Upload folder using huggingface_hub

README.md

@@ -0,0 +1,166 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: mistralai/Mistral-7B-v0.1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: caffeinatedcherrychic/cidds-agg-balanced
+    type: alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./qlora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 256
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 5
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+max_steps: 500
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 1
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.001
+fsdp:
+fsdp_config:
+special_tokens:
+
+
+```
+
+</details><br>
+
+# qlora-out
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1465
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 62
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.6367        | 0.08  | 1    | 7.3009          |
+| 2.3866        | 0.32  | 4    | 0.7138          |
+| 0.948         | 0.64  | 8    | 1.0446          |
+| 0.6822        | 0.96  | 12   | 1.3960          |
+| 0.5222        | 1.28  | 16   | 0.9023          |
+| 0.534         | 1.6   | 20   | 0.4847          |
+| 0.4624        | 1.92  | 24   | 0.5740          |
+| 0.7753        | 2.24  | 28   | 0.3772          |
+| 0.3324        | 2.56  | 32   | 0.2937          |
+| 0.1973        | 2.88  | 36   | 0.5675          |
+| 0.0843        | 3.2   | 40   | 0.2360          |
+| 0.3836        | 3.52  | 44   | 0.1397          |
+| 0.0449        | 3.84  | 48   | 0.2801          |
+| 0.2246        | 4.16  | 52   | 0.1946          |
+| 0.229         | 4.48  | 56   | 0.1618          |
+| 0.3073        | 4.8   | 60   | 0.1465          |
+
+
+### Framework versions
+
+- PEFT 0.10.1.dev0
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef894f6daf736ab4a35fe0fba96204d34d3a179661233fc32771e92bcb515b0d
+size 335706186

checkpoint-13/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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 0.10.1.dev0

checkpoint-13/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-13/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72069b2abc2e8e408822bca99f6492f6272dff7f199d0afff420f28fdcde57ab
+size 335604696

checkpoint-13/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff099a7ecc6bc7c04d5f8fd80d2443dd9f492cb12877c91fe4ea29066d9dd08
+size 168624724

checkpoint-13/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fd0abf3b25d5f521218bb97508206369e6984af4f556dd58b22d5dfbbb6425
+size 14244

checkpoint-13/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3b6aff690f8457dc46d75813d9f660109e8ec63e2dc8cbf92e4d726c3a8a8c
+size 1064

checkpoint-13/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.04,
+  "eval_steps": 4,
+  "global_step": 13,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 102.28898620605469,
+      "learning_rate": 2e-05,
+      "loss": 6.6367,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 7.300913333892822,
+      "eval_runtime": 1.3523,
+      "eval_samples_per_second": 8.873,
+      "eval_steps_per_second": 4.437,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 103.4541015625,
+      "learning_rate": 4e-05,
+      "loss": 7.0616,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 67.47515869140625,
+      "learning_rate": 6e-05,
+      "loss": 4.686,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 72.36919403076172,
+      "learning_rate": 8e-05,
+      "loss": 2.3866,
+      "step": 4
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.7137572169303894,
+      "eval_runtime": 1.3532,
+      "eval_samples_per_second": 8.868,
+      "eval_steps_per_second": 4.434,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.83085060119629,
+      "learning_rate": 0.0001,
+      "loss": 0.6844,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 25.897714614868164,
+      "learning_rate": 0.00012,
+      "loss": 0.914,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 18.89151382446289,
+      "learning_rate": 0.00014,
+      "loss": 0.63,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 27.15555763244629,
+      "learning_rate": 0.00016,
+      "loss": 0.948,
+      "step": 8
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.0445994138717651,
+      "eval_runtime": 1.356,
+      "eval_samples_per_second": 8.85,
+      "eval_steps_per_second": 4.425,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 20.812381744384766,
+      "learning_rate": 0.00018,
+      "loss": 1.0285,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 56.3886604309082,
+      "learning_rate": 0.0002,
+      "loss": 1.3756,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.24803352355957,
+      "learning_rate": 0.00019981755542233177,
+      "loss": 0.5178,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8.379430770874023,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.6822,
+      "step": 12
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.3959709405899048,
+      "eval_runtime": 1.3583,
+      "eval_samples_per_second": 8.835,
+      "eval_steps_per_second": 4.417,
+      "step": 12
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 20.744348526000977,
+      "learning_rate": 0.00019836199069471437,
+      "loss": 1.3762,
+      "step": 13
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 62,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 13,
+  "total_flos": 1138234761412608.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-13/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fede3f83b4ad6ce095e0aa09047d95bd4acc13170780f9e890d9d17d1bdace
+size 5624

