Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: alpindale/Mistral-7B-v0.2-hf
+model-index:
+- name: train_2024-05-15-20-33-30
+  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. -->
+
+# train_2024-05-15-20-33-30
+
+This model is a fine-tuned version of [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) on the emoji_add_instruction_zh dataset.
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0ee3c7c0db814c8a923893c59e8b5c1385c5390e9d984b0e9fe53b17d006bc
+size 13648432

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9975510204081632,
+    "total_flos": 2.854627336867676e+17,
+    "train_loss": 0.0628165303362221,
+    "train_runtime": 9275.9124,
+    "train_samples_per_second": 0.792,
+    "train_steps_per_second": 0.049
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: alpindale/Mistral-7B-v0.2-hf
+---
+
+# 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 0.10.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337a007c5e33fd84bc2c5ca8bc53acdc42f89f41046572dc35aad6349e07d7e2
+size 13648432

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355be49f1184c958521a04a4686f287e5d7f1d83a0a0bf558612ede7263afc8b
+size 27370618

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60400665774c60f2b71ad469813f6e3297e12b0741193b44997e31623e04be92
+size 1064

checkpoint-100/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
+  }
+}

checkpoint-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6530612244897959,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 0.3159657120704651,
+      "learning_rate": 4.9985361990992455e-05,
+      "loss": 0.1654,
+      "step": 5
+    },
+    {
+      "epoch": 0.0653061224489796,
+      "grad_norm": 0.32706642150878906,
+      "learning_rate": 4.9941465105674435e-05,
+      "loss": 0.1369,
+      "step": 10
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": 0.33407843112945557,
+      "learning_rate": 4.986836074908616e-05,
+      "loss": 0.1259,
+      "step": 15
+    },
+    {
+      "epoch": 0.1306122448979592,
+      "grad_norm": 0.3189881443977356,
+      "learning_rate": 4.976613452940604e-05,
+      "loss": 0.1041,
+      "step": 20
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.3424989581108093,
+      "learning_rate": 4.9634906157700036e-05,
+      "loss": 0.1004,
+      "step": 25
+    },
+    {
+      "epoch": 0.19591836734693877,
+      "grad_norm": 0.3253389298915863,
+      "learning_rate": 4.9474829307735115e-05,
+      "loss": 0.0941,
+      "step": 30
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.26078635454177856,
+      "learning_rate": 4.9286091436021015e-05,
+      "loss": 0.0867,
+      "step": 35
+    },
+    {
+      "epoch": 0.2612244897959184,
+      "grad_norm": 0.252139687538147,
+      "learning_rate": 4.906891356229103e-05,
+      "loss": 0.0853,
+      "step": 40
+    },
+    {
+      "epoch": 0.2938775510204082,
+      "grad_norm": 0.3403972387313843,
+      "learning_rate": 4.882355001067892e-05,
+      "loss": 0.0863,
+      "step": 45
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.4710679352283478,
+      "learning_rate": 4.855028811189496e-05,
+      "loss": 0.0874,
+      "step": 50
+    },
+    {
+      "epoch": 0.35918367346938773,
+      "grad_norm": 0.3147217929363251,
+      "learning_rate": 4.8249447866750025e-05,
+      "loss": 0.0733,
+      "step": 55
+    },
+    {
+      "epoch": 0.39183673469387753,
+      "grad_norm": 0.3265310823917389,
+      "learning_rate": 4.792138157142158e-05,
+      "loss": 0.0719,
+      "step": 60
+    },
+    {
+      "epoch": 0.42448979591836733,
+      "grad_norm": 0.35432252287864685,
+      "learning_rate": 4.75664734049005e-05,
+      "loss": 0.0824,
+      "step": 65
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.3701626658439636,
+      "learning_rate": 4.7185138979101864e-05,
+      "loss": 0.0731,
+      "step": 70
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.35868266224861145,
+      "learning_rate": 4.677782485216644e-05,
+      "loss": 0.0725,
+      "step": 75
+    },
+    {
+      "epoch": 0.5224489795918368,
+      "grad_norm": 0.32440632581710815,
+      "learning_rate": 4.6345008005522966e-05,
+      "loss": 0.0694,
+      "step": 80
+    },
+    {
+      "epoch": 0.5551020408163265,
+      "grad_norm": 0.3003002405166626,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.072,
+      "step": 85
+    },
+    {
+      "epoch": 0.5877551020408164,
+      "grad_norm": 0.34989920258522034,
+      "learning_rate": 4.540492280890555e-05,
+      "loss": 0.0646,
+      "step": 90
+    },
+    {
+      "epoch": 0.6204081632653061,
+      "grad_norm": 0.473254919052124,
+      "learning_rate": 4.4898755336977673e-05,
+      "loss": 0.0732,
+      "step": 95
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.30768489837646484,
+      "learning_rate": 4.436928561226087e-05,
+      "loss": 0.068,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 459,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 6.206244600230707e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe05743275e1a0b3185dbc2310f1e055d91d945545cf3f061569e23d25ef075
+size 5176

