "mean_token_accuracy": 0.9606492578983307,
-      "num_tokens": 357585.0,
-      "step": 220
-    },
-    {
-      "entropy": 0.21739678094163536,
-      "epoch": 0.36507936507936506,
-      "grad_norm": 0.49282777309417725,
-      "learning_rate": 0.00019037092653689987,
-      "loss": 0.16624126434326172,
-      "mean_token_accuracy": 0.964983056485653,
-      "num_tokens": 374067.0,
-      "step": 230
-    },
-    {
-      "entropy": 0.2051882056519389,
-      "epoch": 0.38095238095238093,
-      "grad_norm": 0.7691304683685303,
-      "learning_rate": 0.00018921920137501849,
-      "loss": 0.17399615049362183,
-      "mean_token_accuracy": 0.9637806750833988,
-      "num_tokens": 390575.0,
-      "step": 240
-    },
-    {
-      "entropy": 0.19259531470015645,
-      "epoch": 0.3968253968253968,
-      "grad_norm": 0.41227754950523376,
-      "learning_rate": 0.00018800632982911322,
-      "loss": 0.14645222425460816,
-      "mean_token_accuracy": 0.9661086022853851,
-      "num_tokens": 406790.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.12554183262400329,
-      "epoch": 0.4126984126984127,
-      "grad_norm": 0.38903799653053284,
-      "learning_rate": 0.00018673314314075732,
-      "loss": 0.0970867395401001,
-      "mean_token_accuracy": 0.9753100097179412,
-      "num_tokens": 422899.0,
-      "step": 260
-    },
-    {
-      "entropy": 0.21776192565448582,
-      "epoch": 0.42857142857142855,
-      "grad_norm": 0.5275615453720093,
-      "learning_rate": 0.00018540051388850993,
-      "loss": 0.175495445728302,
-      "mean_token_accuracy": 0.9626297920942306,
-      "num_tokens": 439095.0,
-      "step": 270
-    },
-    {
-      "entropy": 0.41472155014052986,
-      "epoch": 0.4444444444444444,
-      "grad_norm": 1.5612674951553345,
-      "learning_rate": 0.0001840093553898942,
-      "loss": 0.3378293514251709,
-      "mean_token_accuracy": 0.9364372007548809,
-      "num_tokens": 455598.0,
-      "step": 280
-    },
-    {
-      "entropy": 0.18331955913454295,
-      "epoch": 0.4603174603174603,
-      "grad_norm": 0.3843788206577301,
-      "learning_rate": 0.00018256062107545518,
-      "loss": 0.13437695503234864,
-      "mean_token_accuracy": 0.9686297826468945,
-      "num_tokens": 471075.0,
-      "step": 290
-    },
-    {
-      "entropy": 0.16779997684061526,
-      "epoch": 0.47619047619047616,
-      "grad_norm": 0.3690398037433624,
-      "learning_rate": 0.00018105530383532607,
-      "loss": 0.13349469900131225,
-      "mean_token_accuracy": 0.9697726428508758,
-      "num_tokens": 486950.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.18286482915282248,
-      "epoch": 0.49206349206349204,
-      "grad_norm": 0.5309385657310486,
-      "learning_rate": 0.000179494435338751,
-      "loss": 0.14468667507171631,
-      "mean_token_accuracy": 0.9676945447921753,
-      "num_tokens": 503167.0,
-      "step": 310
-    },
-    {
-      "entropy": 0.21837912490591407,
-      "epoch": 0.5079365079365079,
-      "grad_norm": 0.5445209741592407,
-      "learning_rate": 0.00017787908532703042,
-      "loss": 0.16839513778686524,
-      "mean_token_accuracy": 0.9623315379023551,
-      "num_tokens": 519080.0,
-      "step": 320
-    },
-    {
-      "entropy": 0.16709138257429004,
-      "epoch": 0.5238095238095238,
-      "grad_norm": 0.712787926197052,
-      "learning_rate": 0.00017621036088037378,
-      "loss": 0.13333501815795898,
-      "mean_token_accuracy": 0.9686624228954315,
-      "num_tokens": 535244.0,
-      "step": 330
-    },
-    {
-      "entropy": 0.1875067687127739,
-      "epoch": 0.5396825396825397,
-      "grad_norm": 0.34370172023773193,
-      "learning_rate": 0.00017448940565916222,
-      "loss": 0.14327633380889893,
-      "mean_token_accuracy": 0.9682756960391998,
-      "num_tokens": 551358.0,
-      "step": 340
-    },
-    {
-      "entropy": 0.15009528640657663,
-      "epoch": 0.5555555555555556,
-      "grad_norm": 0.33299151062965393,
-      "learning_rate": 0.00017271739912014068,
-      "loss": 0.11425788402557373,
-      "mean_token_accuracy": 0.9726194083690644,
-      "num_tokens": 567832.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.15241470024921,
-      "epoch": 0.5714285714285714,
-      "grad_norm": 0.3769768476486206,
-      "learning_rate": 0.00017089555570807736,
-      "loss": 0.1251630187034607,
-      "mean_token_accuracy": 0.9712164625525475,
-      "num_tokens": 583486.0,
-      "step": 360
-    },
-    {
-      "entropy": 0.19003299945034086,
-      "epoch": 0.5873015873015873,
-      "grad_norm": 0.7838993072509766,
-      "learning_rate": 0.00016902512402344373,
-      "loss": 0.1713760018348694,
-      "mean_token_accuracy": 0.9653461590409279,
-      "num_tokens": 599729.0,
-      "step": 370
-    },
-    {
-      "entropy": 0.17572227772325277,
-      "epoch": 0.6031746031746031,
-      "grad_norm": 0.42281991243362427,
-      "learning_rate": 0.00016710738596668632,
-      "loss": 0.1362382650375366,
-      "mean_token_accuracy": 0.9687412306666374,
-      "num_tokens": 616044.0,
-      "step": 380
-    },
-    {
-      "entropy": 0.16331438799388706,
-      "epoch": 0.6190476190476191,
-      "grad_norm": 1.076119065284729,
-      "learning_rate": 0.00016514365585967603,
-      "loss": 0.12754744291305542,
-      "mean_token_accuracy": 0.9687342867255211,
-      "num_tokens": 632147.0,
-      "step": 390
-    },
-    {
-      "entropy": 0.19245414207689465,
-      "epoch": 0.6349206349206349,
-      "grad_norm": 0.644232988357544,
-      "learning_rate": 0.00016313527954493778,
-      "loss": 0.15318721532821655,
-      "mean_token_accuracy": 0.9658746793866158,
-      "num_tokens": 648375.0,
-      "step": 400
-    },
-    {
-      "entropy": 0.21062263241037726,
-      "epoch": 0.6507936507936508,
-      "grad_norm": 1.0224113464355469,
-      "learning_rate": 0.000161083633463277,
-      "loss": 0.15229741334915162,
-      "mean_token_accuracy": 0.9644093818962574,
-      "num_tokens": 664711.0,
-      "step": 410
-    },
-    {
-      "entropy": 0.1936994613148272,
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.7962023615837097,
-      "learning_rate": 0.00015899012371043604,
-      "loss": 0.14902880191802978,
-      "mean_token_accuracy": 0.9662799052894115,
-      "num_tokens": 681157.0,
-      "step": 420
-    },
-    {
-      "entropy": 0.20361803583800792,
-      "epoch": 0.6825396825396826,
-      "grad_norm": 0.2999099791049957,
-      "learning_rate": 0.0001568561850734264,
-      "loss": 0.16481378078460693,
-      "mean_token_accuracy": 0.9628334604203701,
-      "num_tokens": 697602.0,
-      "step": 430
-    },
-    {
-      "entropy": 0.13618148500099778,
-      "epoch": 0.6984126984126984,
-      "grad_norm": 0.4104563295841217,
-      "learning_rate": 0.00015468328004719726,
-      "loss": 0.10586557388305665,
-      "mean_token_accuracy": 0.972815252840519,
-      "num_tokens": 713742.0,
-      "step": 440
-    },
-    {
-      "entropy": 0.1247363390866667,
-      "epoch": 0.7142857142857143,
-      "grad_norm": 0.3249231278896332,
-      "learning_rate": 0.00015247289783231453,
-      "loss": 0.09654146432876587,
-      "mean_token_accuracy": 0.9732306160032749,
-      "num_tokens": 730000.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.14613611157983541,
-      "epoch": 0.7301587301587301,
-      "grad_norm": 0.5225287079811096,
-      "learning_rate": 0.00015022655331433727,
-      "loss": 0.12931008338928224,
-      "mean_token_accuracy": 0.9701415166258812,
-      "num_tokens": 746117.0,
-      "step": 460
-    },
-    {
-      "entropy": 0.21532428292557598,
-      "epoch": 0.746031746031746,
-      "grad_norm": 0.5957981944084167,
-      "learning_rate": 0.00014794578602559067,
-      "loss": 0.16675063371658325,
-      "mean_token_accuracy": 0.9630694188177585,
-      "num_tokens": 762345.0,
-      "step": 470
-    },
-    {
-      "entropy": 0.13289255439303815,
-      "epoch": 0.7619047619047619,
-      "grad_norm": 0.5672221183776855,
-      "learning_rate": 0.0001456321590900476,
-      "loss": 0.10865170955657959,
-      "mean_token_accuracy": 0.9729436971247196,
-      "num_tokens": 778187.0,
-      "step": 480
-    },
-    {
-      "entropy": 0.11678903801366687,
-      "epoch": 0.7777777777777778,
-      "grad_norm": 0.49610644578933716,
-      "learning_rate": 0.00014328725815204144,
-      "loss": 0.09211295247077941,
-      "mean_token_accuracy": 0.9758312977850437,
-      "num_tokens": 794532.0,
-      "step": 490
-    },
-    {
-      "entropy": 0.17705639996565878,
-      "epoch": 0.7936507936507936,
-      "grad_norm": 0.3945449888706207,
-      "learning_rate": 0.00014091269028954458,
-      "loss": 0.13619123697280883,
-      "mean_token_accuracy": 0.9707398265600204,
-      "num_tokens": 810831.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.17228290904313326,
-      "epoch": 0.8095238095238095,
-      "grad_norm": 1.207584261894226,
-      "learning_rate": 0.00013851008291275782,
-      "loss": 0.15327351093292235,
-      "mean_token_accuracy": 0.9661840803921222,
-      "num_tokens": 827075.0,
-      "step": 510
-    },
-    {
-      "entropy": 0.19909042734652757,
-      "epoch": 0.8253968253968254,
-      "grad_norm": 1.158147931098938,
-      "learning_rate": 0.0001360810826487642,
-      "loss": 0.1508009910583496,
-      "mean_token_accuracy": 0.9690110817551613,
-      "num_tokens": 843420.0,
-      "step": 520
-    },
-    {
-      "entropy": 0.09743964811787009,
-      "epoch": 0.8412698412698413,
-      "grad_norm": 0.3383720815181732,
-      "learning_rate": 0.0001336273542130134,
-      "loss": 0.0796388864517212,
-      "mean_token_accuracy": 0.9786469288170337,
-      "num_tokens": 859656.0,
-      "step": 530
-    },
-    {
-      "entropy": 0.13433767426759005,
-      "epoch": 0.8571428571428571,
-      "grad_norm": 0.2866056263446808,
-      "learning_rate": 0.00013115057926840884,
-      "loss": 0.10593793392181397,
-      "mean_token_accuracy": 0.9751186288893223,
-      "num_tokens": 876270.0,
-      "step": 540
-    },
-    {
-      "entropy": 0.11862653940916061,
-      "epoch": 0.873015873015873,
-      "grad_norm": 0.3208288252353668,
-      "learning_rate": 0.00012865245527277986,
-      "loss": 0.08963249325752258,
-      "mean_token_accuracy": 0.9761230409145355,
-      "num_tokens": 892446.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.13657542318105698,
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.7049503326416016,
-      "learning_rate": 0.00012613469431552895,
-      "loss": 0.10923233032226562,
-      "mean_token_accuracy": 0.9730862841010094,
-      "num_tokens": 909132.0,
-      "step": 560
-    },
-    {
-      "entropy": 0.10375349051319063,
-      "epoch": 0.9047619047619048,
-      "grad_norm": 0.31443658471107483,
-      "learning_rate": 0.00012359902194425133,
-      "loss": 0.08820843696594238,
-      "mean_token_accuracy": 0.976572859287262,
-      "num_tokens": 925031.0,
-      "step": 570
-    },
-    {
-      "entropy": 0.15578375817276538,
-      "epoch": 0.9206349206349206,
-      "grad_norm": 0.5118997097015381,
-      "learning_rate": 0.00012104717598213056,
-      "loss": 0.12504205703735352,
-      "mean_token_accuracy": 0.9705536551773548,
-      "num_tokens": 941516.0,
-      "step": 580
-    },
-    {
-      "entropy": 0.12206159401684999,
-      "epoch": 0.9365079365079365,
-      "grad_norm": 0.46927565336227417,
-      "learning_rate": 0.00011848090533692155,
-      "loss": 0.09753256440162658,
-      "mean_token_accuracy": 0.9753957264125347,
-      "num_tokens": 958128.0,
-      "step": 590
-    },
-    {
-      "entropy": 0.11996419210918248,
-      "epoch": 0.9523809523809523,
-      "grad_norm": 0.42994368076324463,
-      "learning_rate": 0.00011590196880233644,
-      "loss": 0.09162289500236512,
-      "mean_token_accuracy": 0.9756640173494816,
-      "num_tokens": 974535.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.10587584185414016,
-      "epoch": 0.9682539682539683,
-      "grad_norm": 0.5217767953872681,
-      "learning_rate": 0.00011331213385265524,
-      "loss": 0.08587267398834228,
-      "mean_token_accuracy": 0.9776035018265248,
-      "num_tokens": 990795.0,
-      "step": 610
-    },
-    {
-      "entropy": 0.10501609425991773,
-      "epoch": 0.9841269841269841,
-      "grad_norm": 0.2820020616054535,
-      "learning_rate": 0.00011071317543138738,
-      "loss": 0.08439798951148987,
-      "mean_token_accuracy": 0.977333414554596,
-      "num_tokens": 1006990.0,
-      "step": 620
-    },
-    {
-      "entropy": 0.12649747403338552,
-      "epoch": 1.0,
-      "grad_norm": 1.2852208614349365,
-      "learning_rate": 0.00010810687473481389,
-      "loss": 0.1123587965965271,
-      "mean_token_accuracy": 0.9716072164475917,
-      "num_tokens": 1023153.0,
-      "step": 630
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.14963509702592864,
-      "eval_loss": 0.12754344940185547,
-      "eval_mean_token_accuracy": 0.9698916635567084,
-      "eval_num_tokens": 1023153.0,
-      "eval_runtime": 123.9839,
-      "eval_samples_per_second": 2.145,
-      "eval_steps_per_second": 2.145,
-      "step": 630
-    },
-    {
-      "entropy": 0.08182793376035988,
-      "epoch": 1.0158730158730158,
-      "grad_norm": 0.2164141982793808,
-      "learning_rate": 0.0001054950179912446,
-      "loss": 0.06998351216316223,
-      "mean_token_accuracy": 0.9800584927201271,
-      "num_tokens": 1039301.0,
-      "step": 640
-    },
-    {
-      "entropy": 0.15589865446090698,
-      "epoch": 1.0317460317460316,
-      "grad_norm": 0.3905109763145447,
-      "learning_rate": 0.00010287939523682634,
-      "loss": 0.11804149150848389,
-      "mean_token_accuracy": 0.9720940880477429,
-      "num_tokens": 1055881.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.13176414640620351,
-      "epoch": 1.0476190476190477,
-      "grad_norm": 0.22936023771762848,
-      "learning_rate": 0.00010026179908874183,
-      "loss": 0.09952049255371094,
-      "mean_token_accuracy": 0.9751471273601056,
-      "num_tokens": 1072034.0,
-      "step": 660
-    },
-    {
-      "entropy": 0.13261872120201587,
-      "epoch": 1.0634920634920635,
-      "grad_norm": 0.3445717990398407,
-      "learning_rate": 9.764402351663901e-05,
-      "loss": 0.09959723353385926,
-      "mean_token_accuracy": 0.9765739187598228,
-      "num_tokens": 1087942.0,
-      "step": 670
-    },
-    {
-      "entropy": 0.09457834200002253,
-      "epoch": 1.0793650793650793,
-      "grad_norm": 0.2506314516067505,
-      "learning_rate": 9.502786261313423e-05,
-      "loss": 0.07293067574501037,
-      "mean_token_accuracy": 0.979874362796545,
-      "num_tokens": 1104345.0,
-      "step": 680
-    },
-    {
-      "entropy": 0.15131392041221262,
-      "epoch": 1.0952380952380953,
-      "grad_norm": 0.6880223155021667,
-      "learning_rate": 9.241510936423062e-05,
-      "loss": 0.11448752880096436,
-      "mean_token_accuracy": 0.9732576005160809,
-      "num_tokens": 1120840.0,
-      "step": 690
-    },
-    {
-      "entropy": 0.10610079388134182,
-      "epoch": 1.1111111111111112,
-      "grad_norm": 0.6070828437805176,
-      "learning_rate": 8.980755442049502e-05,
-      "loss": 0.07732992172241211,
-      "mean_token_accuracy": 0.978425282239914,
-      "num_tokens": 1137127.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.10017788861878216,
-      "epoch": 1.126984126984127,
-      "grad_norm": 0.2830179035663605,
-      "learning_rate": 8.720698486983557e-05,
-      "loss": 0.08647966384887695,
-      "mean_token_accuracy": 0.9760376676917076,
-      "num_tokens": 1153242.0,
-      "step": 710
-    },
-    {
-      "entropy": 0.11412310716696084,
-      "epoch": 1.1428571428571428,
-      "grad_norm": 0.5743200778961182,
-      "learning_rate": 8.461518301272099e-05,
-      "loss": 0.08402568697929383,
-      "mean_token_accuracy": 0.9778100050985813,
-      "num_tokens": 1169145.0,
-      "step": 720
-    },
-    {
-      "entropy": 0.12544448575936257,
-      "epoch": 1.1587301587301586,
-      "grad_norm": 0.3491770625114441,
-      "learning_rate": 8.203392514068074e-05,
-      "loss": 0.09491501450538635,
-      "mean_token_accuracy": 0.9753343552350998,
-      "num_tokens": 1184902.0,
-      "step": 730
-    },
-    {
-      "entropy": 0.12449102494865656,
-      "epoch": 1.1746031746031746,
-      "grad_norm": 0.7691491842269897,
-      "learning_rate": 7.946498031892364e-05,
-      "loss": 0.10109654664993287,
-      "mean_token_accuracy": 0.9746225215494633,
-      "num_tokens": 1201208.0,
-      "step": 740
-    },
-    {
-      "entropy": 0.11652453513816,
-      "epoch": 1.1904761904761905,
-      "grad_norm": 0.4358707368373871,
-      "learning_rate": 7.691010917390874e-05,
-      "loss": 0.08225674629211426,
-      "mean_token_accuracy": 0.9781361222267151,
-      "num_tokens": 1217157.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.11605553817935288,
-      "epoch": 1.2063492063492063,
-      "grad_norm": 0.725312352180481,
-      "learning_rate": 7.437106268670034e-05,
-      "loss": 0.09104912281036377,
-      "mean_token_accuracy": 0.9763554163277149,
-      "num_tokens": 1233144.0,
-      "step": 760
-    },
-    {
-      "entropy": 0.10015753363259136,
-      "epoch": 1.2222222222222223,
-      "grad_norm": 0.23935319483280182,
-      "learning_rate": 7.184958099293246e-05,
-      "loss": 0.07568765282630921,
-      "mean_token_accuracy": 0.9788681827485561,
-      "num_tokens": 1249197.0,
-      "step": 770
-    },
-    {
-      "entropy": 0.11299324771389366,
-      "epoch": 1.2380952380952381,
-      "grad_norm": 0.2620716989040375,
-      "learning_rate": 6.934739219020726e-05,
-      "loss": 0.08495272397994995,
-      "mean_token_accuracy": 0.9769734017550945,
-      "num_tokens": 1265221.0,
-      "step": 780
-    },
-    {
-      "entropy": 0.12418944174423814,
-      "epoch": 1.253968253968254,
-      "grad_norm": 0.8303375244140625,
-      "learning_rate": 6.68662111537429e-05,
-      "loss": 0.09562642574310302,
-      "mean_token_accuracy": 0.9761748388409615,
-      "num_tokens": 1281587.0,
-      "step": 790
-    },
-    {
-      "entropy": 0.09764590142294764,
-      "epoch": 1.2698412698412698,
-      "grad_norm": 0.29645025730133057,
-      "learning_rate": 6.440773836108413e-05,
-      "loss": 0.07879915237426757,
-      "mean_token_accuracy": 0.9772366717457771,
-      "num_tokens": 1297619.0,
-      "step": 800
-    },
-    {
-      "entropy": 0.0912503881379962,
-      "epoch": 1.2857142857142856,
-      "grad_norm": 0.26137638092041016,
-      "learning_rate": 6.197365872667952e-05,
-      "loss": 0.07751978039741517,
-      "mean_token_accuracy": 0.9783523350954055,
-      "num_tokens": 1314138.0,
-      "step": 810
-    },
-    {
-      "entropy": 0.09291230556555093,
-      "epoch": 1.3015873015873016,
-      "grad_norm": 0.2815020680427551,
-      "learning_rate": 5.956564044712551e-05,
-      "loss": 0.07410196661949157,
-      "mean_token_accuracy": 0.9806918106973171,
-      "num_tokens": 1330586.0,
-      "step": 820
-    },
-    {
-      "entropy": 0.10326733374968171,
-      "epoch": 1.3174603174603174,
-      "grad_norm": 0.5554925799369812,
-      "learning_rate": 5.718533385786772e-05,
-      "loss": 0.07725996375083924,
-      "mean_token_accuracy": 0.9791568756103516,
-      "num_tokens": 1346407.0,
-      "step": 830
-    },
-    {
-      "entropy": 0.09574338933452964,
-      "epoch": 1.3333333333333333,
-      "grad_norm": 0.26772093772888184,
-      "learning_rate": 5.483437030214343e-05,
-      "loss": 0.07193758487701415,
-      "mean_token_accuracy": 0.9782747387886047,
-      "num_tokens": 1362665.0,
-      "step": 840
-    },
-    {
-      "entropy": 0.08038676274009049,
-      "epoch": 1.3492063492063493,
-      "grad_norm": 0.2647678554058075,
-      "learning_rate": 5.251436101294056e-05,
-      "loss": 0.06795459985733032,
-      "mean_token_accuracy": 0.9803436301648617,
-      "num_tokens": 1378705.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.0904398019425571,
-      "epoch": 1.3650793650793651,
-      "grad_norm": 0.29914480447769165,
-      "learning_rate": 5.0226896008738786e-05,
-      "loss": 0.073968905210495,
-      "mean_token_accuracy": 0.9796601250767708,
-      "num_tokens": 1394982.0,
-      "step": 860
-    },
-    {
-      "entropy": 0.10209746155887842,
-      "epoch": 1.380952380952381,
-      "grad_norm": 0.5169049501419067,
-      "learning_rate": 4.79735430037906e-05,
-      "loss": 0.07558119297027588,
-      "mean_token_accuracy": 0.9789449907839298,
-      "num_tokens": 1411483.0,
-      "step": 870
-    },
-    {
-      "entropy": 0.1625033107586205,
-      "epoch": 1.3968253968253967,
-      "grad_norm": 0.6515079140663147,
-      "learning_rate": 4.575584633368815e-05,
-      "loss": 0.1234513521194458,
-      "mean_token_accuracy": 0.9717937491834163,
-      "num_tokens": 1427923.0,
-      "step": 880
-    },
-    {
-      "entropy": 0.09612479698844253,
-      "epoch": 1.4126984126984126,
-      "grad_norm": 0.2811136841773987,
-      "learning_rate": 4.35753258969526e-05,
-      "loss": 0.07417153716087341,
-      "mean_token_accuracy": 0.9791869692504406,
-      "num_tokens": 1443910.0,
-      "step": 890
-    },
-    {
-      "entropy": 0.08588011246174573,
-      "epoch": 1.4285714285714286,
-      "grad_norm": 0.1975420117378235,
-      "learning_rate": 4.143347611337194e-05,
-      "loss": 0.0669679045677185,
-      "mean_token_accuracy": 0.9794288754463196,
-      "num_tokens": 1460071.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.09144520740956068,
-      "epoch": 1.4444444444444444,
-      "grad_norm": 0.2851484417915344,
-      "learning_rate": 3.933176489980005e-05,
-      "loss": 0.07232853174209594,
-      "mean_token_accuracy": 0.9785544127225876,
-      "num_tokens": 1476394.0,
-      "step": 910
-    },
-    {
-      "entropy": 0.0951843905262649,
-      "epoch": 1.4603174603174602,
-      "grad_norm": 0.4222939610481262,
-      "learning_rate": 3.7271632664119846e-05,
-      "loss": 0.07465221881866455,
-      "mean_token_accuracy": 0.9787473000586033,
-      "num_tokens": 1492202.0,
-      "step": 920
-    },
-    {
-      "entropy": 0.14563625650480388,
-      "epoch": 1.4761904761904763,
-      "grad_norm": 0.43433165550231934,
-      "learning_rate": 3.525449131805982e-05,
-      "loss": 0.09597810506820678,
-      "mean_token_accuracy": 0.9762231051921845,
-      "num_tokens": 1508587.0,
-      "step": 930
-    },
-    {
-      "entropy": 0.08089337153360247,
-      "epoch": 1.492063492063492,
-      "grad_norm": 0.25026291608810425,
-      "learning_rate": 3.328172330954001e-05,
-      "loss": 0.06541991233825684,
-      "mean_token_accuracy": 0.9804870396852493,
-      "num_tokens": 1524608.0,
-      "step": 940
-    },
-    {
-      "entropy": 0.11199918817728757,
-      "epoch": 1.507936507936508,
-      "grad_norm": 0.2416200041770935,
-      "learning_rate": 3.1354680675211635e-05,
-      "loss": 0.08397775292396545,
-      "mean_token_accuracy": 0.9771605253219604,
-      "num_tokens": 1540705.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.10342249851673842,
-      "epoch": 1.5238095238095237,
-      "grad_norm": 0.2826922535896301,
-      "learning_rate": 2.9474684113838257e-05,
-      "loss": 0.07648788094520569,
-      "mean_token_accuracy": 0.9799712590873242,
-      "num_tokens": 1557086.0,
-      "step": 960
-    },
-    {
-      "entropy": 0.10365813223179429,
-      "epoch": 1.5396825396825395,
-      "grad_norm": 0.22921620309352875,
-      "learning_rate": 2.764302208115509e-05,
-      "loss": 0.07187622189521789,
-      "mean_token_accuracy": 0.9799506664276123,
-      "num_tokens": 1573507.0,
-      "step": 970
-    },
-    {
-      "entropy": 0.11406760299578309,
-      "epoch": 1.5555555555555556,
-      "grad_norm": 0.6570681929588318,
-      "learning_rate": 2.5860949906825795e-05,
-      "loss": 0.08612269759178162,
-      "mean_token_accuracy": 0.9780311018228531,
-      "num_tokens": 1589640.0,
-      "step": 980
-    },
-    {
-      "entropy": 0.11450605299323798,
-      "epoch": 1.5714285714285714,
-      "grad_norm": 0.24385221302509308,
-      "learning_rate": 2.412968893410219e-05,
-      "loss": 0.08079542517662049,
-      "mean_token_accuracy": 0.9784732617437839,
-      "num_tokens": 1605857.0,
-      "step": 990
-    },
-    {
-      "entropy": 0.11478545106947421,
-      "epoch": 1.5873015873015874,
-      "grad_norm": 1.2068188190460205,
-      "learning_rate": 2.2450425682776565e-05,
-      "loss": 0.10695868730545044,
-      "mean_token_accuracy": 0.9749820478260517,
-      "num_tokens": 1622078.0,
-      "step": 1000
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1260,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 9580819642294272.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