checkpoint-26/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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 0.10.1.dev0

checkpoint-26/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-26/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387499c7736d8b7c5cab21843d9b986ad31e4777afa1c953e254a6b821622ab8
+size 335604696

checkpoint-26/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26885c89f597923fecf6d91cf382dfac6eeea66972dd286bb6316360fd0bb69
+size 168624724

checkpoint-26/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69726c1b60735ec075cbe9ef238868d0b5845ade6b93bfd60e810fcee5f233a5
+size 14244

checkpoint-26/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22f4d3e17b1ff1ac5db395ab84ba067bc34a07791275897d3efe0cf1944d439
+size 1064

checkpoint-26/trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.08,
+  "eval_steps": 4,
+  "global_step": 26,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 102.28898620605469,
+      "learning_rate": 2e-05,
+      "loss": 6.6367,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 7.300913333892822,
+      "eval_runtime": 1.3523,
+      "eval_samples_per_second": 8.873,
+      "eval_steps_per_second": 4.437,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 103.4541015625,
+      "learning_rate": 4e-05,
+      "loss": 7.0616,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 67.47515869140625,
+      "learning_rate": 6e-05,
+      "loss": 4.686,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 72.36919403076172,
+      "learning_rate": 8e-05,
+      "loss": 2.3866,
+      "step": 4
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.7137572169303894,
+      "eval_runtime": 1.3532,
+      "eval_samples_per_second": 8.868,
+      "eval_steps_per_second": 4.434,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.83085060119629,
+      "learning_rate": 0.0001,
+      "loss": 0.6844,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 25.897714614868164,
+      "learning_rate": 0.00012,
+      "loss": 0.914,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 18.89151382446289,
+      "learning_rate": 0.00014,
+      "loss": 0.63,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 27.15555763244629,
+      "learning_rate": 0.00016,
+      "loss": 0.948,
+      "step": 8
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.0445994138717651,
+      "eval_runtime": 1.356,
+      "eval_samples_per_second": 8.85,
+      "eval_steps_per_second": 4.425,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 20.812381744384766,
+      "learning_rate": 0.00018,
+      "loss": 1.0285,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 56.3886604309082,
+      "learning_rate": 0.0002,
+      "loss": 1.3756,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.24803352355957,
+      "learning_rate": 0.00019981755542233177,
+      "loss": 0.5178,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8.379430770874023,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.6822,
+      "step": 12
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.3959709405899048,
+      "eval_runtime": 1.3583,
+      "eval_samples_per_second": 8.835,
+      "eval_steps_per_second": 4.417,
+      "step": 12
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 20.744348526000977,
+      "learning_rate": 0.00019836199069471437,
+      "loss": 1.3762,
+      "step": 13
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 4.800480842590332,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.5248,
+      "step": 14
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.284302711486816,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 0.8094,
+      "step": 15
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.787976264953613,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.5222,
+      "step": 16
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.9023411870002747,
+      "eval_runtime": 1.3623,
+      "eval_samples_per_second": 8.808,
+      "eval_steps_per_second": 4.404,
+      "step": 16
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 21.48629379272461,
+      "learning_rate": 0.00019118998459920902,
+      "loss": 0.8027,
+      "step": 17
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 38.0982666015625,
+      "learning_rate": 0.000188545602565321,
+      "loss": 1.7772,
+      "step": 18
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 10.824837684631348,
+      "learning_rate": 0.00018557812723014476,
+      "loss": 0.7737,
+      "step": 19
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 9.1353120803833,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.534,
+      "step": 20
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.4847445785999298,
+      "eval_runtime": 1.3637,
+      "eval_samples_per_second": 8.799,
+      "eval_steps_per_second": 4.4,
+      "step": 20
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 3.8411033153533936,
+      "learning_rate": 0.00017871834806090501,
+      "loss": 0.3201,
+      "step": 21
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 23.888507843017578,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 2.2541,
+      "step": 22
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 8.5956392288208,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.8177,
+      "step": 23
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.825141191482544,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.4624,
+      "step": 24
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.5740255117416382,
+      "eval_runtime": 1.3655,
+      "eval_samples_per_second": 8.788,
+      "eval_steps_per_second": 4.394,
+      "step": 24
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.558993101119995,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 0.3714,
+      "step": 25
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 11.759211540222168,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6562,
+      "step": 26
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 62,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 13,
+  "total_flos": 2276469522825216.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-26/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fede3f83b4ad6ce095e0aa09047d95bd4acc13170780f9e890d9d17d1bdace
+size 5624

