Task: SequenceClassification

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8b37b3ddecd09fa8a562f4d73f4cee93598d06dda692ddd22b3be7079acb03
+size 83978160

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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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
+}

trainer_state-mistral-bnb8-QLORA-super_glue-multirc-sequence_classification.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.792,
+  "eval_steps": 1,
+  "global_step": 14,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.128,
+      "grad_norm": 426.2940979003906,
+      "learning_rate": 2.5e-05,
+      "loss": 7.2927,
+      "step": 1
+    },
+    {
+      "epoch": 0.128,
+      "eval_exact_match": 0.0,
+      "eval_f1_a": 0.0,
+      "eval_f1_m": 0.35077572820670067,
+      "eval_loss": 6.642009735107422,
+      "eval_runtime": 84.411,
+      "eval_samples_per_second": 2.962,
+      "eval_steps_per_second": 0.746,
+      "step": 1
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 358.92913818359375,
+      "learning_rate": 5e-05,
+      "loss": 6.6477,
+      "step": 2
+    },
+    {
+      "epoch": 0.256,
+      "eval_exact_match": 0.16326530612244897,
+      "eval_f1_a": 0.6279863481228669,
+      "eval_f1_m": 0.5070784590892632,
+      "eval_loss": 2.5748679637908936,
+      "eval_runtime": 84.5004,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 2
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 202.6668243408203,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.5318,
+      "step": 3
+    },
+    {
+      "epoch": 0.384,
+      "eval_exact_match": 0.2653061224489796,
+      "eval_f1_a": 0.6779661016949152,
+      "eval_f1_m": 0.6622228112024031,
+      "eval_loss": 1.5085991621017456,
+      "eval_runtime": 84.4987,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 3
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 89.18372344970703,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.021,
+      "step": 4
+    },
+    {
+      "epoch": 0.512,
+      "eval_exact_match": 0.0,
+      "eval_f1_a": 0.038834951456310676,
+      "eval_f1_m": 0.36717514511632166,
+      "eval_loss": 3.572444438934326,
+      "eval_runtime": 84.4787,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 4
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 249.71437072753906,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 3.3149,
+      "step": 5
+    },
+    {
+      "epoch": 0.64,
+      "eval_exact_match": 0.04081632653061224,
+      "eval_f1_a": 0.05769230769230769,
+      "eval_f1_m": 0.3837689254856121,
+      "eval_loss": 2.9223897457122803,
+      "eval_runtime": 84.4654,
+      "eval_samples_per_second": 2.96,
+      "eval_steps_per_second": 0.746,
+      "step": 5
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 234.4349365234375,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 3.0938,
+      "step": 6
+    },
+    {
+      "epoch": 0.768,
+      "eval_exact_match": 0.24489795918367346,
+      "eval_f1_a": 0.6127167630057804,
+      "eval_f1_m": 0.6370587195917328,
+      "eval_loss": 1.037977933883667,
+      "eval_runtime": 84.4697,
+      "eval_samples_per_second": 2.96,
+      "eval_steps_per_second": 0.746,
+      "step": 6
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 44.01259994506836,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.3183,
+      "step": 7
+    },
+    {
+      "epoch": 0.896,
+      "eval_exact_match": 0.2653061224489796,
+      "eval_f1_a": 0.6926406926406927,
+      "eval_f1_m": 0.6772793532997615,
+      "eval_loss": 0.9939583539962769,
+      "eval_runtime": 84.4865,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 7
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 80.42048645019531,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9766,
+      "step": 8
+    },
+    {
+      "epoch": 1.024,
+      "eval_exact_match": 0.32653061224489793,
+      "eval_f1_a": 0.709090909090909,
+      "eval_f1_m": 0.7124046588332301,
+      "eval_loss": 0.9605630040168762,
+      "eval_runtime": 84.508,
+      "eval_samples_per_second": 2.958,
+      "eval_steps_per_second": 0.745,
+      "step": 8
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 50.82283401489258,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.5821,
+      "step": 9
+    },
+    {
+      "epoch": 1.152,
+      "eval_exact_match": 0.3469387755102041,
+      "eval_f1_a": 0.694300518134715,
+      "eval_f1_m": 0.6903760638454516,
+      "eval_loss": 0.932707667350769,
+      "eval_runtime": 84.4808,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 9
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 47.22996139526367,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6158,
+      "step": 10
+    },
+    {
+      "epoch": 1.28,
+      "eval_exact_match": 0.3673469387755102,
+      "eval_f1_a": 0.6989247311827956,
+      "eval_f1_m": 0.7010895000690919,
+      "eval_loss": 0.9111232757568359,
+      "eval_runtime": 84.4887,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 10
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 70.53364562988281,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5635,
+      "step": 11
+    },
+    {
+      "epoch": 1.408,
+      "eval_exact_match": 0.3469387755102041,
+      "eval_f1_a": 0.7040816326530612,
+      "eval_f1_m": 0.7049636304738346,
+      "eval_loss": 0.8203014135360718,
+      "eval_runtime": 84.4658,
+      "eval_samples_per_second": 2.96,
+      "eval_steps_per_second": 0.746,
+      "step": 11
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 24.0622501373291,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5367,
+      "step": 12
+    },
+    {
+      "epoch": 1.536,
+      "eval_exact_match": 0.2857142857142857,
+      "eval_f1_a": 0.7115384615384615,
+      "eval_f1_m": 0.7037444414995435,
+      "eval_loss": 0.8254165649414062,
+      "eval_runtime": 84.4794,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 12
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 49.5471076965332,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.5805,
+      "step": 13
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "eval_exact_match": 0.3877551020408163,
+      "eval_f1_a": 0.7317073170731707,
+      "eval_f1_m": 0.7391583473216126,
+      "eval_loss": 0.7916401624679565,
+      "eval_runtime": 84.4743,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 13
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 32.582847595214844,
+      "learning_rate": 0.0,
+      "loss": 0.4737,
+      "step": 14
+    },
+    {
+      "epoch": 1.792,
+      "eval_exact_match": 0.3469387755102041,
+      "eval_f1_a": 0.6903553299492386,
+      "eval_f1_m": 0.6909562093235563,
+      "eval_loss": 0.7645593881607056,
+      "eval_runtime": 84.4968,
+      "eval_samples_per_second": 2.959,
+      "eval_steps_per_second": 0.746,
+      "step": 14
+    },
+    {
+      "epoch": 1.792,
+      "step": 14,
+      "total_flos": 4.3944687722496e+16,
+      "train_loss": 2.0392316984278813,
+      "train_runtime": 3611.0931,
+      "train_samples_per_second": 0.554,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 14,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4.3944687722496e+16,
+  "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 sha256:420b72de4274264a567cda7f4e581266500542a44c4d9bf0d20d010a605841d1
+size 5048