lora_adapter/checkpoint-1000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d03761d0c056d3be10441632fd015fad7320a6a18d86e794364c2efae99b3
-size 5713

lora_adapter/checkpoint-1200/README.md

@@ -1,209 +0,0 @@
----
-base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/Llama-3.2-1B-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 0.21.0

lora_adapter/checkpoint-1200/adapter_config.json

@@ -1,51 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.0",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

lora_adapter/checkpoint-1200/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c9e045f6cfe9af7906e35dd4efceb4709098d222961d160c5c06e9f0f2b6527d
-size 45118424

lora_adapter/checkpoint-1200/chat_template.jinja

@@ -1,93 +0,0 @@
-{{- 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 %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
-    {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
-    {%- endif %}
-{%- 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 #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\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 %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- 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 %}

lora_adapter/checkpoint-1200/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5725fb0b28f67c61d9a3128d63e310a6a9558fa5912726c333fc4daea2c23d24
-size 90359883

lora_adapter/checkpoint-1200/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
-size 14455

lora_adapter/checkpoint-1200/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d79fe57d82d58ab47716bc1ca2632acaebbb3fa7ab0a60ea13174dd57f96666e
-size 1465

lora_adapter/checkpoint-1200/tokenizer.json

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

lora_adapter/checkpoint-1200/tokenizer_config.json

@@ -1,17 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "left",
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null
-}

