Upload folder using huggingface_hub

training_checkpoints/checkpoint-19290/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: law-ai/InLegalBERT
+---
+
+# 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-19290/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "law-ai/InLegalBERT",
+  "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",
+    "value",
+    "query",
+    "key"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-19290/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05905410de4a7ce1af449a510910a761bc384f46ec0c1900a3fea0ded8f558cc
+size 104549068

training_checkpoints/checkpoint-19290/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 30522
+}

training_checkpoints/checkpoint-19290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fd721664c42bc60ad544c7d769a6b92d96dd6b23f6f7b4426a50ef3f5833fc
+size 21646778

training_checkpoints/checkpoint-19290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d80691acbdf0b779bdccf8a7cd6e941bab5386436837ad3f005161517b8f51
+size 14244

training_checkpoints/checkpoint-19290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d014a256bf001d56736fd3defeb750d943d6fab338696d9207f8f20f5ec7529
+size 1064

training_checkpoints/checkpoint-19290/special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

training_checkpoints/checkpoint-19290/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30522": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_checkpoints/checkpoint-19290/trainer_state.json

@@ -0,0 +1,907 @@
+{
+  "best_metric": 0.7798451044346006,
+  "best_model_checkpoint": "legal-bert-lora-no-grad/checkpoint-13503",
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 19290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.870399170554692e-05,
+      "loss": 1.6412,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7513555383423702,
+      "eval_f1_macro": 0.4277259717095209,
+      "eval_f1_micro": 0.7513555383423703,
+      "eval_f1_weighted": 0.7282568827191913,
+      "eval_loss": 0.7924586534500122,
+      "eval_macro_fpr": 0.023743972756733803,
+      "eval_macro_sensitivity": 0.47068996339347813,
+      "eval_macro_specificity": 0.9814182576870886,
+      "eval_precision": 0.7190272898782211,
+      "eval_precision_macro": 0.4122596954919311,
+      "eval_recall": 0.7513555383423702,
+      "eval_recall_macro": 0.47068996339347813,
+      "eval_runtime": 31.9941,
+      "eval_samples_per_second": 40.351,
+      "eval_steps_per_second": 5.063,
+      "eval_weighted_fpr": 0.023091863894683835,
+      "eval_weighted_sensitivity": 0.7513555383423702,
+      "eval_weighted_specificity": 0.9699183269639584,
+      "step": 643
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.740798341109383e-05,
+      "loss": 0.7481,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7900852052672347,
+      "eval_f1_macro": 0.5997806825026601,
+      "eval_f1_micro": 0.7900852052672347,
+      "eval_f1_weighted": 0.7768800571423996,
+      "eval_loss": 0.6771801710128784,
+      "eval_macro_fpr": 0.019203116699768798,
+      "eval_macro_sensitivity": 0.6251797015497511,
+      "eval_macro_specificity": 0.9842820395671547,
+      "eval_precision": 0.7726267649469656,
+      "eval_precision_macro": 0.595773614705663,
+      "eval_recall": 0.7900852052672347,
+      "eval_recall_macro": 0.6251797015497511,
+      "eval_runtime": 33.2196,
+      "eval_samples_per_second": 38.863,
+      "eval_steps_per_second": 4.877,
+      "eval_weighted_fpr": 0.018624149542986735,
+      "eval_weighted_sensitivity": 0.7900852052672347,
+      "eval_weighted_specificity": 0.9741453882400846,
+      "step": 1286
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.6111975116640746e-05,
+      "loss": 0.6465,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8048024786986832,
+      "eval_f1_macro": 0.610991978534836,
+      "eval_f1_micro": 0.804802478698683,
+      "eval_f1_weighted": 0.7903758160570191,
+      "eval_loss": 0.64998859167099,
+      "eval_macro_fpr": 0.017565196384739988,
+      "eval_macro_sensitivity": 0.6414017118652243,