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: alpindale/Mistral-7B-v0.2-hf
+---
+
+# 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 0.10.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b4c3211836f8f090b5c5553fc90f8e75b61952ddf3e2f1064a48a4abdb9221
+size 13648432

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834005fc5a7e669ca5804fb0bcf7d240428dea685db48c6b0fbd5488d250477e
+size 27370618

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b893e975e740234419d36aadc594ec6b92d665b03b7a3bcd3c414b51ea42ab7
+size 1064

checkpoint-200/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
+  }
+}

checkpoint-200/tokenizer.model

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.306122448979592,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 0.3159657120704651,
+      "learning_rate": 4.9985361990992455e-05,
+      "loss": 0.1654,
+      "step": 5
+    },
+    {
+      "epoch": 0.0653061224489796,
+      "grad_norm": 0.32706642150878906,
+      "learning_rate": 4.9941465105674435e-05,
+      "loss": 0.1369,
+      "step": 10
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": 0.33407843112945557,
+      "learning_rate": 4.986836074908616e-05,
+      "loss": 0.1259,
+      "step": 15
+    },
+    {
+      "epoch": 0.1306122448979592,
+      "grad_norm": 0.3189881443977356,
+      "learning_rate": 4.976613452940604e-05,
+      "loss": 0.1041,
+      "step": 20
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.3424989581108093,
+      "learning_rate": 4.9634906157700036e-05,
+      "loss": 0.1004,
+      "step": 25
+    },
+    {
+      "epoch": 0.19591836734693877,
+      "grad_norm": 0.3253389298915863,
+      "learning_rate": 4.9474829307735115e-05,
+      "loss": 0.0941,
+      "step": 30
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.26078635454177856,
+      "learning_rate": 4.9286091436021015e-05,
+      "loss": 0.0867,
+      "step": 35
+    },
+    {
+      "epoch": 0.2612244897959184,
+      "grad_norm": 0.252139687538147,
+      "learning_rate": 4.906891356229103e-05,
+      "loss": 0.0853,
+      "step": 40
+    },
+    {
+      "epoch": 0.2938775510204082,
+      "grad_norm": 0.3403972387313843,
+      "learning_rate": 4.882355001067892e-05,
+      "loss": 0.0863,
+      "step": 45
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.4710679352283478,
+      "learning_rate": 4.855028811189496e-05,
+      "loss": 0.0874,
+      "step": 50
+    },
+    {
+      "epoch": 0.35918367346938773,
+      "grad_norm": 0.3147217929363251,
+      "learning_rate": 4.8249447866750025e-05,
+      "loss": 0.0733,
+      "step": 55
+    },
+    {
+      "epoch": 0.39183673469387753,
+      "grad_norm": 0.3265310823917389,
+      "learning_rate": 4.792138157142158e-05,
+      "loss": 0.0719,
+      "step": 60
+    },
+    {
+      "epoch": 0.42448979591836733,
+      "grad_norm": 0.35432252287864685,
+      "learning_rate": 4.75664734049005e-05,
+      "loss": 0.0824,
+      "step": 65
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.3701626658439636,
+      "learning_rate": 4.7185138979101864e-05,
+      "loss": 0.0731,
+      "step": 70
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.35868266224861145,
+      "learning_rate": 4.677782485216644e-05,
+      "loss": 0.0725,
+      "step": 75
+    },
+    {
+      "epoch": 0.5224489795918368,
+      "grad_norm": 0.32440632581710815,
+      "learning_rate": 4.6345008005522966e-05,
+      "loss": 0.0694,
+      "step": 80
+    },
+    {
+      "epoch": 0.5551020408163265,
+      "grad_norm": 0.3003002405166626,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.072,
+      "step": 85
+    },
+    {
+      "epoch": 0.5877551020408164,
+      "grad_norm": 0.34989920258522034,
+      "learning_rate": 4.540492280890555e-05,
+      "loss": 0.0646,
+      "step": 90
+    },
+    {
+      "epoch": 0.6204081632653061,
+      "grad_norm": 0.473254919052124,
+      "learning_rate": 4.4898755336977673e-05,