lora_adapter/checkpoint-1200/trainer_state.json

@@ -1,1245 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.9047619047619047,
-  "eval_steps": 500,
-  "global_step": 1200,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 3.2998463183641435,
-      "epoch": 0.015873015873015872,
-      "grad_norm": 5.5954365730285645,
-      "learning_rate": 3e-05,
-      "loss": 4.793289566040039,
-      "mean_token_accuracy": 0.36775660440325736,
-      "num_tokens": 16307.0,
-      "step": 10
-    },
-    {
-      "entropy": 3.745172455906868,
-      "epoch": 0.031746031746031744,
-      "grad_norm": 2.467291831970215,
-      "learning_rate": 6.333333333333333e-05,
-      "loss": 3.7420589447021486,
-      "mean_token_accuracy": 0.43841218277812005,
-      "num_tokens": 32577.0,
-      "step": 20
-    },
-    {
-      "entropy": 3.1654938369989396,
-      "epoch": 0.047619047619047616,
-      "grad_norm": 1.8811299800872803,
-      "learning_rate": 9.666666666666667e-05,
-      "loss": 2.4434362411499024,
-      "mean_token_accuracy": 0.6050871018320322,
-      "num_tokens": 48737.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.9995254769921302,
-      "epoch": 0.06349206349206349,
-      "grad_norm": 1.535879373550415,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.565892219543457,
-      "mean_token_accuracy": 0.7555049300193787,
-      "num_tokens": 64997.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.5211943820118905,
-      "epoch": 0.07936507936507936,
-      "grad_norm": 1.7563194036483765,
-      "learning_rate": 0.00016333333333333334,
-      "loss": 1.1280284881591798,
-      "mean_token_accuracy": 0.812470355629921,
-      "num_tokens": 81080.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.17081895545125,
-      "epoch": 0.09523809523809523,
-      "grad_norm": 1.464584231376648,
-      "learning_rate": 0.00019666666666666666,
-      "loss": 0.8906035423278809,
-      "mean_token_accuracy": 0.8521104611456394,
-      "num_tokens": 97196.0,
-      "step": 60
-    },
-    {
-      "entropy": 0.9356300979852676,
-      "epoch": 0.1111111111111111,
-      "grad_norm": 1.4088091850280762,
-      "learning_rate": 0.00019997224302180006,
-      "loss": 0.670417308807373,
-      "mean_token_accuracy": 0.8883098550140858,
-      "num_tokens": 113569.0,
-      "step": 70
-    },
-    {
-      "entropy": 0.5688819501549005,
-      "epoch": 0.12698412698412698,
-      "grad_norm": 1.340789794921875,
-      "learning_rate": 0.00019987631275635948,
-      "loss": 0.36014580726623535,
-      "mean_token_accuracy": 0.9383806541562081,
-      "num_tokens": 129665.0,
-      "step": 80
-    },
-    {
-      "entropy": 0.5208159729838371,
-      "epoch": 0.14285714285714285,
-      "grad_norm": 1.1698484420776367,
-      "learning_rate": 0.00019971193225508879,
-      "loss": 0.38550715446472167,
-      "mean_token_accuracy": 0.9369473621249199,
-      "num_tokens": 145819.0,
-      "step": 90
-    },
-    {
-      "entropy": 0.35822844561189415,
-      "epoch": 0.15873015873015872,
-      "grad_norm": 1.056837558746338,
-      "learning_rate": 0.00019947921417617267,
-      "loss": 0.24877142906188965,
-      "mean_token_accuracy": 0.9541201412677764,
-      "num_tokens": 162338.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.36921846531331537,
-      "epoch": 0.1746031746031746,
-      "grad_norm": 0.771403431892395,
-      "learning_rate": 0.0001991783180129578,
-      "loss": 0.2972050666809082,
-      "mean_token_accuracy": 0.946565055847168,
-      "num_tokens": 179013.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.4222600903362036,
-      "epoch": 0.19047619047619047,
-      "grad_norm": 0.6926781535148621,
-      "learning_rate": 0.00019880944998464434,
-      "loss": 0.3286353349685669,
-      "mean_token_accuracy": 0.9404827795922757,
-      "num_tokens": 195500.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.23451931905001402,
-      "epoch": 0.20634920634920634,
-      "grad_norm": 1.0064337253570557,
-      "learning_rate": 0.00019837286289495361,
-      "loss": 0.16426128149032593,
-      "mean_token_accuracy": 0.9648101754486561,
-      "num_tokens": 211542.0,
-      "step": 130
-    },
-    {
-      "entropy": 0.26509888684377075,
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.6641770601272583,
-      "learning_rate": 0.0001978688559588688,
-      "loss": 0.1910732865333557,
-      "mean_token_accuracy": 0.9604174040257931,
-      "num_tokens": 227757.0,
-      "step": 140
-    },
-    {
-      "entropy": 0.3036362808197737,
-      "epoch": 0.23809523809523808,
-      "grad_norm": 0.9009377956390381,
-      "learning_rate": 0.0001972977745975682,
-      "loss": 0.24015522003173828,
-      "mean_token_accuracy": 0.9528692953288556,
-      "num_tokens": 244201.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.2707868428900838,
-      "epoch": 0.25396825396825395,
-      "grad_norm": 0.7132826447486877,
-      "learning_rate": 0.00019666001020169073,
-      "loss": 0.21738948822021484,
-      "mean_token_accuracy": 0.9576977901160717,
-      "num_tokens": 260595.0,
-      "step": 160
-    },
-    {
-      "entropy": 0.2235692773014307,
-      "epoch": 0.2698412698412698,
-      "grad_norm": 0.47566577792167664,
-      "learning_rate": 0.00019595599986309628,
-      "loss": 0.1625096917152405,
-      "mean_token_accuracy": 0.9630098052322864,
-      "num_tokens": 276583.0,
-      "step": 170
-    },
-    {
-      "entropy": 0.19970224229618908,
-      "epoch": 0.2857142857142857,
-      "grad_norm": 0.6967102885246277,
-      "learning_rate": 0.0001951862260753048,
-      "loss": 0.1510181427001953,
-      "mean_token_accuracy": 0.9644064873456955,
-      "num_tokens": 292611.0,
-      "step": 180
-    },
-    {
-      "entropy": 0.18911871258169413,
-      "epoch": 0.30158730158730157,
-      "grad_norm": 0.579555869102478,
-      "learning_rate": 0.00019435121640281938,
-      "loss": 0.14125581979751586,
-      "mean_token_accuracy": 0.9668954975903035,
-      "num_tokens": 308945.0,
-      "step": 190
-    },
-    {
-      "entropy": 0.21873050034046174,
-      "epoch": 0.31746031746031744,
-      "grad_norm": 0.6234372854232788,
-      "learning_rate": 0.00019345154311955985,
-      "loss": 0.18390271663665772,
-      "mean_token_accuracy": 0.9605240561068058,
-      "num_tokens": 325018.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.23017035396769642,
-      "epoch": 0.3333333333333333,
-      "grad_norm": 0.5848660469055176,
-      "learning_rate": 0.00019248782281665498,
-      "loss": 0.18674861192703246,
-      "mean_token_accuracy": 0.960551692545414,
-      "num_tokens": 341276.0,
-      "step": 210
-    },
-    {
-      "entropy": 0.23857398927211762,
-      "epoch": 0.3492063492063492,
-      "grad_norm": 0.5835615992546082,
-      "learning_rate": 0.00019146071597986138,
-      "loss": 0.1981763243675232,
-      "mean_token_accuracy": 0.9606492578983307,
-      "num_tokens": 357585.0,
-      "step": 220
-    },
-    {
-      "entropy": 0.21739678094163536,
-      "epoch": 0.36507936507936506,
-      "grad_norm": 0.49282777309417725,
-      "learning_rate": 0.00019037092653689987,
-      "loss": 0.16624126434326172,
-      "mean_token_accuracy": 0.964983056485653,
-      "num_tokens": 374067.0,
-      "step": 230
-    },
-    {
-      "entropy": 0.2051882056519389,
-      "epoch": 0.38095238095238093,
-      "grad_norm": 0.7691304683685303,
-      "learning_rate": 0.00018921920137501849,
-      "loss": 0.17399615049362183,
-      "mean_token_accuracy": 0.9637806750833988,
-      "num_tokens": 390575.0,
-      "step": 240
-    },
-    {
-      "entropy": 0.19259531470015645,
-      "epoch": 0.3968253968253968,
-      "grad_norm": 0.41227754950523376,
-      "learning_rate": 0.00018800632982911322,
-      "loss": 0.14645222425460816,
-      "mean_token_accuracy": 0.9661086022853851,
-      "num_tokens": 406790.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.12554183262400329,
-      "epoch": 0.4126984126984127,
-      "grad_norm": 0.38903799653053284,
-      "learning_rate": 0.00018673314314075732,
-      "loss": 0.0970867395401001,
-      "mean_token_accuracy": 0.9753100097179412,
-      "num_tokens": 422899.0,
-      "step": 260
-    },
-    {
-      "entropy": 0.21776192565448582,
-      "epoch": 0.42857142857142855,
-      "grad_norm": 0.5275615453720093,
-      "learning_rate": 0.00018540051388850993,
-      "loss": 0.175495445728302,
-      "mean_token_accuracy": 0.9626297920942306,
-      "num_tokens": 439095.0,
-      "step": 270
-    },
-    {
-      "entropy": 0.41472155014052986,
-      "epoch": 0.4444444444444444,
-      "grad_norm": 1.5612674951553345,
-      "learning_rate": 0.0001840093553898942,
-      "loss": 0.3378293514251709,
-      "mean_token_accuracy": 0.9364372007548809,
-      "num_tokens": 455598.0,
-      "step": 280
-    },
-    {
-      "entropy": 0.18331955913454295,
-      "epoch": 0.4603174603174603,
-      "grad_norm": 0.3843788206577301,
-      "learning_rate": 0.00018256062107545518,
-      "loss": 0.13437695503234864,
-      "mean_token_accuracy": 0.9686297826468945,
-      "num_tokens": 471075.0,
-      "step": 290
-    },
-    {
-      "entropy": 0.16779997684061526,
-      "epoch": 0.47619047619047616,
-      "grad_norm": 0.3690398037433624,
-      "learning_rate": 0.00018105530383532607,
-      "loss": 0.13349469900131225,
-      "mean_token_accuracy": 0.9697726428508758,
-      "num_tokens": 486950.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.18286482915282248,
-      "epoch": 0.49206349206349204,
-      "grad_norm": 0.5309385657310486,
-      "learning_rate": 0.000179494435338751,
-      "loss": 0.14468667507171631,
-      "mean_token_accuracy": 0.9676945447921753,
-      "num_tokens": 503167.0,
-      "step": 310
-    },
-    {
-      "entropy": 0.21837912490591407,
-      "epoch": 0.5079365079365079,
-      "grad_norm": 0.5445209741592407,
-      "learning_rate": 0.00017787908532703042,
-      "loss": 0.16839513778686524,
-      "mean_token_accuracy": 0.9623315379023551,
-      "num_tokens": 519080.0,
-      "step": 320
-    },
-    {
-      "entropy": 0.16709138257429004,
-      "epoch": 0.5238095238095238,
-      "grad_norm": 0.712787926197052,
-      "learning_rate": 0.00017621036088037378,
-      "loss": 0.13333501815795898,
-      "mean_token_accuracy": 0.9686624228954315,
-      "num_tokens": 535244.0,
-      "step": 330
-    },
-    {
-      "entropy": 0.1875067687127739,
-      "epoch": 0.5396825396825397,
-      "grad_norm": 0.34370172023773193,
-      "learning_rate": 0.00017448940565916222,
-      "loss": 0.14327633380889893,
-      "mean_token_accuracy": 0.9682756960391998,
-      "num_tokens": 551358.0,
-      "step": 340
-    },
-    {
-      "entropy": 0.15009528640657663,
-      "epoch": 0.5555555555555556,
-      "grad_norm": 0.33299151062965393,
-      "learning_rate": 0.00017271739912014068,
-      "loss": 0.11425788402557373,
-      "mean_token_accuracy": 0.9726194083690644,
-      "num_tokens": 567832.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.15241470024921,
-      "epoch": 0.5714285714285714,
-      "grad_norm": 0.3769768476486206,
-      "learning_rate": 0.00017089555570807736,
-      "loss": 0.1251630187034607,
-      "mean_token_accuracy": 0.9712164625525475,
-      "num_tokens": 583486.0,
-      "step": 360
-    },
-    {
-      "entropy": 0.19003299945034086,
-      "epoch": 0.5873015873015873,
-      "grad_norm": 0.7838993072509766,
-      "learning_rate": 0.00016902512402344373,
-      "loss": 0.1713760018348694,
-      "mean_token_accuracy": 0.9653461590409279,
-      "num_tokens": 599729.0,
-      "step": 370
-    },
-    {
-      "entropy": 0.17572227772325277,
-      "epoch": 0.6031746031746031,
-      "grad_norm": 0.42281991243362427,
-      "learning_rate": 0.00016710738596668632,
-      "loss": 0.1362382650375366,
-      "mean_token_accuracy": 0.9687412306666374,
-      "num_tokens": 616044.0,
-      "step": 380
-    },
-    {
-      "entropy": 0.16331438799388706,
-      "epoch": 0.6190476190476191,
-      "grad_norm": 1.076119065284729,
-      "learning_rate": 0.00016514365585967603,
-      "loss": 0.12754744291305542,
-      "mean_token_accuracy": 0.9687342867255211,
-      "num_tokens": 632147.0,
-      "step": 390
-    },
-    {
-      "entropy": 0.19245414207689465,
-      "epoch": 0.6349206349206349,
-      "grad_norm": 0.644232988357544,
-      "learning_rate": 0.00016313527954493778,
-      "loss": 0.15318721532821655,
-      "mean_token_accuracy": 0.9658746793866158,
-      "num_tokens": 648375.0,
-      "step": 400
-    },
-    {
-      "entropy": 0.21062263241037726,
-      "epoch": 0.6507936507936508,
-      "grad_norm": 1.0224113464355469,
-      "learning_rate": 0.000161083633463277,
-      "loss": 0.15229741334915162,
-      "mean_token_accuracy": 0.9644093818962574,
-      "num_tokens": 664711.0,
-      "step": 410
-    },
-    {
-      "entropy": 0.1936994613148272,
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.7962023615837097,
-      "learning_rate": 0.00015899012371043604,
-      "loss": 0.14902880191802978,
-      "mean_token_accuracy": 0.9662799052894115,
-      "num_tokens": 681157.0,
-      "step": 420
-    },
-    {
-      "entropy": 0.20361803583800792,
-      "epoch": 0.6825396825396826,
-      "grad_norm": 0.2999099791049957,
-      "learning_rate": 0.0001568561850734264,
-      "loss": 0.16481378078460693,
-      "mean_token_accuracy": 0.9628334604203701,
-      "num_tokens": 697602.0,
-      "step": 430
-    },
-    {
-      "entropy": 0.13618148500099778,
-      "epoch": 0.6984126984126984,
-      "grad_norm": 0.4104563295841217,
-      "learning_rate": 0.00015468328004719726,
-      "loss": 0.10586557388305665,
-      "mean_token_accuracy": 0.972815252840519,
-      "num_tokens": 713742.0,
-      "step": 440
-    },
-    {
-      "entropy": 0.1247363390866667,
-      "epoch": 0.7142857142857143,
-      "grad_norm": 0.3249231278896332,
-      "learning_rate": 0.00015247289783231453,
-      "loss": 0.09654146432876587,
-      "mean_token_accuracy": 0.9732306160032749,
-      "num_tokens": 730000.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.14613611157983541,
-      "epoch": 0.7301587301587301,
-      "grad_norm": 0.5225287079811096,
-      "learning_rate": 0.00015022655331433727,
-      "loss": 0.12931008338928224,
-      "mean_token_accuracy": 0.9701415166258812,
-      "num_tokens": 746117.0,
-      "step": 460
-    },
-    {
-      "entropy": 0.21532428292557598,
-      "epoch": 0.746031746031746,
-      "grad_norm": 0.5957981944084167,
-      "learning_rate": 0.00014794578602559067,
-      "loss": 0.16675063371658325,
-      "mean_token_accuracy": 0.9630694188177585,
-      "num_tokens": 762345.0,
-      "step": 470
-    },
-    {
-      "entropy": 0.13289255439303815,
-      "epoch": 0.7619047619047619,
-      "grad_norm": 0.5672221183776855,
-      "learning_rate": 0.0001456321590900476,
-      "loss": 0.10865170955657959,
-      "mean_token_accuracy": 0.9729436971247196,
-      "num_tokens": 778187.0,
-      "step": 480
-    },
-    {
-      "entropy": 0.11678903801366687,
-      "epoch": 0.7777777777777778,
-      "grad_norm": 0.49610644578933716,
-      "learning_rate": 0.00014328725815204144,
-      "loss": 0.09211295247077941,
-      "mean_token_accuracy": 0.9758312977850437,
-      "num_tokens": 794532.0,
-      "step": 490
-    },
-    {
-      "entropy": 0.17705639996565878,
-      "epoch": 0.7936507936507936,
-      "grad_norm": 0.3945449888706207,
-      "learning_rate": 0.00014091269028954458,
-      "loss": 0.13619123697280883,
-      "mean_token_accuracy": 0.9707398265600204,
-      "num_tokens": 810831.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.17228290904313326,
-      "epoch": 0.8095238095238095,
-      "grad_norm": 1.207584261894226,
-      "learning_rate": 0.00013851008291275782,
-      "loss": 0.15327351093292235,
-      "mean_token_accuracy": 0.9661840803921222,
-      "num_tokens": 827075.0,
-      "step": 510
-    },
-    {
-      "entropy": 0.19909042734652757,
-      "epoch": 0.8253968253968254,
-      "grad_norm": 1.158147931098938,
-      "learning_rate": 0.0001360810826487642,
-      "loss": 0.1508009910583496,
-      "mean_token_accuracy": 0.9690110817551613,
-      "num_tokens": 843420.0,
-      "step": 520
-    },
-    {
-      "entropy": 0.09743964811787009,
-      "epoch": 0.8412698412698413,
-      "grad_norm": 0.3383720815181732,
-      "learning_rate": 0.0001336273542130134,
-      "loss": 0.0796388864517212,
-      "mean_token_accuracy": 0.9786469288170337,
-      "num_tokens": 859656.0,
-      "step": 530
-    },
-    {
-      "entropy": 0.13433767426759005,
-      "epoch": 0.8571428571428571,
-      "grad_norm": 0.2866056263446808,
-      "learning_rate": 0.00013115057926840884,
-      "loss": 0.10593793392181397,
-      "mean_token_accuracy": 0.9751186288893223,
-      "num_tokens": 876270.0,
-      "step": 540
-    },
-    {
-      "entropy": 0.11862653940916061,
-      "epoch": 0.873015873015873,
-      "grad_norm": 0.3208288252353668,
-      "learning_rate": 0.00012865245527277986,
-      "loss": 0.08963249325752258,
-      "mean_token_accuracy": 0.9761230409145355,
-      "num_tokens": 892446.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.13657542318105698,
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.7049503326416016,
-      "learning_rate": 0.00012613469431552895,
-      "loss": 0.10923233032226562,
-      "mean_token_accuracy": 0.9730862841010094,
-      "num_tokens": 909132.0,
-      "step": 560
-    },
-    {
-      "entropy": 0.10375349051319063,
-      "epoch": 0.9047619047619048,
-      "grad_norm": 0.31443658471107483,
-      "learning_rate": 0.00012359902194425133,
-      "loss": 0.08820843696594238,
-      "mean_token_accuracy": 0.976572859287262,
-      "num_tokens": 925031.0,
-      "step": 570
-    },
-    {
-      "entropy": 0.15578375817276538,
-      "epoch": 0.9206349206349206,
-      "grad_norm": 0.5118997097015381,
-      "learning_rate": 0.00012104717598213056,
-      "loss": 0.12504205703735352,
-      "mean_token_accuracy": 0.9705536551773548,
-      "num_tokens": 941516.0,
-      "step": 580
-    },
-    {
-      "entropy": 0.12206159401684999,
-      "epoch": 0.9365079365079365,
-      "grad_norm": 0.46927565336227417,
-      "learning_rate": 0.00011848090533692155,
-      "loss": 0.09753256440162658,
-      "mean_token_accuracy": 0.9753957264125347,
-      "num_tokens": 958128.0,
-      "step": 590
-    },
-    {
-      "entropy": 0.11996419210918248,
-      "epoch": 0.9523809523809523,
-      "grad_norm": 0.42994368076324463,
-      "learning_rate": 0.00011590196880233644,
-      "loss": 0.09162289500236512,
-      "mean_token_accuracy": 0.9756640173494816,
-      "num_tokens": 974535.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.10587584185414016,
-      "epoch": 0.9682539682539683,
-      "grad_norm": 0.5217767953872681,
-      "learning_rate": 0.00011331213385265524,
-      "loss": 0.08587267398834228,