+      "eval_macro_specificity": 0.9854108558122262,
+      "eval_precision": 0.7930969709541013,
+      "eval_precision_macro": 0.6215844916422869,
+      "eval_recall": 0.8048024786986832,
+      "eval_recall_macro": 0.6414017118652243,
+      "eval_runtime": 33.2556,
+      "eval_samples_per_second": 38.821,
+      "eval_steps_per_second": 4.871,
+      "eval_weighted_fpr": 0.017029328287606435,
+      "eval_weighted_sensitivity": 0.8048024786986832,
+      "eval_weighted_specificity": 0.9763603584847095,
+      "step": 1929
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.481596682218767e-05,
+      "loss": 0.5559,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.3519958527734576e-05,
+      "loss": 0.4707,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8094500387296669,
+      "eval_f1_macro": 0.6424924237429005,
+      "eval_f1_micro": 0.8094500387296669,
+      "eval_f1_weighted": 0.801786166531795,
+      "eval_loss": 0.6704407930374146,
+      "eval_macro_fpr": 0.017261054466023888,
+      "eval_macro_sensitivity": 0.6689319587406968,
+      "eval_macro_specificity": 0.9855970345792379,
+      "eval_precision": 0.8007850899141215,
+      "eval_precision_macro": 0.6321597811403302,
+      "eval_recall": 0.8094500387296669,
+      "eval_recall_macro": 0.6689319587406968,
+      "eval_runtime": 32.7354,
+      "eval_samples_per_second": 39.437,
+      "eval_steps_per_second": 4.949,
+      "eval_weighted_fpr": 0.016536703414896478,
+      "eval_weighted_sensitivity": 0.8094500387296669,
+      "eval_weighted_specificity": 0.9745054799589014,
+      "step": 2572
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 4.22239502332815e-05,
+      "loss": 0.4021,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8280402788536019,
+      "eval_f1_macro": 0.7571266313428899,
+      "eval_f1_micro": 0.8280402788536019,
+      "eval_f1_weighted": 0.8219004240794867,
+      "eval_loss": 0.7320332527160645,
+      "eval_macro_fpr": 0.015397351101601975,
+      "eval_macro_sensitivity": 0.7573467308503988,
+      "eval_macro_specificity": 0.9869691873059906,
+      "eval_precision": 0.8268949272272527,
+      "eval_precision_macro": 0.7782079900717894,
+      "eval_recall": 0.8280402788536019,
+      "eval_recall_macro": 0.7573467308503988,
+      "eval_runtime": 33.3254,
+      "eval_samples_per_second": 38.739,
+      "eval_steps_per_second": 4.861,
+      "eval_weighted_fpr": 0.014616802739004477,
+      "eval_weighted_sensitivity": 0.8280402788536019,
+      "eval_weighted_specificity": 0.9764975307362563,
+      "step": 3215
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 4.092794193882841e-05,
+      "loss": 0.3627,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8241673121611154,
+      "eval_f1_macro": 0.7374017625053243,
+      "eval_f1_micro": 0.8241673121611154,
+      "eval_f1_weighted": 0.8222929814764423,
+      "eval_loss": 0.6892128586769104,
+      "eval_macro_fpr": 0.015594676805191453,
+      "eval_macro_sensitivity": 0.7364879265668598,
+      "eval_macro_specificity": 0.9867341217946985,
+      "eval_precision": 0.822653270980506,
+      "eval_precision_macro": 0.7430958863475831,
+      "eval_recall": 0.8241673121611154,
+      "eval_recall_macro": 0.7364879265668598,
+      "eval_runtime": 32.5839,
+      "eval_samples_per_second": 39.621,
+      "eval_steps_per_second": 4.972,
+      "eval_weighted_fpr": 0.015010249289162203,
+      "eval_weighted_sensitivity": 0.8241673121611154,
+      "eval_weighted_specificity": 0.9768445147593636,
+      "step": 3858
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 3.963193364437533e-05,
+      "loss": 0.3623,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.833592534992224e-05,
+      "loss": 0.2866,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8179705654531371,
+      "eval_f1_macro": 0.7443559250736709,
+      "eval_f1_micro": 0.817970565453137,
+      "eval_f1_weighted": 0.8121793367264196,
+      "eval_loss": 0.8756108283996582,
+      "eval_macro_fpr": 0.016562044787314777,
