Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+library_name: peft
+model_name: lora-output
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for lora-output
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.29.0
+- Transformers: 5.2.0
+- Pytorch: 2.10.0
+- Datasets: 4.6.1
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b013d01342db5b92eb257e6838fd6f864be365af81b172975a1a6377b50672
+size 167832688

chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4187a466f138acc4a47c032b6f3e2851815d25ac627696957f05618cb1eeda
+size 167832688

checkpoint-200/chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73161f7a923b24d5ef267c1c9abc4085ddd45eb6f069501347bb3f269518f12b
+size 170934309

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8631a7b643f0be950f9cd325aaf0b52251278d3aea0914df6a57a18e149fa67
+size 14645

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd974eab46a8eb1ebfc832ad484cc313ed5be41647092e7185c8c638c948c9e7
+size 1465

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.502749410840534,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.4948265369981528,
+      "epoch": 0.12568735271013354,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7029500961303712,
+      "mean_token_accuracy": 0.6537273893132806,
+      "num_tokens": 156024.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.1234326036646962,
+      "epoch": 0.2513747054202671,
+      "grad_norm": 0.037353515625,
+      "learning_rate": 0.00019953520716943371,
+      "loss": 1.1771140098571777,
+      "mean_token_accuracy": 0.7510503690689803,
+      "num_tokens": 298620.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.0369394151493907,
+      "epoch": 0.3770620581304006,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.0001972690659618564,
+      "loss": 1.1110390663146972,
+      "mean_token_accuracy": 0.7662029687315226,
+      "num_tokens": 449966.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.0444004433229566,
+      "epoch": 0.5027494108405341,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001931591088051279,
+      "loss": 1.1269343376159668,
+      "mean_token_accuracy": 0.7651370905339718,
+      "num_tokens": 608754.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.051739121414721,
+      "epoch": 0.6284367635506677,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.00018728324335139814,
+      "loss": 1.088887882232666,
+      "mean_token_accuracy": 0.7666051037609577,
+      "num_tokens": 764583.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9839291835203767,
+      "epoch": 0.7541241162608012,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.0001797528515115709,
+      "loss": 1.020584487915039,
+      "mean_token_accuracy": 0.7803368698805571,
+      "num_tokens": 912716.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0362637933343648,
+      "epoch": 0.8798114689709348,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.0753373146057128,
+      "mean_token_accuracy": 0.7713750531896949,
+      "num_tokens": 1064494.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.9550455894345552,
+      "epoch": 1.0,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001603281250808719,
+      "loss": 0.9675676345825195,
+      "mean_token_accuracy": 0.7857394160008898,
+      "num_tokens": 1201271.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9374621393159032,
+      "epoch": 1.1256873527101336,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00014880200231609983,
+      "loss": 0.9870312690734864,
+      "mean_token_accuracy": 0.7901170210912823,
+      "num_tokens": 1349133.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.949882148578763,
+      "epoch": 1.251374705420267,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.00013635079705638298,
+      "loss": 0.9436046600341796,
+      "mean_token_accuracy": 0.788494935259223,
+      "num_tokens": 1500927.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.251374705420267,
+      "eval_entropy": 0.9404270783276625,
+      "eval_loss": 0.9446325302124023,
+      "eval_mean_token_accuracy": 0.7829881757497787,
+      "eval_num_tokens": 1500927.0,
+      "eval_runtime": 86.1079,
+      "eval_samples_per_second": 1.649,
+      "eval_steps_per_second": 1.649,
+      "step": 100
+    },
+    {
+      "entropy": 0.9173299714922905,
+      "epoch": 1.3770620581304005,
+      "grad_norm": 0.0233154296875,
+      "learning_rate": 0.0001232105322409468,
+      "loss": 0.9481925964355469,
+      "mean_token_accuracy": 0.7930883213877677,
+      "num_tokens": 1646678.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.9073959412053227,
+      "epoch": 1.5027494108405341,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 0.00010963029250531418,
+      "loss": 0.9351880073547363,
+      "mean_token_accuracy": 0.7968914289027452,
+      "num_tokens": 1799797.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.9462396390736103,
+      "epoch": 1.6284367635506678,
+      "grad_norm": 0.029296875,
+      "learning_rate": 9.586750257511867e-05,
+      "loss": 0.9954720497131347,
+      "mean_token_accuracy": 0.789978607185185,
+      "num_tokens": 1958692.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.9035223769024014,
+      "epoch": 1.7541241162608012,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 8.218304756658072e-05,
+      "loss": 0.9473580360412598,
+      "mean_token_accuracy": 0.7965094247832895,
+      "num_tokens": 2098856.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.9002945913001895,
+      "epoch": 1.8798114689709347,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 6.883632769240589e-05,
+      "loss": 0.9326913833618165,
+      "mean_token_accuracy": 0.800568002089858,
+      "num_tokens": 2253582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8597502765897053,
+      "epoch": 2.0,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 5.608034111526298e-05,
+      "loss": 0.8665840148925781,
+      "mean_token_accuracy": 0.8103327634287816,
+      "num_tokens": 2402542.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.8727964337915182,
+      "epoch": 2.1256873527101336,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 4.415688815743858e-05,
+      "loss": 0.9112902641296386,
+      "mean_token_accuracy": 0.8074018105864524,
+      "num_tokens": 2554831.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8327508143149316,
+      "epoch": 2.2513747054202673,
+      "grad_norm": 0.03955078125,
+      "learning_rate": 3.329198777485869e-05,
+      "loss": 0.8397786140441894,
+      "mean_token_accuracy": 0.816638495773077,
+      "num_tokens": 2700898.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8549322345294058,
+      "epoch": 2.3770620581304005,
+      "grad_norm": 0.041015625,
+      "learning_rate": 2.3691593180019366e-05,
+      "loss": 0.8526265144348144,
+      "mean_token_accuracy": 0.8113520180806517,
+      "num_tokens": 2854824.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.8102049398235976,
+      "epoch": 2.502749410840534,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 1.553768782775351e-05,
+      "loss": 0.8202457427978516,
+      "mean_token_accuracy": 0.8225593730807305,
+      "num_tokens": 3003572.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.502749410840534,
+      "eval_entropy": 0.8503286918284187,
+      "eval_loss": 0.8580905795097351,
+      "eval_mean_token_accuracy": 0.8025841964802272,
+      "eval_num_tokens": 3003572.0,
+      "eval_runtime": 85.9551,
+      "eval_samples_per_second": 1.652,
+      "eval_steps_per_second": 1.652,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.2965602468164403e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b53f9087af6406754f9d4a944b842846aaebb983e7344dbff137c8f3f21285
+size 5649