+      "loss": 0.0732,
+      "step": 95
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.30768489837646484,
+      "learning_rate": 4.436928561226087e-05,
+      "loss": 0.068,
+      "step": 100
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.31777673959732056,
+      "learning_rate": 4.381713366536311e-05,
+      "loss": 0.0749,
+      "step": 105
+    },
+    {
+      "epoch": 0.7183673469387755,
+      "grad_norm": 0.40202295780181885,
+      "learning_rate": 4.324294608869817e-05,
+      "loss": 0.0652,
+      "step": 110
+    },
+    {
+      "epoch": 0.7510204081632653,
+      "grad_norm": 0.4353463053703308,
+      "learning_rate": 4.264739527929959e-05,
+      "loss": 0.0562,
+      "step": 115
+    },
+    {
+      "epoch": 0.7836734693877551,
+      "grad_norm": 0.4079282879829407,
+      "learning_rate": 4.203117865141635e-05,
+      "loss": 0.0602,
+      "step": 120
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.40490931272506714,
+      "learning_rate": 4.1395017819812445e-05,
+      "loss": 0.0639,
+      "step": 125
+    },
+    {
+      "epoch": 0.8489795918367347,
+      "grad_norm": 0.423981636762619,
+      "learning_rate": 4.07396577547265e-05,
+      "loss": 0.0651,
+      "step": 130
+    },
+    {
+      "epoch": 0.8816326530612245,
+      "grad_norm": 0.3315489590167999,
+      "learning_rate": 4.0065865909481417e-05,
+      "loss": 0.0676,
+      "step": 135
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.560667097568512,
+      "learning_rate": 3.937443132176517e-05,
+      "loss": 0.0669,
+      "step": 140
+    },
+    {
+      "epoch": 0.9469387755102041,
+      "grad_norm": 0.4202517569065094,
+      "learning_rate": 3.8666163689635616e-05,
+      "loss": 0.0631,
+      "step": 145
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.4563729465007782,
+      "learning_rate": 3.794189242333106e-05,
+      "loss": 0.0649,
+      "step": 150
+    },
+    {
+      "epoch": 1.0122448979591836,
+      "grad_norm": 0.3522864580154419,
+      "learning_rate": 3.720246567399712e-05,
+      "loss": 0.059,
+      "step": 155
+    },
+    {
+      "epoch": 1.0448979591836736,
+      "grad_norm": 0.38459908962249756,
+      "learning_rate": 3.644874934046716e-05,
+      "loss": 0.062,
+      "step": 160
+    },
+    {
+      "epoch": 1.0775510204081633,
+      "grad_norm": 0.37406954169273376,
+      "learning_rate": 3.568162605525953e-05,
+      "loss": 0.0565,
+      "step": 165
+    },
+    {
+      "epoch": 1.110204081632653,
+      "grad_norm": 0.3395706117153168,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.0575,
+      "step": 170
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.31273558735847473,
+      "learning_rate": 3.4110766608332347e-05,
+      "loss": 0.0589,
+      "step": 175
+    },
+    {
+      "epoch": 1.1755102040816325,
+      "grad_norm": 0.44675061106681824,
+      "learning_rate": 3.330886998699149e-05,
+      "loss": 0.0611,
+      "step": 180
+    },
+    {
+      "epoch": 1.2081632653061225,
+      "grad_norm": 0.34769827127456665,
+      "learning_rate": 3.249724334055367e-05,
+      "loss": 0.062,
+      "step": 185
+    },
+    {
+      "epoch": 1.2408163265306122,
+      "grad_norm": 0.31832146644592285,
+      "learning_rate": 3.167683711687179e-05,
+      "loss": 0.0616,
+      "step": 190
+    },
+    {
+      "epoch": 1.273469387755102,
+      "grad_norm": 0.4153653085231781,
+      "learning_rate": 3.084861204504122e-05,
+      "loss": 0.0586,
+      "step": 195
+    },
+    {
+      "epoch": 1.306122448979592,
+      "grad_norm": 0.36249643564224243,
+      "learning_rate": 3.001353801034688e-05,
+      "loss": 0.0578,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 459,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.2409791545887949e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe05743275e1a0b3185dbc2310f1e055d91d945545cf3f061569e23d25ef075
+size 5176