+      "eval_macro_sensitivity": 0.7409975687139162,
+      "eval_macro_specificity": 0.9859854959008175,
+      "eval_precision": 0.8170676985045833,
+      "eval_precision_macro": 0.7748072523920921,
+      "eval_recall": 0.8179705654531371,
+      "eval_recall_macro": 0.7409975687139162,
+      "eval_runtime": 34.5334,
+      "eval_samples_per_second": 37.384,
+      "eval_steps_per_second": 4.691,
+      "eval_weighted_fpr": 0.01564684732671949,
+      "eval_weighted_sensitivity": 0.8179705654531371,
+      "eval_weighted_specificity": 0.9718118730591274,
+      "step": 4501
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 3.7039917055469156e-05,
+      "loss": 0.2639,
+      "step": 5000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8264910921766073,
+      "eval_f1_macro": 0.7480006271740781,
+      "eval_f1_micro": 0.8264910921766073,
+      "eval_f1_weighted": 0.8217020757246023,
+      "eval_loss": 0.8579551577568054,
+      "eval_macro_fpr": 0.0155160293084745,
+      "eval_macro_sensitivity": 0.7427592056873393,
+      "eval_macro_specificity": 0.9868042528312828,
+      "eval_precision": 0.8259376217895409,
+      "eval_precision_macro": 0.798909899893037,
+      "eval_recall": 0.8264910921766073,
+      "eval_recall_macro": 0.7427592056873393,
+      "eval_runtime": 33.4037,
+      "eval_samples_per_second": 38.648,
+      "eval_steps_per_second": 4.85,
+      "eval_weighted_fpr": 0.014773776546629732,
+      "eval_weighted_sensitivity": 0.8264910921766073,
+      "eval_weighted_specificity": 0.9755727002926348,
+      "step": 5144
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 3.574390876101607e-05,
+      "loss": 0.2295,
+      "step": 5500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.82571649883811,
+      "eval_f1_macro": 0.7524178623807065,
+      "eval_f1_micro": 0.82571649883811,
+      "eval_f1_weighted": 0.822346219811999,
+      "eval_loss": 0.9366260170936584,
+      "eval_macro_fpr": 0.015511369010760676,
+      "eval_macro_sensitivity": 0.7465079310173777,
+      "eval_macro_specificity": 0.9867928280373104,
+      "eval_precision": 0.8230871400583257,
+      "eval_precision_macro": 0.7724676433487055,
+      "eval_recall": 0.82571649883811,
+      "eval_recall_macro": 0.7465079310173777,
+      "eval_runtime": 33.4584,
+      "eval_samples_per_second": 38.585,
+      "eval_steps_per_second": 4.842,
+      "eval_weighted_fpr": 0.01485246550927454,
+      "eval_weighted_sensitivity": 0.82571649883811,
+      "eval_weighted_specificity": 0.976175921721546,
+      "step": 5787
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 3.4447900466562985e-05,
+      "loss": 0.195,
+      "step": 6000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8272656855151046,
+      "eval_f1_macro": 0.752814241629395,
+      "eval_f1_micro": 0.8272656855151046,
+      "eval_f1_weighted": 0.8241119102181389,
+      "eval_loss": 0.9685066342353821,
+      "eval_macro_fpr": 0.01532247779991636,
+      "eval_macro_sensitivity": 0.7514626154154147,
+      "eval_macro_specificity": 0.9869341007498275,
+      "eval_precision": 0.8235616888844944,
+      "eval_precision_macro": 0.7594602286715586,
+      "eval_recall": 0.8272656855151046,
+      "eval_recall_macro": 0.7514626154154147,
+      "eval_runtime": 32.9707,
+      "eval_samples_per_second": 39.156,
+      "eval_steps_per_second": 4.913,
+      "eval_weighted_fpr": 0.014695222405271829,
+      "eval_weighted_sensitivity": 0.8272656855151046,
+      "eval_weighted_specificity": 0.9767458257323062,
+      "step": 6430
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 3.315189217210991e-05,
+      "loss": 0.2071,
+      "step": 6500
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 3.1855883877656815e-05,
+      "loss": 0.1617,
+      "step": 7000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.831138652207591,
+      "eval_f1_macro": 0.7542626782968901,
+      "eval_f1_micro": 0.831138652207591,
+      "eval_f1_weighted": 0.8265278944879543,
+      "eval_loss": 1.0405933856964111,
+      "eval_macro_fpr": 0.014948189971054987,
