Upload folder using huggingface_hub

training_checkpoints/checkpoint-1125/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: facebook/bart-base
+---
+
+# 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

training_checkpoints/checkpoint-1125/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/bart-base",
+  "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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense",
+    "v_proj",
+    "fc1",
+    "fc2",
+    "out_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-1125/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab734cd5147930186cef472e28f2c9ed00b819f2652ba1cb2c60a01e622dcff7
+size 13151448

training_checkpoints/checkpoint-1125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35d0eecba2940bf39caf44fed4ac7d336b363cb00651d89ba23ad17ee9afd58
+size 26413626

training_checkpoints/checkpoint-1125/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8760187eb16e8c6ac4e2441520a067a8b7bcb47c0bf32058556dd9b80177bb06
+size 14244

training_checkpoints/checkpoint-1125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40224493aacf0cd0f7038028ae3514743b7f864ad570d1dd323ebd02caa1c08b
+size 1064

training_checkpoints/checkpoint-1125/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-1125/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_checkpoints/checkpoint-1125/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.5608894910772386,
+  "best_model_checkpoint": "bart-base-lora/checkpoint-1125",
+  "epoch": 6.998444790046657,
+  "eval_steps": 500,
+  "global_step": 1125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.611154144074361,
+      "eval_f1_macro": 0.28705545756004525,
+      "eval_f1_micro": 0.611154144074361,
+      "eval_f1_weighted": 0.5574695078229231,
+      "eval_loss": 1.3204560279846191,
+      "eval_macro_fpr": 0.046390243375546196,
+      "eval_macro_sensitivity": 0.302378554842108,
+      "eval_macro_specificity": 0.9691815961629444,
+      "eval_precision": 0.5321554731456403,
+      "eval_precision_macro": 0.2887439395071009,
+      "eval_recall": 0.611154144074361,
+      "eval_recall_macro": 0.302378554842108,
+      "eval_runtime": 45.1674,
+      "eval_samples_per_second": 28.583,
+      "eval_steps_per_second": 3.587,
+      "eval_weighted_fpr": 0.04347073086248701,
+      "eval_weighted_sensitivity": 0.611154144074361,
+      "eval_weighted_specificity": 0.9265697983698051,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6994577846630519,
+      "eval_f1_macro": 0.3947617401663212,
+      "eval_f1_micro": 0.6994577846630519,
+      "eval_f1_weighted": 0.6807748226338182,
+      "eval_loss": 0.887535810470581,
+      "eval_macro_fpr": 0.03062685085400977,
+      "eval_macro_sensitivity": 0.4253981018601158,
+      "eval_macro_specificity": 0.977359054380045,
+      "eval_precision": 0.6728416067370143,
+      "eval_precision_macro": 0.3822291983692299,
+      "eval_recall": 0.6994577846630519,
+      "eval_recall_macro": 0.4253981018601158,
+      "eval_runtime": 44.0045,
+      "eval_samples_per_second": 29.338,
+      "eval_steps_per_second": 3.681,
+      "eval_weighted_fpr": 0.02977743668457406,
+      "eval_weighted_sensitivity": 0.6994577846630519,
+      "eval_weighted_specificity": 0.9609280310376243,
+      "step": 321
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7064291247095275,
+      "eval_f1_macro": 0.39687975393644837,
+      "eval_f1_micro": 0.7064291247095275,
+      "eval_f1_weighted": 0.6751887743731854,
+      "eval_loss": 0.842707633972168,
+      "eval_macro_fpr": 0.029525759570689643,
+      "eval_macro_sensitivity": 0.44418263304043937,
+      "eval_macro_specificity": 0.9780349023882488,
+      "eval_precision": 0.6951917464608133,
+      "eval_precision_macro": 0.4131313886422618,
+      "eval_recall": 0.7064291247095275,
+      "eval_recall_macro": 0.44418263304043937,
+      "eval_runtime": 44.2756,
+      "eval_samples_per_second": 29.158,
+      "eval_steps_per_second": 3.659,
+      "eval_weighted_fpr": 0.02882786947592607,