checkpoint-39/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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 0.10.1.dev0

checkpoint-39/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-39/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b8939dee1c9d7c76fb429805ca8dd1be67417b78ad3ae2622ce37f2a7294d6
+size 335604696

checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c9a9efa8eced911795343502191b7b9044f8b5aa46a6f27343859276faacbc
+size 168624724

checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83b87057617d19867b72bb4f1d7769198abfb127e1bef7a626c1e07b9dee3f2
+size 14244

checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8d987b7fe563f350e72415c21199e03eb1c8b092374967d449229a0b0fa9b1
+size 1064

checkpoint-39/trainer_state.json

@@ -0,0 +1,374 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.12,
+  "eval_steps": 4,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 102.28898620605469,
+      "learning_rate": 2e-05,
+      "loss": 6.6367,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 7.300913333892822,
+      "eval_runtime": 1.3523,
+      "eval_samples_per_second": 8.873,
+      "eval_steps_per_second": 4.437,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 103.4541015625,
+      "learning_rate": 4e-05,
+      "loss": 7.0616,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 67.47515869140625,
+      "learning_rate": 6e-05,
+      "loss": 4.686,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 72.36919403076172,
+      "learning_rate": 8e-05,
+      "loss": 2.3866,
+      "step": 4
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.7137572169303894,
+      "eval_runtime": 1.3532,
+      "eval_samples_per_second": 8.868,
+      "eval_steps_per_second": 4.434,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.83085060119629,
+      "learning_rate": 0.0001,
+      "loss": 0.6844,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 25.897714614868164,
+      "learning_rate": 0.00012,
+      "loss": 0.914,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 18.89151382446289,
+      "learning_rate": 0.00014,
+      "loss": 0.63,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 27.15555763244629,
+      "learning_rate": 0.00016,
+      "loss": 0.948,
+      "step": 8
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.0445994138717651,
+      "eval_runtime": 1.356,
+      "eval_samples_per_second": 8.85,
+      "eval_steps_per_second": 4.425,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 20.812381744384766,
+      "learning_rate": 0.00018,
+      "loss": 1.0285,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 56.3886604309082,
+      "learning_rate": 0.0002,
+      "loss": 1.3756,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.24803352355957,
+      "learning_rate": 0.00019981755542233177,
+      "loss": 0.5178,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8.379430770874023,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.6822,
+      "step": 12
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.3959709405899048,
+      "eval_runtime": 1.3583,
+      "eval_samples_per_second": 8.835,
+      "eval_steps_per_second": 4.417,
+      "step": 12
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 20.744348526000977,
+      "learning_rate": 0.00019836199069471437,
+      "loss": 1.3762,
+      "step": 13
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 4.800480842590332,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.5248,
+      "step": 14
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.284302711486816,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 0.8094,
+      "step": 15
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.787976264953613,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.5222,
+      "step": 16
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.9023411870002747,
+      "eval_runtime": 1.3623,
+      "eval_samples_per_second": 8.808,
+      "eval_steps_per_second": 4.404,
+      "step": 16
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 21.48629379272461,
+      "learning_rate": 0.00019118998459920902,
+      "loss": 0.8027,
+      "step": 17
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 38.0982666015625,
+      "learning_rate": 0.000188545602565321,
+      "loss": 1.7772,
+      "step": 18
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 10.824837684631348,