+      "eval_macro_sensitivity": 0.7552299472419968,
+      "eval_macro_specificity": 0.9872461533889039,
+      "eval_precision": 0.8263112206278148,
+      "eval_precision_macro": 0.7615032315409404,
+      "eval_recall": 0.831138652207591,
+      "eval_recall_macro": 0.7552299472419968,
+      "eval_runtime": 32.4814,
+      "eval_samples_per_second": 39.746,
+      "eval_steps_per_second": 4.987,
+      "eval_weighted_fpr": 0.014304461942257218,
+      "eval_weighted_sensitivity": 0.831138652207591,
+      "eval_weighted_specificity": 0.9775536486259658,
+      "step": 7073
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 3.0559875583203736e-05,
+      "loss": 0.1421,
+      "step": 7500
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8319132455460883,
+      "eval_f1_macro": 0.7546443355775483,
+      "eval_f1_micro": 0.8319132455460883,
+      "eval_f1_weighted": 0.8286773098434994,
+      "eval_loss": 1.0712851285934448,
+      "eval_macro_fpr": 0.014849682505759526,
+      "eval_macro_sensitivity": 0.7533324298517142,
+      "eval_macro_specificity": 0.9872830280264108,
+      "eval_precision": 0.8275778384582335,
+      "eval_precision_macro": 0.7625814308958907,
+      "eval_recall": 0.8319132455460883,
+      "eval_recall_macro": 0.7533324298517142,
+      "eval_runtime": 33.7221,
+      "eval_samples_per_second": 38.284,
+      "eval_steps_per_second": 4.804,
+      "eval_weighted_fpr": 0.014226709499770536,
+      "eval_weighted_sensitivity": 0.8319132455460883,
+      "eval_weighted_specificity": 0.977332174850073,
+      "step": 7716
+    },
+    {
+      "epoch": 12.44,
+      "learning_rate": 2.926386728875065e-05,
+      "loss": 0.1184,
+      "step": 8000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.82571649883811,
+      "eval_f1_macro": 0.7510253218960331,
+      "eval_f1_micro": 0.82571649883811,
+      "eval_f1_weighted": 0.8218884223471629,
+      "eval_loss": 1.1124904155731201,
+      "eval_macro_fpr": 0.015517240035600281,
+      "eval_macro_sensitivity": 0.7503900667536906,
+      "eval_macro_specificity": 0.9868175907777439,
+      "eval_precision": 0.8208602037612678,
+      "eval_precision_macro": 0.7569190431250081,
+      "eval_recall": 0.82571649883811,
+      "eval_recall_macro": 0.7503900667536906,
+      "eval_runtime": 32.7063,
+      "eval_samples_per_second": 39.473,
+      "eval_steps_per_second": 4.953,
+      "eval_weighted_fpr": 0.01485246550927454,
+      "eval_weighted_sensitivity": 0.82571649883811,
+      "eval_weighted_specificity": 0.9765473628280475,
+      "step": 8359
+    },
+    {
+      "epoch": 13.22,
+      "learning_rate": 2.7967858994297562e-05,
+      "loss": 0.1157,
+      "step": 8500
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.667185069984448e-05,
+      "loss": 0.1017,
+      "step": 9000
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8210689388071263,
+      "eval_f1_macro": 0.7726753332748134,
+      "eval_f1_micro": 0.8210689388071263,
+      "eval_f1_weighted": 0.8196057150820856,
+      "eval_loss": 1.1926428079605103,
+      "eval_macro_fpr": 0.01592832331319769,
+      "eval_macro_sensitivity": 0.7814792076835096,
+      "eval_macro_specificity": 0.9865762698201747,
+      "eval_precision": 0.8214722394566816,
+      "eval_precision_macro": 0.7675145052350089,
+      "eval_recall": 0.8210689388071263,
+      "eval_recall_macro": 0.7814792076835096,
+      "eval_runtime": 33.1567,
+      "eval_samples_per_second": 38.936,
+      "eval_steps_per_second": 4.886,
+      "eval_weighted_fpr": 0.015327450069670227,
+      "eval_weighted_sensitivity": 0.8210689388071263,
+      "eval_weighted_specificity": 0.977575108495493,
+      "step": 9002
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 2.53758424053914e-05,
+      "loss": 0.0752,
+      "step": 9500
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.8164213787761425,
+      "eval_f1_macro": 0.740181771196266,
+      "eval_f1_micro": 0.8164213787761425,
+      "eval_f1_weighted": 0.8133417808004717,