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: alpindale/Mistral-7B-v0.2-hf
+---
+
+# 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 0.10.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3bb6500834c9d6e25bd8065d4f0281bcc9a438c6f9caa42db180e6d212b220
+size 13648432

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadc12cc068eba00e32e5259c8cc5eb1d94cf0c29552675656ece7094a5df973
+size 27370618

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99d6c2946d36f46592ac10a40e825eee13c06aeb3529100a7cb0e0070e050e4
+size 1064

checkpoint-300/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
+  }
+}

checkpoint-300/tokenizer.model

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

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9591836734693877,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 0.3159657120704651,
+      "learning_rate": 4.9985361990992455e-05,
+      "loss": 0.1654,
+      "step": 5
+    },
+    {
+      "epoch": 0.0653061224489796,
+      "grad_norm": 0.32706642150878906,
+      "learning_rate": 4.9941465105674435e-05,
+      "loss": 0.1369,
+      "step": 10
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": 0.33407843112945557,
+      "learning_rate": 4.986836074908616e-05,
+      "loss": 0.1259,
+      "step": 15
+    },
+    {
+      "epoch": 0.1306122448979592,
+      "grad_norm": 0.3189881443977356,
+      "learning_rate": 4.976613452940604e-05,
+      "loss": 0.1041,
+      "step": 20
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.3424989581108093,
+      "learning_rate": 4.9634906157700036e-05,
+      "loss": 0.1004,
+      "step": 25
+    },
+    {
+      "epoch": 0.19591836734693877,
+      "grad_norm": 0.3253389298915863,
+      "learning_rate": 4.9474829307735115e-05,
+      "loss": 0.0941,
+      "step": 30
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.26078635454177856,
+      "learning_rate": 4.9286091436021015e-05,
+      "loss": 0.0867,
+      "step": 35
+    },
+    {
+      "epoch": 0.2612244897959184,
+      "grad_norm": 0.252139687538147,
+      "learning_rate": 4.906891356229103e-05,
+      "loss": 0.0853,
+      "step": 40
+    },
+    {
+      "epoch": 0.2938775510204082,
+      "grad_norm": 0.3403972387313843,
+      "learning_rate": 4.882355001067892e-05,
+      "loss": 0.0863,
+      "step": 45
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.4710679352283478,
+      "learning_rate": 4.855028811189496e-05,
+      "loss": 0.0874,
+      "step": 50
+    },
+    {
+      "epoch": 0.35918367346938773,
+      "grad_norm": 0.3147217929363251,
+      "learning_rate": 4.8249447866750025e-05,
+      "loss": 0.0733,
+      "step": 55
+    },
+    {
+      "epoch": 0.39183673469387753,
+      "grad_norm": 0.3265310823917389,
+      "learning_rate": 4.792138157142158e-05,
+      "loss": 0.0719,
+      "step": 60
+    },
+    {
+      "epoch": 0.42448979591836733,
+      "grad_norm": 0.35432252287864685,
+      "learning_rate": 4.75664734049005e-05,
+      "loss": 0.0824,
+      "step": 65
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.3701626658439636,
+      "learning_rate": 4.7185138979101864e-05,
+      "loss": 0.0731,
+      "step": 70
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.35868266224861145,
+      "learning_rate": 4.677782485216644e-05,
+      "loss": 0.0725,
+      "step": 75
+    },
+    {
+      "epoch": 0.5224489795918368,
+      "grad_norm": 0.32440632581710815,
+      "learning_rate": 4.6345008005522966e-05,
+      "loss": 0.0694,
+      "step": 80
+    },
+    {
+      "epoch": 0.5551020408163265,
+      "grad_norm": 0.3003002405166626,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.072,
+      "step": 85
+    },
+    {
+      "epoch": 0.5877551020408164,
+      "grad_norm": 0.34989920258522034,
+      "learning_rate": 4.540492280890555e-05,
+      "loss": 0.0646,
+      "step": 90
+    },
+    {
+      "epoch": 0.6204081632653061,
+      "grad_norm": 0.473254919052124,
+      "learning_rate": 4.4898755336977673e-05,
+      "loss": 0.0732,
+      "step": 95