+      "learning_rate": 0.00018557812723014476,
+      "loss": 0.7737,
+      "step": 19
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 9.1353120803833,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.534,
+      "step": 20
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.4847445785999298,
+      "eval_runtime": 1.3637,
+      "eval_samples_per_second": 8.799,
+      "eval_steps_per_second": 4.4,
+      "step": 20
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 3.8411033153533936,
+      "learning_rate": 0.00017871834806090501,
+      "loss": 0.3201,
+      "step": 21
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 23.888507843017578,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 2.2541,
+      "step": 22
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 8.5956392288208,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.8177,
+      "step": 23
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.825141191482544,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.4624,
+      "step": 24
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.5740255117416382,
+      "eval_runtime": 1.3655,
+      "eval_samples_per_second": 8.788,
+      "eval_steps_per_second": 4.394,
+      "step": 24
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.558993101119995,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 0.3714,
+      "step": 25
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 11.759211540222168,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6562,
+      "step": 26
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 96.2179183959961,
+      "learning_rate": 0.00015173378141776568,
+      "loss": 1.5141,
+      "step": 27
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 31.022045135498047,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.7753,
+      "step": 28
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.3771994113922119,
+      "eval_runtime": 1.3676,
+      "eval_samples_per_second": 8.775,
+      "eval_steps_per_second": 4.387,
+      "step": 28
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 3.5004501342773438,
+      "learning_rate": 0.0001410412805452757,
+      "loss": 0.2649,
+      "step": 29
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 5.16464376449585,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.171,
+      "step": 30
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 25.634010314941406,
+      "learning_rate": 0.00012975030538552032,
+      "loss": 0.9172,
+      "step": 31
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 7.102908134460449,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.3324,
+      "step": 32
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 0.29374203085899353,
+      "eval_runtime": 1.3678,
+      "eval_samples_per_second": 8.773,
+      "eval_steps_per_second": 4.387,
+      "step": 32
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 6.236325263977051,
+      "learning_rate": 0.0001180255037813906,
+      "loss": 0.4932,
+      "step": 33
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 4.445058345794678,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.1284,
+      "step": 34
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 6.94170618057251,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 0.1547,
+      "step": 35
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.656033039093018,
+      "learning_rate": 0.0001,
+      "loss": 0.1973,
+      "step": 36
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 0.5674905180931091,
+      "eval_runtime": 1.3681,
+      "eval_samples_per_second": 8.771,
+      "eval_steps_per_second": 4.386,
+      "step": 36
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 18.19667625427246,
+      "learning_rate": 9.396215025777139e-05,
+      "loss": 0.4884,
+      "step": 37
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 17.964893341064453,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.5526,
+      "step": 38
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 5.015590190887451,
+      "learning_rate": 8.197449621860943e-05,
+      "loss": 0.2116,
+      "step": 39
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 62,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 13,
+  "total_flos": 3414704284237824.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fede3f83b4ad6ce095e0aa09047d95bd4acc13170780f9e890d9d17d1bdace
+size 5624