-      "mean_token_accuracy": 0.9776035018265248,
-      "num_tokens": 990795.0,
-      "step": 610
-    },
-    {
-      "entropy": 0.10501609425991773,
-      "epoch": 0.9841269841269841,
-      "grad_norm": 0.2820020616054535,
-      "learning_rate": 0.00011071317543138738,
-      "loss": 0.08439798951148987,
-      "mean_token_accuracy": 0.977333414554596,
-      "num_tokens": 1006990.0,
-      "step": 620
-    },
-    {
-      "entropy": 0.12649747403338552,
-      "epoch": 1.0,
-      "grad_norm": 1.2852208614349365,
-      "learning_rate": 0.00010810687473481389,
-      "loss": 0.1123587965965271,
-      "mean_token_accuracy": 0.9716072164475917,
-      "num_tokens": 1023153.0,
-      "step": 630
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.14963509702592864,
-      "eval_loss": 0.12754344940185547,
-      "eval_mean_token_accuracy": 0.9698916635567084,
-      "eval_num_tokens": 1023153.0,
-      "eval_runtime": 123.9839,
-      "eval_samples_per_second": 2.145,
-      "eval_steps_per_second": 2.145,
-      "step": 630
-    },
-    {
-      "entropy": 0.08182793376035988,
-      "epoch": 1.0158730158730158,
-      "grad_norm": 0.2164141982793808,
-      "learning_rate": 0.0001054950179912446,
-      "loss": 0.06998351216316223,
-      "mean_token_accuracy": 0.9800584927201271,
-      "num_tokens": 1039301.0,
-      "step": 640
-    },
-    {
-      "entropy": 0.15589865446090698,
-      "epoch": 1.0317460317460316,
-      "grad_norm": 0.3905109763145447,
-      "learning_rate": 0.00010287939523682634,
-      "loss": 0.11804149150848389,
-      "mean_token_accuracy": 0.9720940880477429,
-      "num_tokens": 1055881.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.13176414640620351,
-      "epoch": 1.0476190476190477,
-      "grad_norm": 0.22936023771762848,
-      "learning_rate": 0.00010026179908874183,
-      "loss": 0.09952049255371094,
-      "mean_token_accuracy": 0.9751471273601056,
-      "num_tokens": 1072034.0,
-      "step": 660
-    },
-    {
-      "entropy": 0.13261872120201587,
-      "epoch": 1.0634920634920635,
-      "grad_norm": 0.3445717990398407,
-      "learning_rate": 9.764402351663901e-05,
-      "loss": 0.09959723353385926,
-      "mean_token_accuracy": 0.9765739187598228,
-      "num_tokens": 1087942.0,
-      "step": 670
-    },
-    {
-      "entropy": 0.09457834200002253,
-      "epoch": 1.0793650793650793,
-      "grad_norm": 0.2506314516067505,
-      "learning_rate": 9.502786261313423e-05,
-      "loss": 0.07293067574501037,
-      "mean_token_accuracy": 0.979874362796545,
-      "num_tokens": 1104345.0,
-      "step": 680
-    },
-    {
-      "entropy": 0.15131392041221262,
-      "epoch": 1.0952380952380953,
-      "grad_norm": 0.6880223155021667,
-      "learning_rate": 9.241510936423062e-05,
-      "loss": 0.11448752880096436,
-      "mean_token_accuracy": 0.9732576005160809,
-      "num_tokens": 1120840.0,
-      "step": 690
-    },
-    {
-      "entropy": 0.10610079388134182,
-      "epoch": 1.1111111111111112,
-      "grad_norm": 0.6070828437805176,
-      "learning_rate": 8.980755442049502e-05,
-      "loss": 0.07732992172241211,
-      "mean_token_accuracy": 0.978425282239914,
-      "num_tokens": 1137127.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.10017788861878216,
-      "epoch": 1.126984126984127,
-      "grad_norm": 0.2830179035663605,
-      "learning_rate": 8.720698486983557e-05,
-      "loss": 0.08647966384887695,
-      "mean_token_accuracy": 0.9760376676917076,
-      "num_tokens": 1153242.0,
-      "step": 710
-    },
-    {
-      "entropy": 0.11412310716696084,
-      "epoch": 1.1428571428571428,
-      "grad_norm": 0.5743200778961182,
-      "learning_rate": 8.461518301272099e-05,
-      "loss": 0.08402568697929383,
-      "mean_token_accuracy": 0.9778100050985813,
-      "num_tokens": 1169145.0,
-      "step": 720
-    },
-    {
-      "entropy": 0.12544448575936257,
-      "epoch": 1.1587301587301586,
-      "grad_norm": 0.3491770625114441,
-      "learning_rate": 8.203392514068074e-05,
-      "loss": 0.09491501450538635,
-      "mean_token_accuracy": 0.9753343552350998,
-      "num_tokens": 1184902.0,
-      "step": 730
-    },
-    {
-      "entropy": 0.12449102494865656,
-      "epoch": 1.1746031746031746,
-      "grad_norm": 0.7691491842269897,
-      "learning_rate": 7.946498031892364e-05,
-      "loss": 0.10109654664993287,
-      "mean_token_accuracy": 0.9746225215494633,
-      "num_tokens": 1201208.0,
-      "step": 740
-    },
-    {
-      "entropy": 0.11652453513816,
-      "epoch": 1.1904761904761905,
-      "grad_norm": 0.4358707368373871,
-      "learning_rate": 7.691010917390874e-05,
-      "loss": 0.08225674629211426,
-      "mean_token_accuracy": 0.9781361222267151,
-      "num_tokens": 1217157.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.11605553817935288,
-      "epoch": 1.2063492063492063,
-      "grad_norm": 0.725312352180481,
-      "learning_rate": 7.437106268670034e-05,
-      "loss": 0.09104912281036377,
-      "mean_token_accuracy": 0.9763554163277149,
-      "num_tokens": 1233144.0,
-      "step": 760
-    },
-    {
-      "entropy": 0.10015753363259136,
-      "epoch": 1.2222222222222223,
-      "grad_norm": 0.23935319483280182,
-      "learning_rate": 7.184958099293246e-05,
-      "loss": 0.07568765282630921,
-      "mean_token_accuracy": 0.9788681827485561,
-      "num_tokens": 1249197.0,
-      "step": 770
-    },
-    {
-      "entropy": 0.11299324771389366,
-      "epoch": 1.2380952380952381,
-      "grad_norm": 0.2620716989040375,
-      "learning_rate": 6.934739219020726e-05,
-      "loss": 0.08495272397994995,
-      "mean_token_accuracy": 0.9769734017550945,
-      "num_tokens": 1265221.0,
-      "step": 780
-    },
-    {
-      "entropy": 0.12418944174423814,
-      "epoch": 1.253968253968254,
-      "grad_norm": 0.8303375244140625,
-      "learning_rate": 6.68662111537429e-05,
-      "loss": 0.09562642574310302,
-      "mean_token_accuracy": 0.9761748388409615,
-      "num_tokens": 1281587.0,
-      "step": 790
-    },
-    {
-      "entropy": 0.09764590142294764,
-      "epoch": 1.2698412698412698,
-      "grad_norm": 0.29645025730133057,
-      "learning_rate": 6.440773836108413e-05,
-      "loss": 0.07879915237426757,
-      "mean_token_accuracy": 0.9772366717457771,
-      "num_tokens": 1297619.0,
-      "step": 800
-    },
-    {
-      "entropy": 0.0912503881379962,
-      "epoch": 1.2857142857142856,
-      "grad_norm": 0.26137638092041016,
-      "learning_rate": 6.197365872667952e-05,
-      "loss": 0.07751978039741517,
-      "mean_token_accuracy": 0.9783523350954055,
-      "num_tokens": 1314138.0,
-      "step": 810
-    },
-    {
-      "entropy": 0.09291230556555093,
-      "epoch": 1.3015873015873016,
-      "grad_norm": 0.2815020680427551,
-      "learning_rate": 5.956564044712551e-05,
-      "loss": 0.07410196661949157,
-      "mean_token_accuracy": 0.9806918106973171,
-      "num_tokens": 1330586.0,
-      "step": 820
-    },
-    {
-      "entropy": 0.10326733374968171,
-      "epoch": 1.3174603174603174,
-      "grad_norm": 0.5554925799369812,
-      "learning_rate": 5.718533385786772e-05,
-      "loss": 0.07725996375083924,
-      "mean_token_accuracy": 0.9791568756103516,
-      "num_tokens": 1346407.0,
-      "step": 830
-    },
-    {
-      "entropy": 0.09574338933452964,
-      "epoch": 1.3333333333333333,
-      "grad_norm": 0.26772093772888184,
-      "learning_rate": 5.483437030214343e-05,
-      "loss": 0.07193758487701415,
-      "mean_token_accuracy": 0.9782747387886047,
-      "num_tokens": 1362665.0,
-      "step": 840
-    },
-    {
-      "entropy": 0.08038676274009049,
-      "epoch": 1.3492063492063493,
-      "grad_norm": 0.2647678554058075,
-      "learning_rate": 5.251436101294056e-05,
-      "loss": 0.06795459985733032,
-      "mean_token_accuracy": 0.9803436301648617,
-      "num_tokens": 1378705.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.0904398019425571,
-      "epoch": 1.3650793650793651,
-      "grad_norm": 0.29914480447769165,
-      "learning_rate": 5.0226896008738786e-05,
-      "loss": 0.073968905210495,
-      "mean_token_accuracy": 0.9796601250767708,
-      "num_tokens": 1394982.0,
-      "step": 860
-    },
-    {
-      "entropy": 0.10209746155887842,
-      "epoch": 1.380952380952381,
-      "grad_norm": 0.5169049501419067,
-      "learning_rate": 4.79735430037906e-05,
-      "loss": 0.07558119297027588,
-      "mean_token_accuracy": 0.9789449907839298,
-      "num_tokens": 1411483.0,
-      "step": 870
-    },
-    {
-      "entropy": 0.1625033107586205,
-      "epoch": 1.3968253968253967,
-      "grad_norm": 0.6515079140663147,
-      "learning_rate": 4.575584633368815e-05,
-      "loss": 0.1234513521194458,
-      "mean_token_accuracy": 0.9717937491834163,
-      "num_tokens": 1427923.0,
-      "step": 880
-    },
-    {
-      "entropy": 0.09612479698844253,
-      "epoch": 1.4126984126984126,
-      "grad_norm": 0.2811136841773987,
-      "learning_rate": 4.35753258969526e-05,
-      "loss": 0.07417153716087341,
-      "mean_token_accuracy": 0.9791869692504406,
-      "num_tokens": 1443910.0,
-      "step": 890
-    },
-    {
-      "entropy": 0.08588011246174573,
-      "epoch": 1.4285714285714286,
-      "grad_norm": 0.1975420117378235,
-      "learning_rate": 4.143347611337194e-05,
-      "loss": 0.0669679045677185,
-      "mean_token_accuracy": 0.9794288754463196,
-      "num_tokens": 1460071.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.09144520740956068,
-      "epoch": 1.4444444444444444,
-      "grad_norm": 0.2851484417915344,
-      "learning_rate": 3.933176489980005e-05,
-      "loss": 0.07232853174209594,
-      "mean_token_accuracy": 0.9785544127225876,
-      "num_tokens": 1476394.0,
-      "step": 910
-    },
-    {
-      "entropy": 0.0951843905262649,
-      "epoch": 1.4603174603174602,
-      "grad_norm": 0.4222939610481262,
-      "learning_rate": 3.7271632664119846e-05,
-      "loss": 0.07465221881866455,
-      "mean_token_accuracy": 0.9787473000586033,
-      "num_tokens": 1492202.0,
-      "step": 920
-    },
-    {
-      "entropy": 0.14563625650480388,
-      "epoch": 1.4761904761904763,
-      "grad_norm": 0.43433165550231934,
-      "learning_rate": 3.525449131805982e-05,
-      "loss": 0.09597810506820678,
-      "mean_token_accuracy": 0.9762231051921845,
-      "num_tokens": 1508587.0,
-      "step": 930
-    },
-    {
-      "entropy": 0.08089337153360247,
-      "epoch": 1.492063492063492,
-      "grad_norm": 0.25026291608810425,
-      "learning_rate": 3.328172330954001e-05,
-      "loss": 0.06541991233825684,
-      "mean_token_accuracy": 0.9804870396852493,
-      "num_tokens": 1524608.0,
-      "step": 940
-    },
-    {
-      "entropy": 0.11199918817728757,
-      "epoch": 1.507936507936508,
-      "grad_norm": 0.2416200041770935,
-      "learning_rate": 3.1354680675211635e-05,
-      "loss": 0.08397775292396545,
-      "mean_token_accuracy": 0.9771605253219604,
-      "num_tokens": 1540705.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.10342249851673842,
-      "epoch": 1.5238095238095237,
-      "grad_norm": 0.2826922535896301,
-      "learning_rate": 2.9474684113838257e-05,
-      "loss": 0.07648788094520569,
-      "mean_token_accuracy": 0.9799712590873242,
-      "num_tokens": 1557086.0,
-      "step": 960
-    },
-    {
-      "entropy": 0.10365813223179429,
-      "epoch": 1.5396825396825395,
-      "grad_norm": 0.22921620309352875,
-      "learning_rate": 2.764302208115509e-05,
-      "loss": 0.07187622189521789,
-      "mean_token_accuracy": 0.9799506664276123,
-      "num_tokens": 1573507.0,
-      "step": 970
-    },
-    {
-      "entropy": 0.11406760299578309,
-      "epoch": 1.5555555555555556,
-      "grad_norm": 0.6570681929588318,
-      "learning_rate": 2.5860949906825795e-05,
-      "loss": 0.08612269759178162,
-      "mean_token_accuracy": 0.9780311018228531,
-      "num_tokens": 1589640.0,
-      "step": 980
-    },
-    {
-      "entropy": 0.11450605299323798,
-      "epoch": 1.5714285714285714,
-      "grad_norm": 0.24385221302509308,
-      "learning_rate": 2.412968893410219e-05,
-      "loss": 0.08079542517662049,
-      "mean_token_accuracy": 0.9784732617437839,
-      "num_tokens": 1605857.0,
-      "step": 990
-    },
-    {
-      "entropy": 0.11478545106947421,
-      "epoch": 1.5873015873015874,
-      "grad_norm": 1.2068188190460205,
-      "learning_rate": 2.2450425682776565e-05,
-      "loss": 0.10695868730545044,
-      "mean_token_accuracy": 0.9749820478260517,
-      "num_tokens": 1622078.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.0898138654883951,
-      "epoch": 1.6031746031746033,
-      "grad_norm": 0.23325718939304352,
-      "learning_rate": 2.0824311036000276e-05,
-      "loss": 0.06850396394729615,
-      "mean_token_accuracy": 0.9805276915431023,
-      "num_tokens": 1638322.0,
-      "step": 1010
-    },
-    {
-      "entropy": 0.08142746333032846,
-      "epoch": 1.619047619047619,
-      "grad_norm": 0.23731723427772522,
-      "learning_rate": 1.9252459451526007e-05,
-      "loss": 0.064413982629776,
-      "mean_token_accuracy": 0.9817632213234901,
-      "num_tokens": 1654869.0,
-      "step": 1020
-    },
-    {
-      "entropy": 0.1174024541862309,
-      "epoch": 1.6349206349206349,
-      "grad_norm": 0.34191104769706726,
-      "learning_rate": 1.773594819791403e-05,
-      "loss": 0.08514685034751893,
-      "mean_token_accuracy": 0.9778413355350495,
-      "num_tokens": 1671380.0,
-      "step": 1030
-    },
-    {
-      "entropy": 0.12424507061950862,
-      "epoch": 1.6507936507936507,
-      "grad_norm": 0.21008247137069702,
-      "learning_rate": 1.6275816616226113e-05,
-      "loss": 0.08949556350708007,
-      "mean_token_accuracy": 0.976959352940321,
-      "num_tokens": 1687777.0,
-      "step": 1040
-    },
-    {
-      "entropy": 0.12187586650252343,
-      "epoch": 1.6666666666666665,
-      "grad_norm": 0.294793039560318,
-      "learning_rate": 1.4873065407713149e-05,
-      "loss": 0.08311855792999268,
-      "mean_token_accuracy": 0.977589001506567,
-      "num_tokens": 1704227.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.1303621060680598,
-      "epoch": 1.6825396825396826,
-      "grad_norm": 0.4580724835395813,
-      "learning_rate": 1.3528655947984504e-05,
-      "loss": 0.09254520535469055,
-      "mean_token_accuracy": 0.9763389393687248,
-      "num_tokens": 1720298.0,
-      "step": 1060
-    },
-    {
-      "entropy": 0.0934061048552394,
-      "epoch": 1.6984126984126984,
-      "grad_norm": 0.27665528655052185,
-      "learning_rate": 1.224350962812908e-05,
-      "loss": 0.07436655163764953,
-      "mean_token_accuracy": 0.9802996210753918,
-      "num_tokens": 1736661.0,
-      "step": 1070
-    },
-    {
-      "entropy": 0.09044756721705198,
-      "epoch": 1.7142857142857144,
-      "grad_norm": 0.33052632212638855,
-      "learning_rate": 1.1018507223240038e-05,
-      "loss": 0.07090449333190918,
-      "mean_token_accuracy": 0.9798901811242103,
-      "num_tokens": 1752738.0,
-      "step": 1080
-    },
-    {
-      "entropy": 0.10223812032490968,
-      "epoch": 1.7301587301587302,
-      "grad_norm": 0.2864120900630951,
-      "learning_rate": 9.854488288775422e-06,
-      "loss": 0.07608797550201415,
-      "mean_token_accuracy": 0.9792112439870835,
-      "num_tokens": 1769066.0,
-      "step": 1090
-    },
-    {
-      "entropy": 0.09947904231958091,
-      "epoch": 1.746031746031746,
-      "grad_norm": 0.2548878788948059,
-      "learning_rate": 8.752250585168931e-06,
-      "loss": 0.06912150979042053,
-      "mean_token_accuracy": 0.9813775293529033,
-      "num_tokens": 1785437.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.11234282166697085,
-      "epoch": 1.7619047619047619,
-      "grad_norm": 0.2693788409233093,
-      "learning_rate": 7.71254953108458e-06,
-      "loss": 0.08027521371841431,
-      "mean_token_accuracy": 0.9781207241117954,
-      "num_tokens": 1801683.0,
-      "step": 1110
-    },
-    {
-      "entropy": 0.09257194171659648,
-      "epoch": 1.7777777777777777,
-      "grad_norm": 0.2431974709033966,
-      "learning_rate": 6.736097685690601e-06,
-      "loss": 0.06695151925086976,
-      "mean_token_accuracy": 0.9801147982478142,
-      "num_tokens": 1817817.0,
-      "step": 1120
-    },
-    {
-      "entropy": 0.07755493461154402,
-      "epoch": 1.7936507936507935,
-      "grad_norm": 0.24728603661060333,
-      "learning_rate": 5.823564260306968e-06,
-      "loss": 0.06104744672775268,
-      "mean_token_accuracy": 0.9808968141674995,
-      "num_tokens": 1834578.0,
-      "step": 1130
-    },
-    {
-      "entropy": 0.11796619035303593,
-      "epoch": 1.8095238095238095,
-      "grad_norm": 0.6510683298110962,
-      "learning_rate": 4.975574659761406e-06,
-      "loss": 0.07744659781455994,
-      "mean_token_accuracy": 0.9790396362543106,
-      "num_tokens": 1850969.0,
-      "step": 1140
-    },
-    {
-      "entropy": 0.08559209264349192,
-      "epoch": 1.8253968253968254,
-      "grad_norm": 0.2574602961540222,
-      "learning_rate": 4.19271005376809e-06,
-      "loss": 0.06476410031318665,
-      "mean_token_accuracy": 0.9802613228559494,
-      "num_tokens": 1867530.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.08814950557425619,
-      "epoch": 1.8412698412698414,
-      "grad_norm": 0.3555011451244354,
-      "learning_rate": 3.475506978623e-06,
-      "loss": 0.06674173474311829,
-      "mean_token_accuracy": 0.9801458336412907,
-      "num_tokens": 1883571.0,
-      "step": 1160
-    },
-    {
-      "entropy": 0.10401968103833496,
-      "epoch": 1.8571428571428572,
-      "grad_norm": 0.2704622745513916,
-      "learning_rate": 2.8244569694887426e-06,
-      "loss": 0.08005510568618775,
-      "mean_token_accuracy": 0.9784482754766941,
-      "num_tokens": 1899984.0,
-      "step": 1170
-    },
-    {
-      "entropy": 0.08668653401546181,
-      "epoch": 1.873015873015873,
-      "grad_norm": 0.298379123210907,
-      "learning_rate": 2.240006223520941e-06,
-      "loss": 0.07004132866859436,
-      "mean_token_accuracy": 0.9788191355764866,
-      "num_tokens": 1916079.0,
-      "step": 1180
-    },
-    {
-      "entropy": 0.1208422985393554,
-      "epoch": 1.8888888888888888,
-      "grad_norm": 0.25009885430336,
-      "learning_rate": 1.7225552940668632e-06,
-      "loss": 0.08680980205535889,
-      "mean_token_accuracy": 0.976942615956068,
-      "num_tokens": 1932256.0,
-      "step": 1190
-    },
-    {
-      "entropy": 0.09005042375065386,
-      "epoch": 1.9047619047619047,
-      "grad_norm": 0.2764185965061188,
-      "learning_rate": 1.272458816146349e-06,
-      "loss": 0.06606220006942749,
-      "mean_token_accuracy": 0.980307686328888,
-      "num_tokens": 1948355.0,
-      "step": 1200
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1260,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.150797794813952e+16,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

