add model adapter

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-21170/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-21170/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ''
+---
+
+# 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 0.9.0

checkpoint-21170/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "key",
+    "query"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-21170/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18a76ea7b61cb572e03d16f9615e4643635192c441cd099e19ed07523f46079
+size 3159000

checkpoint-21170/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e51988ce5f6a31231fed936bcf6ced7af735b0c6b2a9b6311197a5c75d500e
+size 6372346

checkpoint-21170/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289d9a23fe1dbe78cf989d441719a4887b91b21696c7ed15ac778b1087efc2ea
+size 14244

checkpoint-21170/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8873ad57fea546b50339a8abe08cd25381da881e029031769b96e70911ae633
+size 1064

checkpoint-21170/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_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
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-21170/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

checkpoint-21170/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-21170/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": 0.3467291593551636,
+  "best_model_checkpoint": "./models/e5_weighted_3\\checkpoint-21170",
+  "epoch": 10.0,
+  "eval_steps": 4234,
+  "global_step": 21170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6739985346794128,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4895,
+      "step": 4234
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6055607917059378,
+      "eval_f1_0: ": 0.0,
+      "eval_f1_1: ": 0.7543293219841503,
+      "eval_loss": 0.4801671504974365,
+      "eval_precision_0: ": 0.0,
+      "eval_precision_1: ": 0.6055607917059378,
+      "eval_recall_0: ": 0.0,
+      "eval_recall_1: ": 1.0,
+      "eval_runtime": 695.7116,
+      "eval_samples_per_second": 3.05,
+      "eval_steps_per_second": 3.05,
+      "step": 4234
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.520650863647461,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.474,
+      "step": 8468
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6710650329877474,
+      "eval_f1_0: ": 0.3102766798418972,
+      "eval_f1_1: ": 0.7840346534653465,
+      "eval_loss": 0.4519682228565216,
+      "eval_precision_0: ": 0.8971428571428571,
+      "eval_precision_1: ": 0.6507447354904982,
+      "eval_recall_0: ": 0.1875746714456392,
+      "eval_recall_1: ": 0.9859922178988327,
+      "eval_runtime": 685.0371,
+      "eval_samples_per_second": 3.098,
+      "eval_steps_per_second": 3.098,
+      "step": 8468
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5096299648284912,
+      "learning_rate": 1.4e-05,
+      "loss": 0.4505,
+      "step": 12702
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7445805843543827,
+      "eval_f1_0: ": 0.5505804311774462,
+      "eval_f1_1: ": 0.8215931533903884,
+      "eval_loss": 0.42401960492134094,
+      "eval_precision_0: ": 0.8997289972899729,
+      "eval_precision_1: ": 0.7119224187107815,
+      "eval_recall_0: ": 0.3966547192353644,
+      "eval_recall_1: ": 0.9712062256809338,
+      "eval_runtime": 684.6385,
+      "eval_samples_per_second": 3.099,
+      "eval_steps_per_second": 3.099,
+      "step": 12702
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.8480051755905151,
+      "learning_rate": 1.2e-05,
+      "loss": 0.418,
+      "step": 16936
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8044297832233742,
+      "eval_f1_0: ": 0.7182620502376104,
+      "eval_f1_1: ": 0.85023457235655,
+      "eval_loss": 0.37760457396507263,
+      "eval_precision_0: ": 0.8317610062893082,
+      "eval_precision_1: ": 0.7927321668909825,
+      "eval_recall_0: ": 0.6320191158900836,
+      "eval_recall_1: ": 0.9167315175097276,
+      "eval_runtime": 680.6302,
+      "eval_samples_per_second": 3.118,
+      "eval_steps_per_second": 3.118,
+      "step": 16936
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.9994410872459412,
+      "learning_rate": 1e-05,
+      "loss": 0.3911,
+      "step": 21170
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8185673892554194,
+      "eval_f1_0: ": 0.752411575562701,
+      "eval_f1_1: ": 0.8568240981777613,
+      "eval_loss": 0.3467291593551636,
+      "eval_precision_0: ": 0.8147632311977716,
+      "eval_precision_1: ": 0.8205128205128205,
+      "eval_recall_0: ": 0.6989247311827957,
+      "eval_recall_1: ": 0.8964980544747082,
+      "eval_runtime": 673.4114,
+      "eval_samples_per_second": 3.151,
+      "eval_steps_per_second": 3.151,
+      "step": 21170
+    }
+  ],
+  "logging_steps": 4234,
+  "max_steps": 42340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 4234,
+  "total_flos": 2.448451500060672e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-21170/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0fa3c600e1f2013e59655213a567ae15af751b91e56b48133bdd9bd5872e8d
+size 4920