checkpoint-52/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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 0.10.1.dev0

checkpoint-52/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-52/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f543a16c2bbb11166292af99cbab42fa039c72766ce2da396aa279512c9d67
+size 335604696

checkpoint-52/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc05bf731a50997e7af44d91b701be1a9474180b446eef7cccd0a9bb6f49593f
+size 168624724

checkpoint-52/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d215519440d74cb3c2d938d0a6d0dcc602aa66ebc4017b44adae1cc4c34379e9
+size 14244

checkpoint-52/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210095055e4e9fa9a08e2ee8a6ef338aebf6d1d63c758470bd2537cf069290da
+size 1064

checkpoint-52/trainer_state.json

@@ -0,0 +1,497 @@
+{
+  "best_metric": 0.19463467597961426,
+  "best_model_checkpoint": "./qlora-out/checkpoint-52",
+  "epoch": 4.16,
+  "eval_steps": 4,
+  "global_step": 52,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 102.28898620605469,
+      "learning_rate": 2e-05,
+      "loss": 6.6367,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 7.300913333892822,
+      "eval_runtime": 1.3523,
+      "eval_samples_per_second": 8.873,
+      "eval_steps_per_second": 4.437,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 103.4541015625,
+      "learning_rate": 4e-05,
+      "loss": 7.0616,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 67.47515869140625,
+      "learning_rate": 6e-05,
+      "loss": 4.686,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 72.36919403076172,
+      "learning_rate": 8e-05,
+      "loss": 2.3866,
+      "step": 4
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.7137572169303894,
+      "eval_runtime": 1.3532,
+      "eval_samples_per_second": 8.868,
+      "eval_steps_per_second": 4.434,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.83085060119629,
+      "learning_rate": 0.0001,
+      "loss": 0.6844,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 25.897714614868164,
+      "learning_rate": 0.00012,
+      "loss": 0.914,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 18.89151382446289,
+      "learning_rate": 0.00014,
+      "loss": 0.63,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 27.15555763244629,
+      "learning_rate": 0.00016,
+      "loss": 0.948,
+      "step": 8
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.0445994138717651,
+      "eval_runtime": 1.356,
+      "eval_samples_per_second": 8.85,
+      "eval_steps_per_second": 4.425,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 20.812381744384766,
+      "learning_rate": 0.00018,
+      "loss": 1.0285,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 56.3886604309082,
+      "learning_rate": 0.0002,
+      "loss": 1.3756,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.24803352355957,
+      "learning_rate": 0.00019981755542233177,
+      "loss": 0.5178,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 8.379430770874023,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.6822,
+      "step": 12
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.3959709405899048,
+      "eval_runtime": 1.3583,
+      "eval_samples_per_second": 8.835,
+      "eval_steps_per_second": 4.417,
+      "step": 12
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 20.744348526000977,
+      "learning_rate": 0.00019836199069471437,
+      "loss": 1.3762,
+      "step": 13
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 4.800480842590332,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.5248,
+      "step": 14
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.284302711486816,
+      "learning_rate": 0.00019547208665085457,
+      "loss": 0.8094,
+      "step": 15
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 5.787976264953613,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.5222,
+      "step": 16
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.9023411870002747,
+      "eval_runtime": 1.3623,
+      "eval_samples_per_second": 8.808,
+      "eval_steps_per_second": 4.404,
+      "step": 16
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 21.48629379272461,
+      "learning_rate": 0.00019118998459920902,
+      "loss": 0.8027,
+      "step": 17
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 38.0982666015625,
+      "learning_rate": 0.000188545602565321,
+      "loss": 1.7772,
+      "step": 18
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 10.824837684631348,
+      "learning_rate": 0.00018557812723014476,
+      "loss": 0.7737,
+      "step": 19
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 9.1353120803833,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.534,
+      "step": 20
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.4847445785999298,
+      "eval_runtime": 1.3637,
+      "eval_samples_per_second": 8.799,
+      "eval_steps_per_second": 4.4,
+      "step": 20
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 3.8411033153533936,
+      "learning_rate": 0.00017871834806090501,
+      "loss": 0.3201,
+      "step": 21
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 23.888507843017578,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 2.2541,
+      "step": 22
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 8.5956392288208,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.8177,
+      "step": 23
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.825141191482544,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.4624,
+      "step": 24
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.5740255117416382,
+      "eval_runtime": 1.3655,
+      "eval_samples_per_second": 8.788,
+      "eval_steps_per_second": 4.394,
+      "step": 24
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.558993101119995,
+      "learning_rate": 0.00016167188726285434,
+      "loss": 0.3714,
+      "step": 25
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 11.759211540222168,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6562,
+      "step": 26
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 96.2179183959961,
+      "learning_rate": 0.00015173378141776568,
+      "loss": 1.5141,
+      "step": 27
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 31.022045135498047,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.7753,
+      "step": 28
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.3771994113922119,
+      "eval_runtime": 1.3676,
+      "eval_samples_per_second": 8.775,