lora_adapter/checkpoint-1200/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d03761d0c056d3be10441632fd015fad7320a6a18d86e794364c2efae99b3
-size 5713

lora_adapter/checkpoint-1260/README.md

@@ -1,209 +0,0 @@
----
-base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/Llama-3.2-1B-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 0.21.0

lora_adapter/checkpoint-1260/adapter_config.json

@@ -1,51 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.0",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

lora_adapter/checkpoint-1260/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2bdb9bfe9dcb6ee40142abfefeb2050b40d333d04db27c6f4bd7fe8a022e3bf
-size 45118424

lora_adapter/checkpoint-1260/chat_template.jinja

@@ -1,93 +0,0 @@
-{{- 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 %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
-    {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
-    {%- endif %}
-{%- 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 #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\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 %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- 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 %}

lora_adapter/checkpoint-1260/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:988906f16aa96aa7d155d9078dbe317446d32cb0e0222f1785b8426bfb363673
-size 90359883

lora_adapter/checkpoint-1260/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
-size 14455

lora_adapter/checkpoint-1260/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:528b546c5dfea6826047bbdf2dc092d1323b93a17d60a41c07382d775e044394
-size 1465

lora_adapter/checkpoint-1260/tokenizer.json

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

lora_adapter/checkpoint-1260/tokenizer_config.json

@@ -1,17 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "left",
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null
-}

