Upload 13 files

README.md

@@ -1,3 +1,204 @@
 ---
-license: apache-2.0
+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 0.8.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e2d5baff34d3a6233c5518c00081c661359201d0c62d6e8f211a350d5426c5
+size 83945296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422de47b5306d6f6a0c7c5f2eb657ac7c6f8609a2ddd327d4486b371fc546d40
+size 168155346

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c14a4ae7ee0152d8a0f491146236125724084b6800f88df85d93b510b532730
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6f372a1f7681a08561ae2fcff28e0d72bb529c4c57eba4ba1f8700484bba04
+size 1064

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": "<unk>",
+  "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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.3364,
+      "step": 1
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011363636363636362,
+      "loss": 0.1163,
+      "step": 25
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001499042835718179,
+      "loss": 0.0592,
+      "step": 50
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00014941639959850612,
+      "loss": 0.0931,
+      "step": 75
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00014851784029408765,
+      "loss": 0.0872,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_dev.en.casimedicos.rag_loss": 0.060965459793806076,
+      "eval_dev.en.casimedicos.rag_runtime": 86.964,
+      "eval_dev.en.casimedicos.rag_samples_per_second": 0.724,
+      "eval_dev.en.casimedicos.rag_steps_per_second": 0.092,
+      "step": 109
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00014721356445987312,
+      "loss": 0.0679,
+      "step": 125
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00014551076988980255,
+      "loss": 0.0418,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00014341885364860423,
+      "loss": 0.0404,
+      "step": 175
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0001409493602130284,
+      "loss": 0.062,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_dev.en.casimedicos.rag_loss": 0.06188119202852249,
+      "eval_dev.en.casimedicos.rag_runtime": 84.614,
+      "eval_dev.en.casimedicos.rag_samples_per_second": 0.745,
+      "eval_dev.en.casimedicos.rag_steps_per_second": 0.095,
+      "step": 218
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013811591776234454,
+      "loss": 0.0473,
+      "step": 225
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00013493416296969042,
+      "loss": 0.0269,
+      "step": 250
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.0001314216547093198,
+      "loss": 0.0383,
+      "step": 275
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00012759777715596606,
+      "loss": 0.036,
+      "step": 300
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0001234836328110779,
+      "loss": 0.0292,
+      "step": 325
+    },
+    {
+      "epoch": 3.0,
+      "eval_dev.en.casimedicos.rag_loss": 0.07440634071826935,
+      "eval_dev.en.casimedicos.rag_runtime": 84.4854,
+      "eval_dev.en.casimedicos.rag_samples_per_second": 0.746,
+      "eval_dev.en.casimedicos.rag_steps_per_second": 0.095,
+      "step": 327
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.00011910192604627463,
+      "loss": 0.017,
+      "step": 350
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.00011447683780669952,
+      "loss": 0.0163,
+      "step": 375
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.00010963389216573467,
+      "loss": 0.0083,
+      "step": 400
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.00010459981546751072,
+      "loss": 0.0056,
+      "step": 425
+    },
+    {
+      "epoch": 4.0,
+      "eval_dev.en.casimedicos.rag_loss": 0.09140212833881378,
+      "eval_dev.en.casimedicos.rag_runtime": 83.9809,
+      "eval_dev.en.casimedicos.rag_samples_per_second": 0.75,
+      "eval_dev.en.casimedicos.rag_steps_per_second": 0.095,
+      "step": 436
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 9.940238883454927e-05,
+      "loss": 0.0003,
+      "step": 450
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 9.407029485449108e-05,
+      "loss": 0.003,
+      "step": 475
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 8.863295929198699e-05,
+      "loss": 0.0056,
+      "step": 500
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 8.312038869928251e-05,
+      "loss": 0.0027,
+      "step": 525
+    },
+    {
+      "epoch": 5.0,
+      "eval_dev.en.casimedicos.rag_loss": 0.11252260953187943,
+      "eval_dev.en.casimedicos.rag_runtime": 84.0376,
+      "eval_dev.en.casimedicos.rag_samples_per_second": 0.75,
+      "eval_dev.en.casimedicos.rag_steps_per_second": 0.095,
+      "step": 545
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1090,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 7.319956897348977e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d7c855d06d210edf88a2ed3a0eda7073fbb38a924e24ac1075187126f05cc3
+size 4984