+      "eval_loss": 1.2507578134536743,
+      "eval_macro_fpr": 0.016423646764491533,
+      "eval_macro_sensitivity": 0.7376546806118065,
+      "eval_macro_specificity": 0.9861141336738363,
+      "eval_precision": 0.8120522617771967,
+      "eval_precision_macro": 0.7479093161875279,
+      "eval_recall": 0.8164213787761425,
+      "eval_recall_macro": 0.7376546806118065,
+      "eval_runtime": 33.1196,
+      "eval_samples_per_second": 38.98,
+      "eval_steps_per_second": 4.891,
+      "eval_weighted_fpr": 0.01580737677582872,
+      "eval_weighted_sensitivity": 0.8164213787761425,
+      "eval_weighted_specificity": 0.9752906263314008,
+      "step": 9645
+    },
+    {
+      "epoch": 15.55,
+      "learning_rate": 2.4079834110938313e-05,
+      "loss": 0.0787,
+      "step": 10000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.7698437404057171,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.8187688080779877,
+      "eval_loss": 1.3246989250183105,
+      "eval_macro_fpr": 0.015979873481610722,
+      "eval_macro_sensitivity": 0.7584947789467064,
+      "eval_macro_specificity": 0.9864726076618879,
+      "eval_precision": 0.819938232209624,
+      "eval_precision_macro": 0.8033763498836805,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7584947789467064,
+      "eval_runtime": 33.1643,
+      "eval_samples_per_second": 38.927,
+      "eval_steps_per_second": 4.885,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.9752455827826969,
+      "step": 10288
+    },
+    {
+      "epoch": 16.33,
+      "learning_rate": 2.2783825816485228e-05,
+      "loss": 0.0668,
+      "step": 10500
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.8210689388071263,
+      "eval_f1_macro": 0.7468315966002393,
+      "eval_f1_micro": 0.8210689388071263,
+      "eval_f1_weighted": 0.8197761848180135,
+      "eval_loss": 1.3497052192687988,
+      "eval_macro_fpr": 0.01580496987707635,
+      "eval_macro_sensitivity": 0.7486969612108813,
+      "eval_macro_specificity": 0.9865911342551769,
+      "eval_precision": 0.8201285330679784,
+      "eval_precision_macro": 0.7499841938739371,
+      "eval_recall": 0.8210689388071263,
+      "eval_recall_macro": 0.7486969612108813,
+      "eval_runtime": 32.2442,
+      "eval_samples_per_second": 40.038,
+      "eval_steps_per_second": 5.024,
+      "eval_weighted_fpr": 0.015327450069670227,
+      "eval_weighted_sensitivity": 0.8210689388071263,
+      "eval_weighted_specificity": 0.9777980750205295,
+      "step": 10931
+    },
+    {
+      "epoch": 17.11,
+      "learning_rate": 2.1487817522032143e-05,
+      "loss": 0.0457,
+      "step": 11000
+    },
+    {
+      "epoch": 17.88,
+      "learning_rate": 2.0191809227579057e-05,
+      "loss": 0.0471,
+      "step": 11500
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8164213787761425,
+      "eval_f1_macro": 0.7644188412597084,
+      "eval_f1_micro": 0.8164213787761425,
+      "eval_f1_weighted": 0.8159145099342531,
+      "eval_loss": 1.4277746677398682,
+      "eval_macro_fpr": 0.01645147998475456,
+      "eval_macro_sensitivity": 0.7669665145653268,
+      "eval_macro_specificity": 0.9861526001666732,
+      "eval_precision": 0.8173561788436983,
+      "eval_precision_macro": 0.7672032880393017,
+      "eval_recall": 0.8164213787761425,
+      "eval_recall_macro": 0.7669665145653268,
+      "eval_runtime": 32.6421,
+      "eval_samples_per_second": 39.55,
+      "eval_steps_per_second": 4.963,
+      "eval_weighted_fpr": 0.01580737677582872,
+      "eval_weighted_sensitivity": 0.8164213787761425,
+      "eval_weighted_specificity": 0.9758676237239569,
+      "step": 11574
+    },
+    {
+      "epoch": 18.66,
+      "learning_rate": 1.8895800933125972e-05,
+      "loss": 0.0492,
+      "step": 12000
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.8179705654531371,
+      "eval_f1_macro": 0.7453033208790572,
+      "eval_f1_micro": 0.817970565453137,
+      "eval_f1_weighted": 0.815620086845711,
+      "eval_loss": 1.4784481525421143,
+      "eval_macro_fpr": 0.016224618841081385,