checkpoint-240/README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-240/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-240/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b013d01342db5b92eb257e6838fd6f864be365af81b172975a1a6377b50672
+size 167832688

checkpoint-240/chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b8ebb32685ec9f9f7275850b319072e453a1ac873b9b54b34106838109dc8e
+size 170934309

checkpoint-240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac6065aad7129a0a012d9dbf74576977fc6e57d2aa725d6d299df37a52ec6f9
+size 14645

checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ca1a11d830dd1fe262b52bdd49d3d858aa6f94fb097b5f8cbe02edb1720435
+size 1465

checkpoint-240/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-240/trainer_state.json

@@ -0,0 +1,296 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.4948265369981528,
+      "epoch": 0.12568735271013354,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7029500961303712,
+      "mean_token_accuracy": 0.6537273893132806,
+      "num_tokens": 156024.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.1234326036646962,
+      "epoch": 0.2513747054202671,
+      "grad_norm": 0.037353515625,
+      "learning_rate": 0.00019953520716943371,
+      "loss": 1.1771140098571777,
+      "mean_token_accuracy": 0.7510503690689803,
+      "num_tokens": 298620.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.0369394151493907,
+      "epoch": 0.3770620581304006,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.0001972690659618564,
+      "loss": 1.1110390663146972,
+      "mean_token_accuracy": 0.7662029687315226,
+      "num_tokens": 449966.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.0444004433229566,
+      "epoch": 0.5027494108405341,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001931591088051279,
+      "loss": 1.1269343376159668,
+      "mean_token_accuracy": 0.7651370905339718,
+      "num_tokens": 608754.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.051739121414721,
+      "epoch": 0.6284367635506677,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.00018728324335139814,
+      "loss": 1.088887882232666,
+      "mean_token_accuracy": 0.7666051037609577,
+      "num_tokens": 764583.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9839291835203767,
+      "epoch": 0.7541241162608012,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.0001797528515115709,
+      "loss": 1.020584487915039,
+      "mean_token_accuracy": 0.7803368698805571,
+      "num_tokens": 912716.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0362637933343648,
+      "epoch": 0.8798114689709348,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.0753373146057128,
+      "mean_token_accuracy": 0.7713750531896949,
+      "num_tokens": 1064494.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.9550455894345552,
+      "epoch": 1.0,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001603281250808719,
+      "loss": 0.9675676345825195,
+      "mean_token_accuracy": 0.7857394160008898,
+      "num_tokens": 1201271.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9374621393159032,
+      "epoch": 1.1256873527101336,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00014880200231609983,
+      "loss": 0.9870312690734864,
+      "mean_token_accuracy": 0.7901170210912823,
+      "num_tokens": 1349133.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.949882148578763,
+      "epoch": 1.251374705420267,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.00013635079705638298,
+      "loss": 0.9436046600341796,
+      "mean_token_accuracy": 0.788494935259223,
+      "num_tokens": 1500927.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.251374705420267,
+      "eval_entropy": 0.9404270783276625,
+      "eval_loss": 0.9446325302124023,
+      "eval_mean_token_accuracy": 0.7829881757497787,
+      "eval_num_tokens": 1500927.0,
+      "eval_runtime": 86.1079,
+      "eval_samples_per_second": 1.649,
+      "eval_steps_per_second": 1.649,
+      "step": 100
+    },
+    {
+      "entropy": 0.9173299714922905,
+      "epoch": 1.3770620581304005,
+      "grad_norm": 0.0233154296875,
+      "learning_rate": 0.0001232105322409468,
+      "loss": 0.9481925964355469,
+      "mean_token_accuracy": 0.7930883213877677,
+      "num_tokens": 1646678.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.9073959412053227,
+      "epoch": 1.5027494108405341,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 0.00010963029250531418,