+      "eval_weighted_sensitivity": 0.7064291247095275,
+      "eval_weighted_specificity": 0.9640944111142056,
+      "step": 482
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.2895,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7273431448489543,
+      "eval_f1_macro": 0.42839565617146974,
+      "eval_f1_micro": 0.7273431448489543,
+      "eval_f1_weighted": 0.7166656051521775,
+      "eval_loss": 0.7718679904937744,
+      "eval_macro_fpr": 0.026373610346420835,
+      "eval_macro_sensitivity": 0.4597947061276887,
+      "eval_macro_specificity": 0.9797578098165848,
+      "eval_precision": 0.7132141916978711,
+      "eval_precision_macro": 0.41981312370683244,
+      "eval_recall": 0.7273431448489543,
+      "eval_recall_macro": 0.4597947061276887,
+      "eval_runtime": 44.0471,
+      "eval_samples_per_second": 29.31,
+      "eval_steps_per_second": 3.678,
+      "eval_weighted_fpr": 0.026077937472218107,
+      "eval_weighted_sensitivity": 0.7273431448489543,
+      "eval_weighted_specificity": 0.9690240023998159,
+      "step": 643
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.750580945003873,
+      "eval_f1_macro": 0.5071625387211971,
+      "eval_f1_micro": 0.750580945003873,
+      "eval_f1_weighted": 0.7368350875727435,
+      "eval_loss": 0.7387559413909912,
+      "eval_macro_fpr": 0.02390193870216418,
+      "eval_macro_sensitivity": 0.5165232292614671,
+      "eval_macro_specificity": 0.9813510652812688,
+      "eval_precision": 0.739991301984922,
+      "eval_precision_macro": 0.5733174750951799,
+      "eval_recall": 0.750580945003873,
+      "eval_recall_macro": 0.5165232292614671,
+      "eval_runtime": 43.5191,
+      "eval_samples_per_second": 29.665,
+      "eval_steps_per_second": 3.723,
+      "eval_weighted_fpr": 0.023185483870967742,
+      "eval_weighted_sensitivity": 0.750580945003873,
+      "eval_weighted_specificity": 0.9696850342151593,
+      "step": 803
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7443841982958946,
+      "eval_f1_macro": 0.508766573370445,
+      "eval_f1_micro": 0.7443841982958946,
+      "eval_f1_weighted": 0.726841801268282,
+      "eval_loss": 0.7526118755340576,
+      "eval_macro_fpr": 0.024741953499129225,
+      "eval_macro_sensitivity": 0.5229557335240369,
+      "eval_macro_specificity": 0.980899976318631,
+      "eval_precision": 0.7337183019873953,
+      "eval_precision_macro": 0.5703412270657953,
+      "eval_recall": 0.7443841982958946,
+      "eval_recall_macro": 0.5229557335240369,
+      "eval_runtime": 43.7116,
+      "eval_samples_per_second": 29.534,
+      "eval_steps_per_second": 3.706,
+      "eval_weighted_fpr": 0.023940800928612886,
+      "eval_weighted_sensitivity": 0.7443841982958946,
+      "eval_weighted_specificity": 0.9691154464835722,
+      "step": 964
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.7332,
+      "step": 1000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7552285050348567,
+      "eval_f1_macro": 0.5608894910772386,
+      "eval_f1_micro": 0.7552285050348567,
+      "eval_f1_weighted": 0.7460771491633669,
+      "eval_loss": 0.7082085609436035,
+      "eval_macro_fpr": 0.02329269548734161,
+      "eval_macro_sensitivity": 0.5727565701904757,
+      "eval_macro_specificity": 0.9817624646436656,
+      "eval_precision": 0.7436383222975608,
+      "eval_precision_macro": 0.5665418243254761,
+      "eval_recall": 0.7552285050348567,
+      "eval_recall_macro": 0.5727565701904757,
+      "eval_runtime": 43.8592,
+      "eval_samples_per_second": 29.435,
+      "eval_steps_per_second": 3.694,
+      "eval_weighted_fpr": 0.02262637834741515,
+      "eval_weighted_sensitivity": 0.7552285050348567,
+      "eval_weighted_specificity": 0.9712084646201266,
+      "step": 1125
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2400,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 1.1393942951172096e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-1125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb230625284b71a8582d0495ae9a462b745f8cb976f9d7932c4f91357944609
+size 4600