lora_adapter/checkpoint-1260/trainer_state.json

@@ -1,1305 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "eval_steps": 500,
-  "global_step": 1260,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 3.2998463183641435,
-      "epoch": 0.015873015873015872,
-      "grad_norm": 5.5954365730285645,
-      "learning_rate": 3e-05,
-      "loss": 4.793289566040039,
-      "mean_token_accuracy": 0.36775660440325736,
-      "num_tokens": 16307.0,
-      "step": 10
-    },
-    {
-      "entropy": 3.745172455906868,
-      "epoch": 0.031746031746031744,
-      "grad_norm": 2.467291831970215,
-      "learning_rate": 6.333333333333333e-05,
-      "loss": 3.7420589447021486,
-      "mean_token_accuracy": 0.43841218277812005,
-      "num_tokens": 32577.0,
-      "step": 20
-    },
-    {
-      "entropy": 3.1654938369989396,
-      "epoch": 0.047619047619047616,
-      "grad_norm": 1.8811299800872803,
-      "learning_rate": 9.666666666666667e-05,
-      "loss": 2.4434362411499024,
-      "mean_token_accuracy": 0.6050871018320322,
-      "num_tokens": 48737.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.9995254769921302,
-      "epoch": 0.06349206349206349,
-      "grad_norm": 1.535879373550415,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.565892219543457,
-      "mean_token_accuracy": 0.7555049300193787,
-      "num_tokens": 64997.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.5211943820118905,
-      "epoch": 0.07936507936507936,
-      "grad_norm": 1.7563194036483765,
-      "learning_rate": 0.00016333333333333334,
-      "loss": 1.1280284881591798,
-      "mean_token_accuracy": 0.812470355629921,
-      "num_tokens": 81080.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.17081895545125,
-      "epoch": 0.09523809523809523,
-      "grad_norm": 1.464584231376648,
-      "learning_rate": 0.00019666666666666666,
-      "loss": 0.8906035423278809,
-      "mean_token_accuracy": 0.8521104611456394,
-      "num_tokens": 97196.0,
-      "step": 60
-    },
-    {
-      "entropy": 0.9356300979852676,
-      "epoch": 0.1111111111111111,
-      "grad_norm": 1.4088091850280762,
-      "learning_rate": 0.00019997224302180006,
-      "loss": 0.670417308807373,
-      "mean_token_accuracy": 0.8883098550140858,
-      "num_tokens": 113569.0,
-      "step": 70
-    },
-    {
-      "entropy": 0.5688819501549005,
-      "epoch": 0.12698412698412698,
-      "grad_norm": 1.340789794921875,
-      "learning_rate": 0.00019987631275635948,
-      "loss": 0.36014580726623535,
-      "mean_token_accuracy": 0.9383806541562081,
-      "num_tokens": 129665.0,
-      "step": 80
-    },
-    {
-      "entropy": 0.5208159729838371,
-      "epoch": 0.14285714285714285,
-      "grad_norm": 1.1698484420776367,
-      "learning_rate": 0.00019971193225508879,
-      "loss": 0.38550715446472167,
-      "mean_token_accuracy": 0.9369473621249199,
-      "num_tokens": 145819.0,
-      "step": 90
-    },
-    {
-      "entropy": 0.35822844561189415,
-      "epoch": 0.15873015873015872,
-      "grad_norm": 1.056837558746338,
-      "learning_rate": 0.00019947921417617267,
-      "loss": 0.24877142906188965,
-      "mean_token_accuracy": 0.9541201412677764,
-      "num_tokens": 162338.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.36921846531331537,
-      "epoch": 0.1746031746031746,
-      "grad_norm": 0.771403431892395,
-      "learning_rate": 0.0001991783180129578,
-      "loss": 0.2972050666809082,
-      "mean_token_accuracy": 0.946565055847168,
-      "num_tokens": 179013.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.4222600903362036,
-      "epoch": 0.19047619047619047,
-      "grad_norm": 0.6926781535148621,
-      "learning_rate": 0.00019880944998464434,
-      "loss": 0.3286353349685669,
-      "mean_token_accuracy": 0.9404827795922757,
-      "num_tokens": 195500.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.23451931905001402,
-      "epoch": 0.20634920634920634,
-      "grad_norm": 1.0064337253570557,
-      "learning_rate": 0.00019837286289495361,
-      "loss": 0.16426128149032593,
-      "mean_token_accuracy": 0.9648101754486561,
-      "num_tokens": 211542.0,
-      "step": 130
-    },
-    {
-      "entropy": 0.26509888684377075,
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.6641770601272583,
-      "learning_rate": 0.0001978688559588688,
-      "loss": 0.1910732865333557,
-      "mean_token_accuracy": 0.9604174040257931,
-      "num_tokens": 227757.0,
-      "step": 140
-    },
-    {
-      "entropy": 0.3036362808197737,
-      "epoch": 0.23809523809523808,
-      "grad_norm": 0.9009377956390381,
-      "learning_rate": 0.0001972977745975682,
-      "loss": 0.24015522003173828,
-      "mean_token_accuracy": 0.9528692953288556,
-      "num_tokens": 244201.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.2707868428900838,
-      "epoch": 0.25396825396825395,
-      "grad_norm": 0.7132826447486877,
-      "learning_rate": 0.00019666001020169073,
-      "loss": 0.21738948822021484,
-      "mean_token_accuracy": 0.9576977901160717,
-      "num_tokens": 260595.0,
-      "step": 160
-    },
-    {
-      "entropy": 0.2235692773014307,
-      "epoch": 0.2698412698412698,
-      "grad_norm": 0.47566577792167664,
-      "learning_rate": 0.00019595599986309628,
-      "loss": 0.1625096917152405,
-      "mean_token_accuracy": 0.9630098052322864,
-      "num_tokens": 276583.0,
-      "step": 170
-    },
-    {
-      "entropy": 0.19970224229618908,
-      "epoch": 0.2857142857142857,
-      "grad_norm": 0.6967102885246277,
-      "learning_rate": 0.0001951862260753048,
-      "loss": 0.1510181427001953,
-      "mean_token_accuracy": 0.9644064873456955,
-      "num_tokens": 292611.0,
-      "step": 180
-    },
-    {
-      "entropy": 0.18911871258169413,
-      "epoch": 0.30158730158730157,
-      "grad_norm": 0.579555869102478,
-      "learning_rate": 0.00019435121640281938,
-      "loss": 0.14125581979751586,
-      "mean_token_accuracy": 0.9668954975903035,
-      "num_tokens": 308945.0,
-      "step": 190
-    },
-    {
-      "entropy": 0.21873050034046174,
-      "epoch": 0.31746031746031744,
-      "grad_norm": 0.6234372854232788,
-      "learning_rate": 0.00019345154311955985,
-      "loss": 0.18390271663665772,
-      "mean_token_accuracy": 0.9605240561068058,
-      "num_tokens": 325018.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.23017035396769642,
-      "epoch": 0.3333333333333333,
-      "grad_norm": 0.5848660469055176,
-      "learning_rate": 0.00019248782281665498,
-      "loss": 0.18674861192703246,
-      "mean_token_accuracy": 0.960551692545414,
-      "num_tokens": 341276.0,
-      "step": 210
-    },
-    {
-      "entropy": 0.23857398927211762,
-      "epoch": 0.3492063492063492,
-      "grad_norm": 0.5835615992546082,
-      "learning_rate": 0.00019146071597986138,
-      "loss": 0.1981763243675232,
-      "mean_token_accuracy": 0.9606492578983307,
-      "num_tokens": 357585.0,
-      "step": 220
-    },
-    {
-      "entropy": 0.21739678094163536,
-      "epoch": 0.36507936507936506,
-      "grad_norm": 0.49282777309417725,
-      "learning_rate": 0.00019037092653689987,
-      "loss": 0.16624126434326172,
-      "mean_token_accuracy": 0.964983056485653,
-      "num_tokens": 374067.0,
-      "step": 230
-    },
-    {
-      "entropy": 0.2051882056519389,
-      "epoch": 0.38095238095238093,
-      "grad_norm": 0.7691304683685303,
-      "learning_rate": 0.00018921920137501849,
-      "loss": 0.17399615049362183,
-      "mean_token_accuracy": 0.9637806750833988,
-      "num_tokens": 390575.0,
-      "step": 240
-    },
-    {
-      "entropy": 0.19259531470015645,
-      "epoch": 0.3968253968253968,
-      "grad_norm": 0.41227754950523376,
-      "learning_rate": 0.00018800632982911322,
-      "loss": 0.14645222425460816,
-      "mean_token_accuracy": 0.9661086022853851,
-      "num_tokens": 406790.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.12554183262400329,
-      "epoch": 0.4126984126984127,
-      "grad_norm": 0.38903799653053284,
-      "learning_rate": 0.00018673314314075732,
-      "loss": 0.0970867395401001,
-      "mean_token_accuracy": 0.9753100097179412,
-      "num_tokens": 422899.0,
-      "step": 260
-    },
-    {
-      "entropy": 0.21776192565448582,
-      "epoch": 0.42857142857142855,
-      "grad_norm": 0.5275615453720093,
-      "learning_rate": 0.00018540051388850993,
-      "loss": 0.175495445728302,
-      "mean_token_accuracy": 0.9626297920942306,
-      "num_tokens": 439095.0,
-      "step": 270
-    },
-    {
-      "entropy": 0.41472155014052986,
-      "epoch": 0.4444444444444444,
-      "grad_norm": 1.5612674951553345,
-      "learning_rate": 0.0001840093553898942,
-      "loss": 0.3378293514251709,
-      "mean_token_accuracy": 0.9364372007548809,
-      "num_tokens": 455598.0,
-      "step": 280
-    },
-    {
-      "entropy": 0.18331955913454295,
-      "epoch": 0.4603174603174603,
-      "grad_norm": 0.3843788206577301,
-      "learning_rate": 0.00018256062107545518,
-      "loss": 0.13437695503234864,
-      "mean_token_accuracy": 0.9686297826468945,
-      "num_tokens": 471075.0,
-      "step": 290
-    },
-    {
-      "entropy": 0.16779997684061526,
-      "epoch": 0.47619047619047616,
-      "grad_norm": 0.3690398037433624,
-      "learning_rate": 0.00018105530383532607,
-      "loss": 0.13349469900131225,
-      "mean_token_accuracy": 0.9697726428508758,
-      "num_tokens": 486950.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.18286482915282248,
-      "epoch": 0.49206349206349204,
-      "grad_norm": 0.5309385657310486,
-      "learning_rate": 0.000179494435338751,
-      "loss": 0.14468667507171631,
-      "mean_token_accuracy": 0.9676945447921753,
-      "num_tokens": 503167.0,
-      "step": 310
-    },
-    {
-      "entropy": 0.21837912490591407,
-      "epoch": 0.5079365079365079,
-      "grad_norm": 0.5445209741592407,
-      "learning_rate": 0.00017787908532703042,
-      "loss": 0.16839513778686524,
-      "mean_token_accuracy": 0.9623315379023551,
-      "num_tokens": 519080.0,
-      "step": 320
-    },
-    {
-      "entropy": 0.16709138257429004,
-      "epoch": 0.5238095238095238,
-      "grad_norm": 0.712787926197052,
-      "learning_rate": 0.00017621036088037378,
-      "loss": 0.13333501815795898,
-      "mean_token_accuracy": 0.9686624228954315,
-      "num_tokens": 535244.0,
-      "step": 330
-    },
-    {
-      "entropy": 0.1875067687127739,
-      "epoch": 0.5396825396825397,
-      "grad_norm": 0.34370172023773193,
-      "learning_rate": 0.00017448940565916222,
-      "loss": 0.14327633380889893,
-      "mean_token_accuracy": 0.9682756960391998,
-      "num_tokens": 551358.0,
-      "step": 340
-    },
-    {
-      "entropy": 0.15009528640657663,
-      "epoch": 0.5555555555555556,
-      "grad_norm": 0.33299151062965393,
-      "learning_rate": 0.00017271739912014068,
-      "loss": 0.11425788402557373,
-      "mean_token_accuracy": 0.9726194083690644,
-      "num_tokens": 567832.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.15241470024921,
-      "epoch": 0.5714285714285714,
-      "grad_norm": 0.3769768476486206,
-      "learning_rate": 0.00017089555570807736,
-      "loss": 0.1251630187034607,
-      "mean_token_accuracy": 0.9712164625525475,
-      "num_tokens": 583486.0,
-      "step": 360
-    },
-    {
-      "entropy": 0.19003299945034086,
-      "epoch": 0.5873015873015873,
-      "grad_norm": 0.7838993072509766,
-      "learning_rate": 0.00016902512402344373,
-      "loss": 0.1713760018348694,
-      "mean_token_accuracy": 0.9653461590409279,
-      "num_tokens": 599729.0,
-      "step": 370
-    },
-    {
-      "entropy": 0.17572227772325277,
-      "epoch": 0.6031746031746031,
-      "grad_norm": 0.42281991243362427,
-      "learning_rate": 0.00016710738596668632,
-      "loss": 0.1362382650375366,
-      "mean_token_accuracy": 0.9687412306666374,
-      "num_tokens": 616044.0,
-      "step": 380
-    },
-    {
-      "entropy": 0.16331438799388706,
-      "epoch": 0.6190476190476191,
-      "grad_norm": 1.076119065284729,
-      "learning_rate": 0.00016514365585967603,
-      "loss": 0.12754744291305542,
-      "mean_token_accuracy": 0.9687342867255211,
-      "num_tokens": 632147.0,
-      "step": 390
-    },
-    {
-      "entropy": 0.19245414207689465,
-      "epoch": 0.6349206349206349,
-      "grad_norm": 0.644232988357544,
-      "learning_rate": 0.00016313527954493778,
-      "loss": 0.15318721532821655,
-      "mean_token_accuracy": 0.9658746793866158,
-      "num_tokens": 648375.0,
-      "step": 400
-    },
-    {
-      "entropy": 0.21062263241037726,
-      "epoch": 0.6507936507936508,
-      "grad_norm": 1.0224113464355469,
-      "learning_rate": 0.000161083633463277,
-      "loss": 0.15229741334915162,
-      "mean_token_accuracy": 0.9644093818962574,
-      "num_tokens": 664711.0,
-      "step": 410
-    },
-    {
-      "entropy": 0.1936994613148272,
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.7962023615837097,
-      "learning_rate": 0.00015899012371043604,
-      "loss": 0.14902880191802978,
-      "mean_token_accuracy": 0.9662799052894115,
-      "num_tokens": 681157.0,
-      "step": 420
-    },
-    {
-      "entropy": 0.20361803583800792,
-      "epoch": 0.6825396825396826,
-      "grad_norm": 0.2999099791049957,
-      "learning_rate": 0.0001568561850734264,
-      "loss": 0.16481378078460693,
-      "mean_token_accuracy": 0.9628334604203701,
-      "num_tokens": 697602.0,
-      "step": 430
-    },
-    {
-      "entropy": 0.13618148500099778,
-      "epoch": 0.6984126984126984,
-      "grad_norm": 0.4104563295841217,
-      "learning_rate": 0.00015468328004719726,
-      "loss": 0.10586557388305665,
-      "mean_token_accuracy": 0.972815252840519,
-      "num_tokens": 713742.0,
-      "step": 440
-    },
-    {
-      "entropy": 0.1247363390866667,
-      "epoch": 0.7142857142857143,
-      "grad_norm": 0.3249231278896332,
-      "learning_rate": 0.00015247289783231453,
-      "loss": 0.09654146432876587,
-      "mean_token_accuracy": 0.9732306160032749,
-      "num_tokens": 730000.0,
-      "step": 450
-    },
-    {
-      "entropy": 0.14613611157983541,
-      "epoch": 0.7301587301587301,
-      "grad_norm": 0.5225287079811096,
-      "learning_rate": 0.00015022655331433727,
-      "loss": 0.12931008338928224,
-      "mean_token_accuracy": 0.9701415166258812,
-      "num_tokens": 746117.0,
-      "step": 460
-    },
-    {
-      "entropy": 0.21532428292557598,
-      "epoch": 0.746031746031746,
-      "grad_norm": 0.5957981944084167,
-      "learning_rate": 0.00014794578602559067,
-      "loss": 0.16675063371658325,
-      "mean_token_accuracy": 0.9630694188177585,
-      "num_tokens": 762345.0,
-      "step": 470
-    },
-    {
-      "entropy": 0.13289255439303815,
-      "epoch": 0.7619047619047619,
-      "grad_norm": 0.5672221183776855,
-      "learning_rate": 0.0001456321590900476,
-      "loss": 0.10865170955657959,
-      "mean_token_accuracy": 0.9729436971247196,
-      "num_tokens": 778187.0,
-      "step": 480
-    },
-    {
-      "entropy": 0.11678903801366687,
-      "epoch": 0.7777777777777778,
-      "grad_norm": 0.49610644578933716,
-      "learning_rate": 0.00014328725815204144,
-      "loss": 0.09211295247077941,
-      "mean_token_accuracy": 0.9758312977850437,
-      "num_tokens": 794532.0,
-      "step": 490
-    },
-    {
-      "entropy": 0.17705639996565878,
-      "epoch": 0.7936507936507936,
-      "grad_norm": 0.3945449888706207,
-      "learning_rate": 0.00014091269028954458,
-      "loss": 0.13619123697280883,
-      "mean_token_accuracy": 0.9707398265600204,
-      "num_tokens": 810831.0,
-      "step": 500
-    },
-    {
-      "entropy": 0.17228290904313326,
-      "epoch": 0.8095238095238095,
-      "grad_norm": 1.207584261894226,
-      "learning_rate": 0.00013851008291275782,
-      "loss": 0.15327351093292235,
-      "mean_token_accuracy": 0.9661840803921222,
-      "num_tokens": 827075.0,
-      "step": 510
-    },
-    {
-      "entropy": 0.19909042734652757,
-      "epoch": 0.8253968253968254,
-      "grad_norm": 1.158147931098938,
-      "learning_rate": 0.0001360810826487642,
-      "loss": 0.1508009910583496,
-      "mean_token_accuracy": 0.9690110817551613,
-      "num_tokens": 843420.0,
-      "step": 520
-    },
-    {
-      "entropy": 0.09743964811787009,
-      "epoch": 0.8412698412698413,
-      "grad_norm": 0.3383720815181732,
-      "learning_rate": 0.0001336273542130134,
-      "loss": 0.0796388864517212,
-      "mean_token_accuracy": 0.9786469288170337,
-      "num_tokens": 859656.0,
-      "step": 530
-    },
-    {
-      "entropy": 0.13433767426759005,
-      "epoch": 0.8571428571428571,
-      "grad_norm": 0.2866056263446808,
-      "learning_rate": 0.00013115057926840884,
-      "loss": 0.10593793392181397,
-      "mean_token_accuracy": 0.9751186288893223,
-      "num_tokens": 876270.0,
-      "step": 540
-    },
-    {
-      "entropy": 0.11862653940916061,
-      "epoch": 0.873015873015873,
-      "grad_norm": 0.3208288252353668,
-      "learning_rate": 0.00012865245527277986,
-      "loss": 0.08963249325752258,
-      "mean_token_accuracy": 0.9761230409145355,
-      "num_tokens": 892446.0,
-      "step": 550
-    },
-    {
-      "entropy": 0.13657542318105698,
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.7049503326416016,
-      "learning_rate": 0.00012613469431552895,
-      "loss": 0.10923233032226562,
-      "mean_token_accuracy": 0.9730862841010094,
-      "num_tokens": 909132.0,
-      "step": 560
-    },
-    {
-      "entropy": 0.10375349051319063,
-      "epoch": 0.9047619047619048,
-      "grad_norm": 0.31443658471107483,
-      "learning_rate": 0.00012359902194425133,
-      "loss": 0.08820843696594238,
-      "mean_token_accuracy": 0.976572859287262,
-      "num_tokens": 925031.0,
-      "step": 570
-    },
-    {
-      "entropy": 0.15578375817276538,
-      "epoch": 0.9206349206349206,
-      "grad_norm": 0.5118997097015381,
-      "learning_rate": 0.00012104717598213056,
-      "loss": 0.12504205703735352,
-      "mean_token_accuracy": 0.9705536551773548,
-      "num_tokens": 941516.0,
-      "step": 580
-    },
-    {
-      "entropy": 0.12206159401684999,
-      "epoch": 0.9365079365079365,
-      "grad_norm": 0.46927565336227417,
-      "learning_rate": 0.00011848090533692155,
-      "loss": 0.09753256440162658,
-      "mean_token_accuracy": 0.9753957264125347,
-      "num_tokens": 958128.0,
-      "step": 590
-    },
-    {
-      "entropy": 0.11996419210918248,
-      "epoch": 0.9523809523809523,
-      "grad_norm": 0.42994368076324463,
-      "learning_rate": 0.00011590196880233644,
-      "loss": 0.09162289500236512,
-      "mean_token_accuracy": 0.9756640173494816,
-      "num_tokens": 974535.0,
-      "step": 600
-    },
-    {
-      "entropy": 0.10587584185414016,
-      "epoch": 0.9682539682539683,
-      "grad_norm": 0.5217767953872681,
-      "learning_rate": 0.00011331213385265524,
-      "loss": 0.08587267398834228,
-      "mean_token_accuracy": 0.9776035018265248,
-      "num_tokens": 990795.0,
-      "step": 610
-    },
-    {
-      "entropy": 0.10501609425991773,
-      "epoch": 0.9841269841269841,
-      "grad_norm": 0.2820020616054535,
-      "learning_rate": 0.00011071317543138738,
-      "loss": 0.08439798951148987,
-      "mean_token_accuracy": 0.977333414554596,
-      "num_tokens": 1006990.0,
-      "step": 620
-    },
-    {
-      "entropy": 0.12649747403338552,
-      "epoch": 1.0,
-      "grad_norm": 1.2852208614349365,
-      "learning_rate": 0.00010810687473481389,
-      "loss": 0.1123587965965271,
-      "mean_token_accuracy": 0.9716072164475917,
-      "num_tokens": 1023153.0,
-      "step": 630
-    },
-    {
-      "epoch": 1.0,
-      "eval_entropy": 0.14963509702592864,
-      "eval_loss": 0.12754344940185547,
-      "eval_mean_token_accuracy": 0.9698916635567084,
-      "eval_num_tokens": 1023153.0,
-      "eval_runtime": 123.9839,