+      "loss": 0.9351880073547363,
+      "mean_token_accuracy": 0.7968914289027452,
+      "num_tokens": 1799797.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.9462396390736103,
+      "epoch": 1.6284367635506678,
+      "grad_norm": 0.029296875,
+      "learning_rate": 9.586750257511867e-05,
+      "loss": 0.9954720497131347,
+      "mean_token_accuracy": 0.789978607185185,
+      "num_tokens": 1958692.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.9035223769024014,
+      "epoch": 1.7541241162608012,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 8.218304756658072e-05,
+      "loss": 0.9473580360412598,
+      "mean_token_accuracy": 0.7965094247832895,
+      "num_tokens": 2098856.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.9002945913001895,
+      "epoch": 1.8798114689709347,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 6.883632769240589e-05,
+      "loss": 0.9326913833618165,
+      "mean_token_accuracy": 0.800568002089858,
+      "num_tokens": 2253582.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8597502765897053,
+      "epoch": 2.0,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 5.608034111526298e-05,
+      "loss": 0.8665840148925781,
+      "mean_token_accuracy": 0.8103327634287816,
+      "num_tokens": 2402542.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.8727964337915182,
+      "epoch": 2.1256873527101336,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 4.415688815743858e-05,
+      "loss": 0.9112902641296386,
+      "mean_token_accuracy": 0.8074018105864524,
+      "num_tokens": 2554831.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8327508143149316,
+      "epoch": 2.2513747054202673,
+      "grad_norm": 0.03955078125,
+      "learning_rate": 3.329198777485869e-05,
+      "loss": 0.8397786140441894,
+      "mean_token_accuracy": 0.816638495773077,
+      "num_tokens": 2700898.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8549322345294058,
+      "epoch": 2.3770620581304005,
+      "grad_norm": 0.041015625,
+      "learning_rate": 2.3691593180019366e-05,
+      "loss": 0.8526265144348144,
+      "mean_token_accuracy": 0.8113520180806517,
+      "num_tokens": 2854824.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.8102049398235976,
+      "epoch": 2.502749410840534,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 1.553768782775351e-05,
+      "loss": 0.8202457427978516,
+      "mean_token_accuracy": 0.8225593730807305,
+      "num_tokens": 3003572.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.502749410840534,
+      "eval_entropy": 0.8503286918284187,
+      "eval_loss": 0.8580905795097351,
+      "eval_mean_token_accuracy": 0.8025841964802272,
+      "eval_num_tokens": 3003572.0,
+      "eval_runtime": 85.9551,
+      "eval_samples_per_second": 1.652,
+      "eval_steps_per_second": 1.652,
+      "step": 200
+    },
+    {
+      "entropy": 0.8026974092237651,
+      "epoch": 2.628436763550668,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 8.98483576766631e-06,
+      "loss": 0.805226993560791,
+      "mean_token_accuracy": 0.8234594237059355,
+      "num_tokens": 3151440.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.7800698866136372,
+      "epoch": 2.754124116260801,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 4.1572517541747294e-06,
+      "loss": 0.7574594020843506,
+      "mean_token_accuracy": 0.8299322757869959,
+      "num_tokens": 3316394.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.7608709936961532,
+      "epoch": 2.8798114689709347,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 1.146446652649169e-06,
+      "loss": 0.7368635654449462,
+      "mean_token_accuracy": 0.8316391207277775,
+      "num_tokens": 3459207.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.7886644739146326,
+      "epoch": 3.0,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 9.49277494008971e-09,
+      "loss": 0.737561845779419,
+      "mean_token_accuracy": 0.828946531208512,
+      "num_tokens": 3603813.0,
+      "step": 240
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.5556679422901453e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-240/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b53f9087af6406754f9d4a944b842846aaebb983e7344dbff137c8f3f21285
+size 5649

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b53f9087af6406754f9d4a944b842846aaebb983e7344dbff137c8f3f21285
+size 5649