+      "eval_macro_sensitivity": 0.743144190937684,
+      "eval_macro_specificity": 0.9862867942836505,
+      "eval_precision": 0.8178114033858023,
+      "eval_precision_macro": 0.7631419722725519,
+      "eval_recall": 0.8179705654531371,
+      "eval_recall_macro": 0.743144190937684,
+      "eval_runtime": 36.8743,
+      "eval_samples_per_second": 35.011,
+      "eval_steps_per_second": 4.393,
+      "eval_weighted_fpr": 0.01564684732671949,
+      "eval_weighted_sensitivity": 0.8179705654531371,
+      "eval_weighted_specificity": 0.9763313488016223,
+      "step": 12217
+    },
+    {
+      "epoch": 19.44,
+      "learning_rate": 1.7599792638672887e-05,
+      "loss": 0.0368,
+      "step": 12500
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8195197521301317,
+      "eval_f1_macro": 0.7621759547269054,
+      "eval_f1_micro": 0.8195197521301317,
+      "eval_f1_weighted": 0.817963185592044,
+      "eval_loss": 1.4747339487075806,
+      "eval_macro_fpr": 0.01613456443240687,
+      "eval_macro_sensitivity": 0.7567902244133032,
+      "eval_macro_specificity": 0.9863676058849223,
+      "eval_precision": 0.8183422461388873,
+      "eval_precision_macro": 0.7729024081192102,
+      "eval_recall": 0.8195197521301317,
+      "eval_recall_macro": 0.7567902244133032,
+      "eval_runtime": 33.7742,
+      "eval_samples_per_second": 38.224,
+      "eval_steps_per_second": 4.797,
+      "eval_weighted_fpr": 0.01548687271518777,
+      "eval_weighted_sensitivity": 0.8195197521301317,
+      "eval_weighted_specificity": 0.9759943361437048,
+      "step": 12860
+    },
+    {
+      "epoch": 20.22,
+      "learning_rate": 1.6303784344219805e-05,
+      "loss": 0.0283,
+      "step": 13000
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 1.500777604976672e-05,
+      "loss": 0.0329,
+      "step": 13500
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.8280402788536019,
+      "eval_f1_macro": 0.7798451044346006,
+      "eval_f1_micro": 0.8280402788536019,
+      "eval_f1_weighted": 0.826772845769794,
+      "eval_loss": 1.5075095891952515,
+      "eval_macro_fpr": 0.015201804107211978,
+      "eval_macro_sensitivity": 0.7845100062460777,
+      "eval_macro_specificity": 0.9870807598208488,
+      "eval_precision": 0.8289805116198049,
+      "eval_precision_macro": 0.7825198626457465,
+      "eval_recall": 0.8280402788536019,
+      "eval_recall_macro": 0.7845100062460777,
+      "eval_runtime": 33.5257,
+      "eval_samples_per_second": 38.508,
+      "eval_steps_per_second": 4.832,
+      "eval_weighted_fpr": 0.014616802739004477,
+      "eval_weighted_sensitivity": 0.8280402788536019,
+      "eval_weighted_specificity": 0.9781711184591322,
+      "step": 13503
+    },
+    {
+      "epoch": 21.77,
+      "learning_rate": 1.3711767755313634e-05,
+      "loss": 0.0266,
+      "step": 14000
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.8272656855151046,
+      "eval_f1_macro": 0.765128228840441,
+      "eval_f1_micro": 0.8272656855151046,
+      "eval_f1_weighted": 0.8247163624860825,
+      "eval_loss": 1.4783282279968262,
+      "eval_macro_fpr": 0.015306165757253654,
+      "eval_macro_sensitivity": 0.7612370203923594,
+      "eval_macro_specificity": 0.9870078611821269,
+      "eval_precision": 0.826248912698554,
+      "eval_precision_macro": 0.7780325612996924,
+      "eval_recall": 0.8272656855151046,
+      "eval_recall_macro": 0.7612370203923594,
+      "eval_runtime": 32.6824,
+      "eval_samples_per_second": 39.501,
+      "eval_steps_per_second": 4.957,
+      "eval_weighted_fpr": 0.014695222405271829,
+      "eval_weighted_sensitivity": 0.8272656855151046,
+      "eval_weighted_specificity": 0.9778522322167991,
+      "step": 14146
+    },
+    {
+      "epoch": 22.55,
+      "learning_rate": 1.241575946086055e-05,
+      "loss": 0.0302,
+      "step": 14500
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.8233927188226181,
+      "eval_f1_macro": 0.7679149401665657,
+      "eval_f1_micro": 0.8233927188226181,
+      "eval_f1_weighted": 0.822363691525487,