-      "eval_samples_per_second": 2.145,
-      "eval_steps_per_second": 2.145,
-      "step": 630
-    },
-    {
-      "entropy": 0.08182793376035988,
-      "epoch": 1.0158730158730158,
-      "grad_norm": 0.2164141982793808,
-      "learning_rate": 0.0001054950179912446,
-      "loss": 0.06998351216316223,
-      "mean_token_accuracy": 0.9800584927201271,
-      "num_tokens": 1039301.0,
-      "step": 640
-    },
-    {
-      "entropy": 0.15589865446090698,
-      "epoch": 1.0317460317460316,
-      "grad_norm": 0.3905109763145447,
-      "learning_rate": 0.00010287939523682634,
-      "loss": 0.11804149150848389,
-      "mean_token_accuracy": 0.9720940880477429,
-      "num_tokens": 1055881.0,
-      "step": 650
-    },
-    {
-      "entropy": 0.13176414640620351,
-      "epoch": 1.0476190476190477,
-      "grad_norm": 0.22936023771762848,
-      "learning_rate": 0.00010026179908874183,
-      "loss": 0.09952049255371094,
-      "mean_token_accuracy": 0.9751471273601056,
-      "num_tokens": 1072034.0,
-      "step": 660
-    },
-    {
-      "entropy": 0.13261872120201587,
-      "epoch": 1.0634920634920635,
-      "grad_norm": 0.3445717990398407,
-      "learning_rate": 9.764402351663901e-05,
-      "loss": 0.09959723353385926,
-      "mean_token_accuracy": 0.9765739187598228,
-      "num_tokens": 1087942.0,
-      "step": 670
-    },
-    {
-      "entropy": 0.09457834200002253,
-      "epoch": 1.0793650793650793,
-      "grad_norm": 0.2506314516067505,
-      "learning_rate": 9.502786261313423e-05,
-      "loss": 0.07293067574501037,
-      "mean_token_accuracy": 0.979874362796545,
-      "num_tokens": 1104345.0,
-      "step": 680
-    },
-    {
-      "entropy": 0.15131392041221262,
-      "epoch": 1.0952380952380953,
-      "grad_norm": 0.6880223155021667,
-      "learning_rate": 9.241510936423062e-05,
-      "loss": 0.11448752880096436,
-      "mean_token_accuracy": 0.9732576005160809,
-      "num_tokens": 1120840.0,
-      "step": 690
-    },
-    {
-      "entropy": 0.10610079388134182,
-      "epoch": 1.1111111111111112,
-      "grad_norm": 0.6070828437805176,
-      "learning_rate": 8.980755442049502e-05,
-      "loss": 0.07732992172241211,
-      "mean_token_accuracy": 0.978425282239914,
-      "num_tokens": 1137127.0,
-      "step": 700
-    },
-    {
-      "entropy": 0.10017788861878216,
-      "epoch": 1.126984126984127,
-      "grad_norm": 0.2830179035663605,
-      "learning_rate": 8.720698486983557e-05,
-      "loss": 0.08647966384887695,
-      "mean_token_accuracy": 0.9760376676917076,
-      "num_tokens": 1153242.0,
-      "step": 710
-    },
-    {
-      "entropy": 0.11412310716696084,
-      "epoch": 1.1428571428571428,
-      "grad_norm": 0.5743200778961182,
-      "learning_rate": 8.461518301272099e-05,
-      "loss": 0.08402568697929383,
-      "mean_token_accuracy": 0.9778100050985813,
-      "num_tokens": 1169145.0,
-      "step": 720
-    },
-    {
-      "entropy": 0.12544448575936257,
-      "epoch": 1.1587301587301586,
-      "grad_norm": 0.3491770625114441,
-      "learning_rate": 8.203392514068074e-05,
-      "loss": 0.09491501450538635,
-      "mean_token_accuracy": 0.9753343552350998,
-      "num_tokens": 1184902.0,
-      "step": 730
-    },
-    {
-      "entropy": 0.12449102494865656,
-      "epoch": 1.1746031746031746,
-      "grad_norm": 0.7691491842269897,
-      "learning_rate": 7.946498031892364e-05,
-      "loss": 0.10109654664993287,
-      "mean_token_accuracy": 0.9746225215494633,
-      "num_tokens": 1201208.0,
-      "step": 740
-    },
-    {
-      "entropy": 0.11652453513816,
-      "epoch": 1.1904761904761905,
-      "grad_norm": 0.4358707368373871,
-      "learning_rate": 7.691010917390874e-05,
-      "loss": 0.08225674629211426,
-      "mean_token_accuracy": 0.9781361222267151,
-      "num_tokens": 1217157.0,
-      "step": 750
-    },
-    {
-      "entropy": 0.11605553817935288,
-      "epoch": 1.2063492063492063,
-      "grad_norm": 0.725312352180481,
-      "learning_rate": 7.437106268670034e-05,
-      "loss": 0.09104912281036377,
-      "mean_token_accuracy": 0.9763554163277149,
-      "num_tokens": 1233144.0,
-      "step": 760
-    },
-    {
-      "entropy": 0.10015753363259136,
-      "epoch": 1.2222222222222223,
-      "grad_norm": 0.23935319483280182,
-      "learning_rate": 7.184958099293246e-05,
-      "loss": 0.07568765282630921,
-      "mean_token_accuracy": 0.9788681827485561,
-      "num_tokens": 1249197.0,
-      "step": 770
-    },
-    {
-      "entropy": 0.11299324771389366,
-      "epoch": 1.2380952380952381,
-      "grad_norm": 0.2620716989040375,
-      "learning_rate": 6.934739219020726e-05,
-      "loss": 0.08495272397994995,
-      "mean_token_accuracy": 0.9769734017550945,
-      "num_tokens": 1265221.0,
-      "step": 780
-    },
-    {
-      "entropy": 0.12418944174423814,
-      "epoch": 1.253968253968254,
-      "grad_norm": 0.8303375244140625,
-      "learning_rate": 6.68662111537429e-05,
-      "loss": 0.09562642574310302,
-      "mean_token_accuracy": 0.9761748388409615,
-      "num_tokens": 1281587.0,
-      "step": 790
-    },
-    {
-      "entropy": 0.09764590142294764,
-      "epoch": 1.2698412698412698,
-      "grad_norm": 0.29645025730133057,
-      "learning_rate": 6.440773836108413e-05,
-      "loss": 0.07879915237426757,
-      "mean_token_accuracy": 0.9772366717457771,
-      "num_tokens": 1297619.0,
-      "step": 800
-    },
-    {
-      "entropy": 0.0912503881379962,
-      "epoch": 1.2857142857142856,
-      "grad_norm": 0.26137638092041016,
-      "learning_rate": 6.197365872667952e-05,
-      "loss": 0.07751978039741517,
-      "mean_token_accuracy": 0.9783523350954055,
-      "num_tokens": 1314138.0,
-      "step": 810
-    },
-    {
-      "entropy": 0.09291230556555093,
-      "epoch": 1.3015873015873016,
-      "grad_norm": 0.2815020680427551,
-      "learning_rate": 5.956564044712551e-05,
-      "loss": 0.07410196661949157,
-      "mean_token_accuracy": 0.9806918106973171,
-      "num_tokens": 1330586.0,
-      "step": 820
-    },
-    {
-      "entropy": 0.10326733374968171,
-      "epoch": 1.3174603174603174,
-      "grad_norm": 0.5554925799369812,
-      "learning_rate": 5.718533385786772e-05,
-      "loss": 0.07725996375083924,
-      "mean_token_accuracy": 0.9791568756103516,
-      "num_tokens": 1346407.0,
-      "step": 830
-    },
-    {
-      "entropy": 0.09574338933452964,
-      "epoch": 1.3333333333333333,
-      "grad_norm": 0.26772093772888184,
-      "learning_rate": 5.483437030214343e-05,
-      "loss": 0.07193758487701415,
-      "mean_token_accuracy": 0.9782747387886047,
-      "num_tokens": 1362665.0,
-      "step": 840
-    },
-    {
-      "entropy": 0.08038676274009049,
-      "epoch": 1.3492063492063493,
-      "grad_norm": 0.2647678554058075,
-      "learning_rate": 5.251436101294056e-05,
-      "loss": 0.06795459985733032,
-      "mean_token_accuracy": 0.9803436301648617,
-      "num_tokens": 1378705.0,
-      "step": 850
-    },
-    {
-      "entropy": 0.0904398019425571,
-      "epoch": 1.3650793650793651,
-      "grad_norm": 0.29914480447769165,
-      "learning_rate": 5.0226896008738786e-05,
-      "loss": 0.073968905210495,
-      "mean_token_accuracy": 0.9796601250767708,
-      "num_tokens": 1394982.0,
-      "step": 860
-    },
-    {
-      "entropy": 0.10209746155887842,
-      "epoch": 1.380952380952381,
-      "grad_norm": 0.5169049501419067,
-      "learning_rate": 4.79735430037906e-05,
-      "loss": 0.07558119297027588,
-      "mean_token_accuracy": 0.9789449907839298,
-      "num_tokens": 1411483.0,
-      "step": 870
-    },
-    {
-      "entropy": 0.1625033107586205,
-      "epoch": 1.3968253968253967,
-      "grad_norm": 0.6515079140663147,
-      "learning_rate": 4.575584633368815e-05,
-      "loss": 0.1234513521194458,
-      "mean_token_accuracy": 0.9717937491834163,
-      "num_tokens": 1427923.0,
-      "step": 880
-    },
-    {
-      "entropy": 0.09612479698844253,
-      "epoch": 1.4126984126984126,
-      "grad_norm": 0.2811136841773987,
-      "learning_rate": 4.35753258969526e-05,
-      "loss": 0.07417153716087341,
-      "mean_token_accuracy": 0.9791869692504406,
-      "num_tokens": 1443910.0,
-      "step": 890
-    },
-    {
-      "entropy": 0.08588011246174573,
-      "epoch": 1.4285714285714286,
-      "grad_norm": 0.1975420117378235,
-      "learning_rate": 4.143347611337194e-05,
-      "loss": 0.0669679045677185,
-      "mean_token_accuracy": 0.9794288754463196,
-      "num_tokens": 1460071.0,
-      "step": 900
-    },
-    {
-      "entropy": 0.09144520740956068,
-      "epoch": 1.4444444444444444,
-      "grad_norm": 0.2851484417915344,
-      "learning_rate": 3.933176489980005e-05,
-      "loss": 0.07232853174209594,
-      "mean_token_accuracy": 0.9785544127225876,
-      "num_tokens": 1476394.0,
-      "step": 910
-    },
-    {
-      "entropy": 0.0951843905262649,
-      "epoch": 1.4603174603174602,
-      "grad_norm": 0.4222939610481262,
-      "learning_rate": 3.7271632664119846e-05,
-      "loss": 0.07465221881866455,
-      "mean_token_accuracy": 0.9787473000586033,
-      "num_tokens": 1492202.0,
-      "step": 920
-    },
-    {
-      "entropy": 0.14563625650480388,
-      "epoch": 1.4761904761904763,
-      "grad_norm": 0.43433165550231934,
-      "learning_rate": 3.525449131805982e-05,
-      "loss": 0.09597810506820678,
-      "mean_token_accuracy": 0.9762231051921845,
-      "num_tokens": 1508587.0,
-      "step": 930
-    },
-    {
-      "entropy": 0.08089337153360247,
-      "epoch": 1.492063492063492,
-      "grad_norm": 0.25026291608810425,
-      "learning_rate": 3.328172330954001e-05,
-      "loss": 0.06541991233825684,
-      "mean_token_accuracy": 0.9804870396852493,
-      "num_tokens": 1524608.0,
-      "step": 940
-    },
-    {
-      "entropy": 0.11199918817728757,
-      "epoch": 1.507936507936508,
-      "grad_norm": 0.2416200041770935,
-      "learning_rate": 3.1354680675211635e-05,
-      "loss": 0.08397775292396545,
-      "mean_token_accuracy": 0.9771605253219604,
-      "num_tokens": 1540705.0,
-      "step": 950
-    },
-    {
-      "entropy": 0.10342249851673842,
-      "epoch": 1.5238095238095237,
-      "grad_norm": 0.2826922535896301,
-      "learning_rate": 2.9474684113838257e-05,
-      "loss": 0.07648788094520569,
-      "mean_token_accuracy": 0.9799712590873242,
-      "num_tokens": 1557086.0,
-      "step": 960
-    },
-    {
-      "entropy": 0.10365813223179429,
-      "epoch": 1.5396825396825395,
-      "grad_norm": 0.22921620309352875,
-      "learning_rate": 2.764302208115509e-05,
-      "loss": 0.07187622189521789,
-      "mean_token_accuracy": 0.9799506664276123,
-      "num_tokens": 1573507.0,
-      "step": 970
-    },
-    {
-      "entropy": 0.11406760299578309,
-      "epoch": 1.5555555555555556,
-      "grad_norm": 0.6570681929588318,
-      "learning_rate": 2.5860949906825795e-05,
-      "loss": 0.08612269759178162,
-      "mean_token_accuracy": 0.9780311018228531,
-      "num_tokens": 1589640.0,
-      "step": 980
-    },
-    {
-      "entropy": 0.11450605299323798,
-      "epoch": 1.5714285714285714,
-      "grad_norm": 0.24385221302509308,
-      "learning_rate": 2.412968893410219e-05,
-      "loss": 0.08079542517662049,
-      "mean_token_accuracy": 0.9784732617437839,
-      "num_tokens": 1605857.0,
-      "step": 990
-    },
-    {
-      "entropy": 0.11478545106947421,
-      "epoch": 1.5873015873015874,
-      "grad_norm": 1.2068188190460205,
-      "learning_rate": 2.2450425682776565e-05,
-      "loss": 0.10695868730545044,
-      "mean_token_accuracy": 0.9749820478260517,
-      "num_tokens": 1622078.0,
-      "step": 1000
-    },
-    {
-      "entropy": 0.0898138654883951,
-      "epoch": 1.6031746031746033,
-      "grad_norm": 0.23325718939304352,
-      "learning_rate": 2.0824311036000276e-05,
-      "loss": 0.06850396394729615,
-      "mean_token_accuracy": 0.9805276915431023,
-      "num_tokens": 1638322.0,
-      "step": 1010
-    },
-    {
-      "entropy": 0.08142746333032846,
-      "epoch": 1.619047619047619,
-      "grad_norm": 0.23731723427772522,
-      "learning_rate": 1.9252459451526007e-05,
-      "loss": 0.064413982629776,
-      "mean_token_accuracy": 0.9817632213234901,
-      "num_tokens": 1654869.0,
-      "step": 1020
-    },
-    {
-      "entropy": 0.1174024541862309,
-      "epoch": 1.6349206349206349,
-      "grad_norm": 0.34191104769706726,
-      "learning_rate": 1.773594819791403e-05,
-      "loss": 0.08514685034751893,
-      "mean_token_accuracy": 0.9778413355350495,
-      "num_tokens": 1671380.0,
-      "step": 1030
-    },
-    {
-      "entropy": 0.12424507061950862,
-      "epoch": 1.6507936507936507,
-      "grad_norm": 0.21008247137069702,
-      "learning_rate": 1.6275816616226113e-05,
-      "loss": 0.08949556350708007,
-      "mean_token_accuracy": 0.976959352940321,
-      "num_tokens": 1687777.0,
-      "step": 1040
-    },
-    {
-      "entropy": 0.12187586650252343,
-      "epoch": 1.6666666666666665,
-      "grad_norm": 0.294793039560318,
-      "learning_rate": 1.4873065407713149e-05,
-      "loss": 0.08311855792999268,
-      "mean_token_accuracy": 0.977589001506567,
-      "num_tokens": 1704227.0,
-      "step": 1050
-    },
-    {
-      "entropy": 0.1303621060680598,
-      "epoch": 1.6825396825396826,
-      "grad_norm": 0.4580724835395813,
-      "learning_rate": 1.3528655947984504e-05,
-      "loss": 0.09254520535469055,
-      "mean_token_accuracy": 0.9763389393687248,
-      "num_tokens": 1720298.0,
-      "step": 1060
-    },
-    {
-      "entropy": 0.0934061048552394,
-      "epoch": 1.6984126984126984,
-      "grad_norm": 0.27665528655052185,
-      "learning_rate": 1.224350962812908e-05,
-      "loss": 0.07436655163764953,
-      "mean_token_accuracy": 0.9802996210753918,
-      "num_tokens": 1736661.0,
-      "step": 1070
-    },
-    {
-      "entropy": 0.09044756721705198,
-      "epoch": 1.7142857142857144,
-      "grad_norm": 0.33052632212638855,
-      "learning_rate": 1.1018507223240038e-05,
-      "loss": 0.07090449333190918,
-      "mean_token_accuracy": 0.9798901811242103,
-      "num_tokens": 1752738.0,
-      "step": 1080
-    },
-    {
-      "entropy": 0.10223812032490968,
-      "epoch": 1.7301587301587302,
-      "grad_norm": 0.2864120900630951,
-      "learning_rate": 9.854488288775422e-06,
-      "loss": 0.07608797550201415,
-      "mean_token_accuracy": 0.9792112439870835,
-      "num_tokens": 1769066.0,
-      "step": 1090
-    },
-    {
-      "entropy": 0.09947904231958091,
-      "epoch": 1.746031746031746,
-      "grad_norm": 0.2548878788948059,
-      "learning_rate": 8.752250585168931e-06,
-      "loss": 0.06912150979042053,
-      "mean_token_accuracy": 0.9813775293529033,
-      "num_tokens": 1785437.0,
-      "step": 1100
-    },
-    {
-      "entropy": 0.11234282166697085,
-      "epoch": 1.7619047619047619,
-      "grad_norm": 0.2693788409233093,
-      "learning_rate": 7.71254953108458e-06,
-      "loss": 0.08027521371841431,
-      "mean_token_accuracy": 0.9781207241117954,
-      "num_tokens": 1801683.0,
-      "step": 1110
-    },
-    {
-      "entropy": 0.09257194171659648,
-      "epoch": 1.7777777777777777,
-      "grad_norm": 0.2431974709033966,
-      "learning_rate": 6.736097685690601e-06,
-      "loss": 0.06695151925086976,
-      "mean_token_accuracy": 0.9801147982478142,
-      "num_tokens": 1817817.0,
-      "step": 1120
-    },
-    {
-      "entropy": 0.07755493461154402,
-      "epoch": 1.7936507936507935,
-      "grad_norm": 0.24728603661060333,
-      "learning_rate": 5.823564260306968e-06,
-      "loss": 0.06104744672775268,
-      "mean_token_accuracy": 0.9808968141674995,
-      "num_tokens": 1834578.0,
-      "step": 1130
-    },
-    {
-      "entropy": 0.11796619035303593,
-      "epoch": 1.8095238095238095,
-      "grad_norm": 0.6510683298110962,
-      "learning_rate": 4.975574659761406e-06,
-      "loss": 0.07744659781455994,
-      "mean_token_accuracy": 0.9790396362543106,
-      "num_tokens": 1850969.0,
-      "step": 1140
-    },
-    {
-      "entropy": 0.08559209264349192,
-      "epoch": 1.8253968253968254,
-      "grad_norm": 0.2574602961540222,
-      "learning_rate": 4.19271005376809e-06,
-      "loss": 0.06476410031318665,
-      "mean_token_accuracy": 0.9802613228559494,
-      "num_tokens": 1867530.0,
-      "step": 1150
-    },
-    {
-      "entropy": 0.08814950557425619,
-      "epoch": 1.8412698412698414,
-      "grad_norm": 0.3555011451244354,
-      "learning_rate": 3.475506978623e-06,
-      "loss": 0.06674173474311829,
-      "mean_token_accuracy": 0.9801458336412907,
-      "num_tokens": 1883571.0,
-      "step": 1160
-    },
-    {
-      "entropy": 0.10401968103833496,
-      "epoch": 1.8571428571428572,
-      "grad_norm": 0.2704622745513916,
-      "learning_rate": 2.8244569694887426e-06,
-      "loss": 0.08005510568618775,
-      "mean_token_accuracy": 0.9784482754766941,
-      "num_tokens": 1899984.0,
-      "step": 1170
-    },
-    {
-      "entropy": 0.08668653401546181,
-      "epoch": 1.873015873015873,
-      "grad_norm": 0.298379123210907,
-      "learning_rate": 2.240006223520941e-06,
-      "loss": 0.07004132866859436,
-      "mean_token_accuracy": 0.9788191355764866,
-      "num_tokens": 1916079.0,
-      "step": 1180
-    },
-    {
-      "entropy": 0.1208422985393554,
-      "epoch": 1.8888888888888888,
-      "grad_norm": 0.25009885430336,
-      "learning_rate": 1.7225552940668632e-06,
-      "loss": 0.08680980205535889,
-      "mean_token_accuracy": 0.976942615956068,
-      "num_tokens": 1932256.0,
-      "step": 1190
-    },
-    {
-      "entropy": 0.09005042375065386,
-      "epoch": 1.9047619047619047,
-      "grad_norm": 0.2764185965061188,
-      "learning_rate": 1.272458816146349e-06,
-      "loss": 0.06606220006942749,
-      "mean_token_accuracy": 0.980307686328888,
-      "num_tokens": 1948355.0,
-      "step": 1200
-    },
-    {
-      "entropy": 0.11479772976599634,
-      "epoch": 1.9206349206349205,
-      "grad_norm": 0.2552097737789154,
-      "learning_rate": 8.900252634025274e-07,
-      "loss": 0.08005352020263672,
-      "mean_token_accuracy": 0.978291603922844,
-      "num_tokens": 1964550.0,
-      "step": 1210
-    },
-    {
-      "entropy": 0.10592010961845517,
-      "epoch": 1.9365079365079365,
-      "grad_norm": 0.43525171279907227,
-      "learning_rate": 5.755167366894632e-07,
-      "loss": 0.075601726770401,
-      "mean_token_accuracy": 0.9780680626630783,
-      "num_tokens": 1980588.0,
-      "step": 1220
-    },
-    {
-      "entropy": 0.07827817667275667,
-      "epoch": 1.9523809523809523,
-      "grad_norm": 0.36340612173080444,
-      "learning_rate": 3.2914878444131326e-07,
-      "loss": 0.06421470046043395,
-      "mean_token_accuracy": 0.9807937018573284,
-      "num_tokens": 1997132.0,
-      "step": 1230
-    },
-    {
-      "entropy": 0.07028297204524278,
-      "epoch": 1.9682539682539684,
-      "grad_norm": 0.23065409064292908,
-      "learning_rate": 1.5109025494620677e-07,
-      "loss": 0.06025356650352478,
-      "mean_token_accuracy": 0.9816915906965733,
-      "num_tokens": 2013437.0,
-      "step": 1240
-    },
-    {
-      "entropy": 0.08529750020243228,
-      "epoch": 1.9841269841269842,
-      "grad_norm": 0.2376810908317566,
-      "learning_rate": 4.146318062603349e-08,
-      "loss": 0.06440364122390747,
-      "mean_token_accuracy": 0.980226569622755,
-      "num_tokens": 2029735.0,
-      "step": 1250
-    },
-    {
-      "entropy": 0.10629875352606177,
-      "epoch": 2.0,
-      "grad_norm": 0.27127400040626526,
-      "learning_rate": 3.426944015227918e-10,
-      "loss": 0.07178234457969665,
-      "mean_token_accuracy": 0.9805600672960282,
-      "num_tokens": 2046306.0,
-      "step": 1260
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1260,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.2086526491910144e+16,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