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.30768489837646484,
+      "learning_rate": 4.436928561226087e-05,
+      "loss": 0.068,
+      "step": 100
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.31777673959732056,
+      "learning_rate": 4.381713366536311e-05,
+      "loss": 0.0749,
+      "step": 105
+    },
+    {
+      "epoch": 0.7183673469387755,
+      "grad_norm": 0.40202295780181885,
+      "learning_rate": 4.324294608869817e-05,
+      "loss": 0.0652,
+      "step": 110
+    },
+    {
+      "epoch": 0.7510204081632653,
+      "grad_norm": 0.4353463053703308,
+      "learning_rate": 4.264739527929959e-05,
+      "loss": 0.0562,
+      "step": 115
+    },
+    {
+      "epoch": 0.7836734693877551,
+      "grad_norm": 0.4079282879829407,
+      "learning_rate": 4.203117865141635e-05,
+      "loss": 0.0602,
+      "step": 120
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.40490931272506714,
+      "learning_rate": 4.1395017819812445e-05,
+      "loss": 0.0639,
+      "step": 125
+    },
+    {
+      "epoch": 0.8489795918367347,
+      "grad_norm": 0.423981636762619,
+      "learning_rate": 4.07396577547265e-05,
+      "loss": 0.0651,
+      "step": 130
+    },
+    {
+      "epoch": 0.8816326530612245,
+      "grad_norm": 0.3315489590167999,
+      "learning_rate": 4.0065865909481417e-05,
+      "loss": 0.0676,
+      "step": 135
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.560667097568512,
+      "learning_rate": 3.937443132176517e-05,
+      "loss": 0.0669,
+      "step": 140
+    },
+    {
+      "epoch": 0.9469387755102041,
+      "grad_norm": 0.4202517569065094,
+      "learning_rate": 3.8666163689635616e-05,
+      "loss": 0.0631,
+      "step": 145
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.4563729465007782,
+      "learning_rate": 3.794189242333106e-05,
+      "loss": 0.0649,
+      "step": 150
+    },
+    {
+      "epoch": 1.0122448979591836,
+      "grad_norm": 0.3522864580154419,
+      "learning_rate": 3.720246567399712e-05,
+      "loss": 0.059,
+      "step": 155
+    },
+    {
+      "epoch": 1.0448979591836736,
+      "grad_norm": 0.38459908962249756,
+      "learning_rate": 3.644874934046716e-05,
+      "loss": 0.062,
+      "step": 160
+    },
+    {
+      "epoch": 1.0775510204081633,
+      "grad_norm": 0.37406954169273376,
+      "learning_rate": 3.568162605525953e-05,
+      "loss": 0.0565,
+      "step": 165
+    },
+    {
+      "epoch": 1.110204081632653,
+      "grad_norm": 0.3395706117153168,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.0575,
+      "step": 170
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.31273558735847473,
+      "learning_rate": 3.4110766608332347e-05,
+      "loss": 0.0589,
+      "step": 175
+    },
+    {
+      "epoch": 1.1755102040816325,
+      "grad_norm": 0.44675061106681824,
+      "learning_rate": 3.330886998699149e-05,
+      "loss": 0.0611,
+      "step": 180
+    },
+    {
+      "epoch": 1.2081632653061225,
+      "grad_norm": 0.34769827127456665,
+      "learning_rate": 3.249724334055367e-05,
+      "loss": 0.062,
+      "step": 185
+    },
+    {
+      "epoch": 1.2408163265306122,
+      "grad_norm": 0.31832146644592285,
+      "learning_rate": 3.167683711687179e-05,
+      "loss": 0.0616,
+      "step": 190
+    },
+    {
+      "epoch": 1.273469387755102,
+      "grad_norm": 0.4153653085231781,
+      "learning_rate": 3.084861204504122e-05,
+      "loss": 0.0586,
+      "step": 195
+    },
+    {
+      "epoch": 1.306122448979592,
+      "grad_norm": 0.36249643564224243,
+      "learning_rate": 3.001353801034688e-05,
+      "loss": 0.0578,
+      "step": 200
+    },
+    {
+      "epoch": 1.3387755102040817,
+      "grad_norm": 0.43447113037109375,
+      "learning_rate": 2.917259291848814e-05,
+      "loss": 0.0547,
+      "step": 205
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 0.3350294530391693,
+      "learning_rate": 2.8326761550411345e-05,
+      "loss": 0.0581,
+      "step": 210
+    },
+    {
+      "epoch": 1.4040816326530612,
+      "grad_norm": 0.34255513548851013,