+      "eval_loss": 1.5281126499176025,
+      "eval_macro_fpr": 0.01578769634505232,
+      "eval_macro_sensitivity": 0.769870430823106,
+      "eval_macro_specificity": 0.9866251949198597,
+      "eval_precision": 0.8246221729606811,
+      "eval_precision_macro": 0.7744500129487238,
+      "eval_recall": 0.8233927188226181,
+      "eval_recall_macro": 0.769870430823106,
+      "eval_runtime": 32.6209,
+      "eval_samples_per_second": 39.576,
+      "eval_steps_per_second": 4.966,
+      "eval_weighted_fpr": 0.015089344804765056,
+      "eval_weighted_sensitivity": 0.8233927188226181,
+      "eval_weighted_specificity": 0.9759852049752782,
+      "step": 14789
+    },
+    {
+      "epoch": 23.33,
+      "learning_rate": 1.1119751166407467e-05,
+      "loss": 0.0207,
+      "step": 15000
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.8264910921766073,
+      "eval_f1_macro": 0.7720566132705003,
+      "eval_f1_micro": 0.8264910921766073,
+      "eval_f1_weighted": 0.8248275404138076,
+      "eval_loss": 1.5474671125411987,
+      "eval_macro_fpr": 0.015452378985664239,
+      "eval_macro_sensitivity": 0.7726605197382722,
+      "eval_macro_specificity": 0.9868849046120488,
+      "eval_precision": 0.826237232491233,
+      "eval_precision_macro": 0.7809260488595394,
+      "eval_recall": 0.8264910921766073,
+      "eval_recall_macro": 0.7726605197382722,
+      "eval_runtime": 33.8928,
+      "eval_samples_per_second": 38.091,
+      "eval_steps_per_second": 4.78,
+      "eval_weighted_fpr": 0.014773776546629732,
+      "eval_weighted_sensitivity": 0.8264910921766073,
+      "eval_weighted_specificity": 0.9767824770041241,
+      "step": 15432
+    },
+    {
+      "epoch": 24.11,
+      "learning_rate": 9.82374287195438e-06,
+      "loss": 0.0107,
+      "step": 15500
+    },
+    {
+      "epoch": 24.88,
+      "learning_rate": 8.527734577501296e-06,
+      "loss": 0.0168,
+      "step": 16000
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.8241673121611154,
+      "eval_f1_macro": 0.7628766843062061,
+      "eval_f1_micro": 0.8241673121611154,
+      "eval_f1_weighted": 0.8231422521167715,
+      "eval_loss": 1.5236613750457764,
+      "eval_macro_fpr": 0.015538992240674433,
+      "eval_macro_sensitivity": 0.7618795505323602,
+      "eval_macro_specificity": 0.9867782540147019,
+      "eval_precision": 0.8236868454122461,
+      "eval_precision_macro": 0.7725526191062821,
+      "eval_recall": 0.8241673121611154,
+      "eval_recall_macro": 0.7618795505323602,
+      "eval_runtime": 33.5006,
+      "eval_samples_per_second": 38.537,
+      "eval_steps_per_second": 4.836,
+      "eval_weighted_fpr": 0.015010249289162203,
+      "eval_weighted_sensitivity": 0.8241673121611154,
+      "eval_weighted_specificity": 0.977506498059414,
+      "step": 16075
+    },
+    {
+      "epoch": 25.66,
+      "learning_rate": 7.2317262830482126e-06,
+      "loss": 0.0167,
+      "step": 16500
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.8233927188226181,
+      "eval_f1_macro": 0.7707209167508291,
+      "eval_f1_micro": 0.8233927188226181,
+      "eval_f1_weighted": 0.8232430254298418,
+      "eval_loss": 1.5814664363861084,
+      "eval_macro_fpr": 0.01564454124386674,
+      "eval_macro_sensitivity": 0.7727722480878652,
+      "eval_macro_specificity": 0.9867228825303838,
+      "eval_precision": 0.8254554866081273,
+      "eval_precision_macro": 0.7766099992749074,
+      "eval_recall": 0.8233927188226181,
+      "eval_recall_macro": 0.7727722480878652,
+      "eval_runtime": 33.0297,
+      "eval_samples_per_second": 39.086,
+      "eval_steps_per_second": 4.905,
+      "eval_weighted_fpr": 0.015089344804765056,
+      "eval_weighted_sensitivity": 0.8233927188226181,
+      "eval_weighted_specificity": 0.9774505191331391,
+      "step": 16718
+    },
+    {
+      "epoch": 26.44,
+      "learning_rate": 5.935717988595127e-06,
+      "loss": 0.0127,
+      "step": 17000
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.7708948022043273,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.8210863491796815,