+      "eval_steps_per_second": 4.387,
+      "step": 28
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 3.5004501342773438,
+      "learning_rate": 0.0001410412805452757,
+      "loss": 0.2649,
+      "step": 29
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 5.16464376449585,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.171,
+      "step": 30
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 25.634010314941406,
+      "learning_rate": 0.00012975030538552032,
+      "loss": 0.9172,
+      "step": 31
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 7.102908134460449,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.3324,
+      "step": 32
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 0.29374203085899353,
+      "eval_runtime": 1.3678,
+      "eval_samples_per_second": 8.773,
+      "eval_steps_per_second": 4.387,
+      "step": 32
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 6.236325263977051,
+      "learning_rate": 0.0001180255037813906,
+      "loss": 0.4932,
+      "step": 33
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 4.445058345794678,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.1284,
+      "step": 34
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 6.94170618057251,
+      "learning_rate": 0.00010603784974222861,
+      "loss": 0.1547,
+      "step": 35
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.656033039093018,
+      "learning_rate": 0.0001,
+      "loss": 0.1973,
+      "step": 36
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 0.5674905180931091,
+      "eval_runtime": 1.3681,
+      "eval_samples_per_second": 8.771,
+      "eval_steps_per_second": 4.386,
+      "step": 36
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 18.19667625427246,
+      "learning_rate": 9.396215025777139e-05,
+      "loss": 0.4884,
+      "step": 37
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 17.964893341064453,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.5526,
+      "step": 38
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 5.015590190887451,
+      "learning_rate": 8.197449621860943e-05,
+      "loss": 0.2116,
+      "step": 39
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 5.6883225440979,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 0.0843,
+      "step": 40
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 0.2360386848449707,
+      "eval_runtime": 1.3667,
+      "eval_samples_per_second": 8.78,
+      "eval_steps_per_second": 4.39,
+      "step": 40
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 6.636446475982666,
+      "learning_rate": 7.024969461447972e-05,
+      "loss": 0.1158,
+      "step": 41
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.405576229095459,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.2755,
+      "step": 42
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 1.6179524660110474,
+      "learning_rate": 5.8958719454724346e-05,
+      "loss": 0.0186,
+      "step": 43
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 8.783114433288574,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 0.3836,
+      "step": 44
+    },
+    {
+      "epoch": 3.52,
+      "eval_loss": 0.13969357311725616,
+      "eval_runtime": 1.3687,
+      "eval_samples_per_second": 8.767,
+      "eval_steps_per_second": 4.384,
+      "step": 44
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.8835445046424866,
+      "learning_rate": 4.826621858223431e-05,
+      "loss": 0.0141,
+      "step": 45
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 12.678099632263184,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.6196,
+      "step": 46
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 5.320870876312256,
+      "learning_rate": 3.832811273714569e-05,
+      "loss": 0.0948,
+      "step": 47
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.7501108646392822,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 0.0449,
+      "step": 48
+    },
+    {
+      "epoch": 3.84,
+      "eval_loss": 0.2801015079021454,
+      "eval_runtime": 1.3706,
+      "eval_samples_per_second": 8.755,
+      "eval_steps_per_second": 4.378,
+      "step": 48
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 4.41072940826416,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.3026,
+      "step": 49
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2105910778045654,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.0152,
+      "step": 50
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 4.502895355224609,
+      "learning_rate": 2.1281651939094992e-05,
+      "loss": 0.0629,
+      "step": 51
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 6.058006286621094,
+      "learning_rate": 1.7701613410634365e-05,
+      "loss": 0.2246,
+      "step": 52
+    },
+    {
+      "epoch": 4.16,
+      "eval_loss": 0.19463467597961426,
+      "eval_runtime": 1.3725,
+      "eval_samples_per_second": 8.743,
+      "eval_steps_per_second": 4.372,
+      "step": 52
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 62,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 13,
+  "total_flos": 4552939045650432.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-52/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fede3f83b4ad6ce095e0aa09047d95bd4acc13170780f9e890d9d17d1bdace
+size 5624

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

merged/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

merged/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0.dev0"
+}

merged/pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbefe924d88ca0cd30bc695b27d524c7a1e1e102eec3c44809d78da182784d6e
+size 4943185632

merged/pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244c470b7b7bf63e652eeabed256b9e48b9b627ac0ea8423bf217435390a8e32
+size 4999844744

merged/pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6497299148ff6b197c49bd7046c4f481c732c2edb190f31af6780102b5fe911f
+size 4540537414

merged/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

merged/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

merged/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

merged/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

runs/Apr09_08-29-36_gpu06.pri.dmog.alces.network/events.out.tfevents.1712647777.gpu06.pri.dmog.alces.network.30736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b916e565a77dcb7d5bd53aba6f367407f84d56fd38e46a20f33d8b05d82f6ec7
+size 23212

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}