+      "learning_rate": 2.747703440909128e-05,
+      "loss": 0.0535,
+      "step": 215
+    },
+    {
+      "epoch": 1.436734693877551,
+      "grad_norm": 0.6323994398117065,
+      "learning_rate": 2.662440655961183e-05,
+      "loss": 0.0666,
+      "step": 220
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": 0.3421262502670288,
+      "learning_rate": 2.5769876463904265e-05,
+      "loss": 0.053,
+      "step": 225
+    },
+    {
+      "epoch": 1.5020408163265306,
+      "grad_norm": 0.4133753478527069,
+      "learning_rate": 2.491444481150763e-05,
+      "loss": 0.0602,
+      "step": 230
+    },
+    {
+      "epoch": 1.5346938775510204,
+      "grad_norm": 0.37677302956581116,
+      "learning_rate": 2.4059113347720574e-05,
+      "loss": 0.0573,
+      "step": 235
+    },
+    {
+      "epoch": 1.5673469387755103,
+      "grad_norm": 0.3683429956436157,
+      "learning_rate": 2.3204883700516812e-05,
+      "loss": 0.0544,
+      "step": 240
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.34340280294418335,
+      "learning_rate": 2.235275620759797e-05,
+      "loss": 0.0552,
+      "step": 245
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.39541885256767273,
+      "learning_rate": 2.150372874495739e-05,
+      "loss": 0.0543,
+      "step": 250
+    },
+    {
+      "epoch": 1.6653061224489796,
+      "grad_norm": 0.384330689907074,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0481,
+      "step": 255
+    },
+    {
+      "epoch": 1.6979591836734693,
+      "grad_norm": 0.4634612798690796,
+      "learning_rate": 1.9818946098873766e-05,
+      "loss": 0.052,
+      "step": 260
+    },
+    {
+      "epoch": 1.730612244897959,
+      "grad_norm": 0.4186592400074005,
+      "learning_rate": 1.8985163864514645e-05,
+      "loss": 0.0516,
+      "step": 265
+    },
+    {
+      "epoch": 1.763265306122449,
+      "grad_norm": 0.4726428985595703,
+      "learning_rate": 1.815842524819793e-05,
+      "loss": 0.0559,
+      "step": 270
+    },
+    {
+      "epoch": 1.7959183673469388,
+      "grad_norm": 0.38660183548927307,
+      "learning_rate": 1.733969839450863e-05,
+      "loss": 0.0554,
+      "step": 275
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 0.40636590123176575,
+      "learning_rate": 1.6529942065931477e-05,
+      "loss": 0.0576,
+      "step": 280
+    },
+    {
+      "epoch": 1.8612244897959185,
+      "grad_norm": 0.3667762875556946,
+      "learning_rate": 1.5730104520100982e-05,
+      "loss": 0.0546,
+      "step": 285
+    },
+    {
+      "epoch": 1.8938775510204082,
+      "grad_norm": 0.38867512345314026,
+      "learning_rate": 1.4941122399353185e-05,
+      "loss": 0.0539,
+      "step": 290
+    },
+    {
+      "epoch": 1.926530612244898,
+      "grad_norm": 0.37944862246513367,
+      "learning_rate": 1.4163919633879324e-05,
+      "loss": 0.0537,
+      "step": 295
+    },
+    {
+      "epoch": 1.9591836734693877,
+      "grad_norm": 0.394191175699234,
+      "learning_rate": 1.339940635976592e-05,
+      "loss": 0.0493,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 459,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.8642398036380877e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe05743275e1a0b3185dbc2310f1e055d91d945545cf3f061569e23d25ef075
+size 5176

checkpoint-400/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: alpindale/Mistral-7B-v0.2-hf
+---
+
+# 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 0.10.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f44fe689c6a1969a4ec2f0a280e8548e0d301caa5938d00b682d6559bf93762
+size 13648432

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07b1bb5f3bc74b6484dd418751dc49bb89826c99c0295d649b6582f2c4de67a
+size 27370618

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d6fbdefdd70f2b18634581d91c76f8fc4f901712088d9523b488224d822533
+size 1064

checkpoint-400/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
+  }
+}

checkpoint-400/tokenizer.model

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

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}