+      "eval_loss": 1.6010326147079468,
+      "eval_macro_fpr": 0.01583806984289565,
+      "eval_macro_sensitivity": 0.7715917272078064,
+      "eval_macro_specificity": 0.9865804418598565,
+      "eval_precision": 0.8227874226730683,
+      "eval_precision_macro": 0.7790403153096314,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7715917272078064,
+      "eval_runtime": 32.782,
+      "eval_samples_per_second": 39.381,
+      "eval_steps_per_second": 4.942,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.9768630957522239,
+      "step": 17361
+    },
+    {
+      "epoch": 27.22,
+      "learning_rate": 4.639709694142043e-06,
+      "loss": 0.0092,
+      "step": 17500
+    },
+    {
+      "epoch": 27.99,
+      "learning_rate": 3.343701399688958e-06,
+      "loss": 0.0094,
+      "step": 18000
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.8264910921766073,
+      "eval_f1_macro": 0.7727667291395837,
+      "eval_f1_micro": 0.8264910921766073,
+      "eval_f1_weighted": 0.8258171895625699,
+      "eval_loss": 1.5774097442626953,
+      "eval_macro_fpr": 0.015341103668483914,
+      "eval_macro_sensitivity": 0.773854813454954,
+      "eval_macro_specificity": 0.9869529159693116,
+      "eval_precision": 0.826891768040439,
+      "eval_precision_macro": 0.7788022729128791,
+      "eval_recall": 0.8264910921766073,
+      "eval_recall_macro": 0.773854813454954,
+      "eval_runtime": 33.0216,
+      "eval_samples_per_second": 39.096,
+      "eval_steps_per_second": 4.906,
+      "eval_weighted_fpr": 0.014773776546629732,
+      "eval_weighted_sensitivity": 0.8264910921766073,
+      "eval_weighted_specificity": 0.9778026473630672,
+      "step": 18004
+    },
+    {
+      "epoch": 28.77,
+      "learning_rate": 2.047693105235874e-06,
+      "loss": 0.0063,
+      "step": 18500
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.8303640588690937,
+      "eval_f1_macro": 0.7758691241332945,
+      "eval_f1_micro": 0.8303640588690937,
+      "eval_f1_weighted": 0.8296320064519734,
+      "eval_loss": 1.5894256830215454,
+      "eval_macro_fpr": 0.01497399644790724,
+      "eval_macro_sensitivity": 0.7763923480076292,
+      "eval_macro_specificity": 0.9872175028470982,
+      "eval_precision": 0.8306423335269149,
+      "eval_precision_macro": 0.7825319843012052,
+      "eval_recall": 0.8303640588690937,
+      "eval_recall_macro": 0.7763923480076292,
+      "eval_runtime": 33.6377,
+      "eval_samples_per_second": 38.38,
+      "eval_steps_per_second": 4.816,
+      "eval_weighted_fpr": 0.014382347146516056,
+      "eval_weighted_sensitivity": 0.8303640588690937,
+      "eval_weighted_specificity": 0.9778984838373787,
+      "step": 18647
+    },
+    {
+      "epoch": 29.55,
+      "learning_rate": 7.516848107827891e-07,
+      "loss": 0.0126,
+      "step": 19000
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.8288148721920992,
+      "eval_f1_macro": 0.7760523651578057,
+      "eval_f1_micro": 0.8288148721920992,
+      "eval_f1_weighted": 0.827854551198293,
+      "eval_loss": 1.5927218198776245,
+      "eval_macro_fpr": 0.015145294133303922,
+      "eval_macro_sensitivity": 0.7756187985215348,
+      "eval_macro_specificity": 0.9870860118446655,
+      "eval_precision": 0.8290933179263601,
+      "eval_precision_macro": 0.7851985889478389,
+      "eval_recall": 0.8288148721920992,
+      "eval_recall_macro": 0.7756187985215348,
+      "eval_runtime": 32.9894,
+      "eval_samples_per_second": 39.134,
+      "eval_steps_per_second": 4.911,
+      "eval_weighted_fpr": 0.014538517202815604,
+      "eval_weighted_sensitivity": 0.8288148721920992,
+      "eval_weighted_specificity": 0.977475305477883,
+      "step": 19290
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 19290,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 4.183458652090368e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-19290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3966a5cf2e74453915e0e279c4bf152ff082b27790a1b18e560374923b97a431
+size 4600