lora_adapter/checkpoint-1260/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d03761d0c056d3be10441632fd015fad7320a6a18d86e794364c2efae99b3
-size 5713

lora_adapter/checkpoint-400/README.md

@@ -1,209 +0,0 @@
----
-base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/Llama-3.2-1B-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 0.21.0

lora_adapter/checkpoint-400/adapter_config.json

@@ -1,51 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.0",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}

lora_adapter/checkpoint-400/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4ae8252383974bcc25da0056809fc1c34c78b0695153be8fa885a95570a5013
-size 45118424

lora_adapter/checkpoint-400/chat_template.jinja

@@ -1,93 +0,0 @@
-{{- 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 %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
-    {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
-    {%- endif %}
-{%- 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 #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\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 %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- 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 %}

lora_adapter/checkpoint-400/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3cc9a12b568442de0431789479c35d92e9a8e3982fae281b7604d8609f6f871f
-size 90359883

lora_adapter/checkpoint-400/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2cddf27219365242ec1046a3532a63a24c3f350c77f100e4f973369db2cc849d
-size 14455

lora_adapter/checkpoint-400/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:54d73025d96631205a46c90b3629e62c7f9779444fb8bded0541c71a569291bc
-size 1465

lora_adapter/checkpoint-400/tokenizer.json

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

lora_adapter/checkpoint-400/tokenizer_config.json

@@ -1,17 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "is_local": false,
-  "local_files_only": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "left",
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": null
-}

lora_adapter/checkpoint-400/trainer_state.json

@@ -1,434 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.6349206349206349,
-  "eval_steps": 500,
-  "global_step": 400,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "entropy": 3.2998463183641435,
-      "epoch": 0.015873015873015872,
-      "grad_norm": 5.5954365730285645,
-      "learning_rate": 3e-05,
-      "loss": 4.793289566040039,
-      "mean_token_accuracy": 0.36775660440325736,
-      "num_tokens": 16307.0,
-      "step": 10
-    },
-    {
-      "entropy": 3.745172455906868,
-      "epoch": 0.031746031746031744,
-      "grad_norm": 2.467291831970215,
-      "learning_rate": 6.333333333333333e-05,
-      "loss": 3.7420589447021486,
-      "mean_token_accuracy": 0.43841218277812005,
-      "num_tokens": 32577.0,
-      "step": 20
-    },
-    {
-      "entropy": 3.1654938369989396,
-      "epoch": 0.047619047619047616,
-      "grad_norm": 1.8811299800872803,
-      "learning_rate": 9.666666666666667e-05,
-      "loss": 2.4434362411499024,
-      "mean_token_accuracy": 0.6050871018320322,
-      "num_tokens": 48737.0,
-      "step": 30
-    },
-    {
-      "entropy": 1.9995254769921302,
-      "epoch": 0.06349206349206349,
-      "grad_norm": 1.535879373550415,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.565892219543457,
-      "mean_token_accuracy": 0.7555049300193787,
-      "num_tokens": 64997.0,
-      "step": 40
-    },
-    {
-      "entropy": 1.5211943820118905,
-      "epoch": 0.07936507936507936,
-      "grad_norm": 1.7563194036483765,
-      "learning_rate": 0.00016333333333333334,
-      "loss": 1.1280284881591798,
-      "mean_token_accuracy": 0.812470355629921,
-      "num_tokens": 81080.0,
-      "step": 50
-    },
-    {
-      "entropy": 1.17081895545125,
-      "epoch": 0.09523809523809523,
-      "grad_norm": 1.464584231376648,
-      "learning_rate": 0.00019666666666666666,
-      "loss": 0.8906035423278809,
-      "mean_token_accuracy": 0.8521104611456394,
-      "num_tokens": 97196.0,
-      "step": 60
-    },
-    {
-      "entropy": 0.9356300979852676,
-      "epoch": 0.1111111111111111,
-      "grad_norm": 1.4088091850280762,
-      "learning_rate": 0.00019997224302180006,
-      "loss": 0.670417308807373,
-      "mean_token_accuracy": 0.8883098550140858,
-      "num_tokens": 113569.0,
-      "step": 70
-    },
-    {
-      "entropy": 0.5688819501549005,
-      "epoch": 0.12698412698412698,
-      "grad_norm": 1.340789794921875,
-      "learning_rate": 0.00019987631275635948,
-      "loss": 0.36014580726623535,
-      "mean_token_accuracy": 0.9383806541562081,
-      "num_tokens": 129665.0,
-      "step": 80
-    },
-    {
-      "entropy": 0.5208159729838371,
-      "epoch": 0.14285714285714285,
-      "grad_norm": 1.1698484420776367,
-      "learning_rate": 0.00019971193225508879,
-      "loss": 0.38550715446472167,
-      "mean_token_accuracy": 0.9369473621249199,
-      "num_tokens": 145819.0,
-      "step": 90
-    },
-    {
-      "entropy": 0.35822844561189415,
-      "epoch": 0.15873015873015872,
-      "grad_norm": 1.056837558746338,
-      "learning_rate": 0.00019947921417617267,
-      "loss": 0.24877142906188965,
-      "mean_token_accuracy": 0.9541201412677764,
-      "num_tokens": 162338.0,
-      "step": 100
-    },
-    {
-      "entropy": 0.36921846531331537,
-      "epoch": 0.1746031746031746,
-      "grad_norm": 0.771403431892395,
-      "learning_rate": 0.0001991783180129578,
-      "loss": 0.2972050666809082,
-      "mean_token_accuracy": 0.946565055847168,
-      "num_tokens": 179013.0,
-      "step": 110
-    },
-    {
-      "entropy": 0.4222600903362036,
-      "epoch": 0.19047619047619047,
-      "grad_norm": 0.6926781535148621,
-      "learning_rate": 0.00019880944998464434,
-      "loss": 0.3286353349685669,
-      "mean_token_accuracy": 0.9404827795922757,
-      "num_tokens": 195500.0,
-      "step": 120
-    },
-    {
-      "entropy": 0.23451931905001402,
-      "epoch": 0.20634920634920634,
-      "grad_norm": 1.0064337253570557,
-      "learning_rate": 0.00019837286289495361,
-      "loss": 0.16426128149032593,
-      "mean_token_accuracy": 0.9648101754486561,
-      "num_tokens": 211542.0,
-      "step": 130
-    },
-    {
-      "entropy": 0.26509888684377075,
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.6641770601272583,
-      "learning_rate": 0.0001978688559588688,
-      "loss": 0.1910732865333557,
-      "mean_token_accuracy": 0.9604174040257931,
-      "num_tokens": 227757.0,
-      "step": 140
-    },
-    {
-      "entropy": 0.3036362808197737,
-      "epoch": 0.23809523809523808,
-      "grad_norm": 0.9009377956390381,
-      "learning_rate": 0.0001972977745975682,
-      "loss": 0.24015522003173828,
-      "mean_token_accuracy": 0.9528692953288556,
-      "num_tokens": 244201.0,
-      "step": 150
-    },
-    {
-      "entropy": 0.2707868428900838,
-      "epoch": 0.25396825396825395,
-      "grad_norm": 0.7132826447486877,
-      "learning_rate": 0.00019666001020169073,
-      "loss": 0.21738948822021484,
-      "mean_token_accuracy": 0.9576977901160717,
-      "num_tokens": 260595.0,
-      "step": 160
-    },
-    {
-      "entropy": 0.2235692773014307,
-      "epoch": 0.2698412698412698,
-      "grad_norm": 0.47566577792167664,
-      "learning_rate": 0.00019595599986309628,
-      "loss": 0.1625096917152405,
-      "mean_token_accuracy": 0.9630098052322864,
-      "num_tokens": 276583.0,
-      "step": 170
-    },
-    {
-      "entropy": 0.19970224229618908,
-      "epoch": 0.2857142857142857,
-      "grad_norm": 0.6967102885246277,
-      "learning_rate": 0.0001951862260753048,
-      "loss": 0.1510181427001953,
-      "mean_token_accuracy": 0.9644064873456955,
-      "num_tokens": 292611.0,
-      "step": 180
-    },
-    {
-      "entropy": 0.18911871258169413,
-      "epoch": 0.30158730158730157,
-      "grad_norm": 0.579555869102478,
-      "learning_rate": 0.00019435121640281938,
-      "loss": 0.14125581979751586,
-      "mean_token_accuracy": 0.9668954975903035,
-      "num_tokens": 308945.0,
-      "step": 190
-    },
-    {
-      "entropy": 0.21873050034046174,
-      "epoch": 0.31746031746031744,
-      "grad_norm": 0.6234372854232788,
-      "learning_rate": 0.00019345154311955985,
-      "loss": 0.18390271663665772,
-      "mean_token_accuracy": 0.9605240561068058,
-      "num_tokens": 325018.0,
-      "step": 200
-    },
-    {
-      "entropy": 0.23017035396769642,
-      "epoch": 0.3333333333333333,
-      "grad_norm": 0.5848660469055176,
-      "learning_rate": 0.00019248782281665498,
-      "loss": 0.18674861192703246,
-      "mean_token_accuracy": 0.960551692545414,
-      "num_tokens": 341276.0,
-      "step": 210
-    },
-    {
-      "entropy": 0.23857398927211762,
-      "epoch": 0.3492063492063492,
-      "grad_norm": 0.5835615992546082,
-      "learning_rate": 0.00019146071597986138,
-      "loss": 0.1981763243675232,
-      "mean_token_accuracy": 0.9606492578983307,
-      "num_tokens": 357585.0,
-      "step": 220
-    },
-    {
-      "entropy": 0.21739678094163536,
-      "epoch": 0.36507936507936506,
-      "grad_norm": 0.49282777309417725,
-      "learning_rate": 0.00019037092653689987,
-      "loss": 0.16624126434326172,
-      "mean_token_accuracy": 0.964983056485653,
-      "num_tokens": 374067.0,
-      "step": 230
-    },
-    {
-      "entropy": 0.2051882056519389,
-      "epoch": 0.38095238095238093,
-      "grad_norm": 0.7691304683685303,
-      "learning_rate": 0.00018921920137501849,
-      "loss": 0.17399615049362183,
-      "mean_token_accuracy": 0.9637806750833988,
-      "num_tokens": 390575.0,
-      "step": 240
-    },
-    {
-      "entropy": 0.19259531470015645,
-      "epoch": 0.3968253968253968,
-      "grad_norm": 0.41227754950523376,
-      "learning_rate": 0.00018800632982911322,
-      "loss": 0.14645222425460816,
-      "mean_token_accuracy": 0.9661086022853851,
-      "num_tokens": 406790.0,
-      "step": 250
-    },
-    {
-      "entropy": 0.12554183262400329,
-      "epoch": 0.4126984126984127,
-      "grad_norm": 0.38903799653053284,
-      "learning_rate": 0.00018673314314075732,
-      "loss": 0.0970867395401001,
-      "mean_token_accuracy": 0.9753100097179412,
-      "num_tokens": 422899.0,
-      "step": 260
-    },
-    {
-      "entropy": 0.21776192565448582,
-      "epoch": 0.42857142857142855,
-      "grad_norm": 0.5275615453720093,
-      "learning_rate": 0.00018540051388850993,
-      "loss": 0.175495445728302,
-      "mean_token_accuracy": 0.9626297920942306,
-      "num_tokens": 439095.0,
-      "step": 270
-    },
-    {
-      "entropy": 0.41472155014052986,
-      "epoch": 0.4444444444444444,
-      "grad_norm": 1.5612674951553345,
-      "learning_rate": 0.0001840093553898942,
-      "loss": 0.3378293514251709,
-      "mean_token_accuracy": 0.9364372007548809,
-      "num_tokens": 455598.0,
-      "step": 280
-    },
-    {
-      "entropy": 0.18331955913454295,
-      "epoch": 0.4603174603174603,
-      "grad_norm": 0.3843788206577301,
-      "learning_rate": 0.00018256062107545518,
-      "loss": 0.13437695503234864,
-      "mean_token_accuracy": 0.9686297826468945,
-      "num_tokens": 471075.0,
-      "step": 290
-    },
-    {
-      "entropy": 0.16779997684061526,
-      "epoch": 0.47619047619047616,
-      "grad_norm": 0.3690398037433624,
-      "learning_rate": 0.00018105530383532607,
-      "loss": 0.13349469900131225,
-      "mean_token_accuracy": 0.9697726428508758,
-      "num_tokens": 486950.0,
-      "step": 300
-    },
-    {
-      "entropy": 0.18286482915282248,
-      "epoch": 0.49206349206349204,
-      "grad_norm": 0.5309385657310486,
-      "learning_rate": 0.000179494435338751,
-      "loss": 0.14468667507171631,
-      "mean_token_accuracy": 0.9676945447921753,
-      "num_tokens": 503167.0,
-      "step": 310
-    },
-    {
-      "entropy": 0.21837912490591407,
-      "epoch": 0.5079365079365079,
-      "grad_norm": 0.5445209741592407,
-      "learning_rate": 0.00017787908532703042,
-      "loss": 0.16839513778686524,
-      "mean_token_accuracy": 0.9623315379023551,
-      "num_tokens": 519080.0,
-      "step": 320
-    },
-    {
-      "entropy": 0.16709138257429004,
-      "epoch": 0.5238095238095238,
-      "grad_norm": 0.712787926197052,
-      "learning_rate": 0.00017621036088037378,
-      "loss": 0.13333501815795898,
-      "mean_token_accuracy": 0.9686624228954315,
-      "num_tokens": 535244.0,
-      "step": 330
-    },
-    {
-      "entropy": 0.1875067687127739,
-      "epoch": 0.5396825396825397,
-      "grad_norm": 0.34370172023773193,
-      "learning_rate": 0.00017448940565916222,
-      "loss": 0.14327633380889893,
-      "mean_token_accuracy": 0.9682756960391998,
-      "num_tokens": 551358.0,
-      "step": 340
-    },
-    {
-      "entropy": 0.15009528640657663,
-      "epoch": 0.5555555555555556,
-      "grad_norm": 0.33299151062965393,
-      "learning_rate": 0.00017271739912014068,
-      "loss": 0.11425788402557373,
-      "mean_token_accuracy": 0.9726194083690644,
-      "num_tokens": 567832.0,
-      "step": 350
-    },
-    {
-      "entropy": 0.15241470024921,
-      "epoch": 0.5714285714285714,
-      "grad_norm": 0.3769768476486206,
-      "learning_rate": 0.00017089555570807736,
-      "loss": 0.1251630187034607,
-      "mean_token_accuracy": 0.9712164625525475,
-      "num_tokens": 583486.0,
-      "step": 360
-    },
-    {
-      "entropy": 0.19003299945034086,
-      "epoch": 0.5873015873015873,
-      "grad_norm": 0.7838993072509766,
-      "learning_rate": 0.00016902512402344373,
-      "loss": 0.1713760018348694,
-      "mean_token_accuracy": 0.9653461590409279,
-      "num_tokens": 599729.0,
-      "step": 370
-    },
-    {
-      "entropy": 0.17572227772325277,
-      "epoch": 0.6031746031746031,
-      "grad_norm": 0.42281991243362427,
-      "learning_rate": 0.00016710738596668632,
-      "loss": 0.1362382650375366,
-      "mean_token_accuracy": 0.9687412306666374,
-      "num_tokens": 616044.0,
-      "step": 380
-    },
-    {
-      "entropy": 0.16331438799388706,
-      "epoch": 0.6190476190476191,
-      "grad_norm": 1.076119065284729,
-      "learning_rate": 0.00016514365585967603,
-      "loss": 0.12754744291305542,
-      "mean_token_accuracy": 0.9687342867255211,
-      "num_tokens": 632147.0,
-      "step": 390
-    },
-    {
-      "entropy": 0.19245414207689465,
-      "epoch": 0.6349206349206349,
-      "grad_norm": 0.644232988357544,
-      "learning_rate": 0.00016313527954493778,
-      "loss": 0.15318721532821655,
-      "mean_token_accuracy": 0.9658746793866158,
-      "num_tokens": 648375.0,
-      "step": 400
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1260,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 3829633307136000.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

lora_adapter/checkpoint-400/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d03761d0c056d3be10441632fd015fad7320a6a18d86e794364c2efae99b3
-size 5713

lora_adapter/checkpoint-600/README.md

@@ -1,209 +0,0 @@
----
-base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/Llama-3.2-1B-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 0.21.0

lora_adapter/checkpoint-600/adapter_config.json

@@ -1,51 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-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,
-  "kasa_config": null,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "lora_ga_config": null,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "monteclora_config": null,
-  "peft_type": "LORA",
-  "peft_version": "0.21.0",
-  "qalora_group_size": 16,
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_bdlora": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
-}