Upload folder using huggingface_hub

training_checkpoints/checkpoint-19290/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: nlpaueb/legal-bert-base-uncased
+---
+
+# 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": "nlpaueb/legal-bert-base-uncased",
+  "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",
+    "key",
+    "query",
+    "value"
+  ],
+  "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 sha256:488870c093dc4ac86d865be8a00f7c1869150b9ee39f8285d8cdcb1bb83f6d87
+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 sha256:0bd7ede76eb91d3796cac9fbcf73e8aa633ff6ad0daeca17469b147912651364
+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": 0.8053775485765992,
+  "best_model_checkpoint": "legal-bert-lora-no-grad/checkpoint-15432",
+  "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": 1.5473,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7172734314484895,
+      "eval_f1_macro": 0.3920432121625908,
+      "eval_f1_micro": 0.7172734314484894,
+      "eval_f1_weighted": 0.6868869808248764,
+      "eval_loss": 0.8484711050987244,
+      "eval_macro_fpr": 0.027836504093424867,
+      "eval_macro_sensitivity": 0.44215864388540455,
+      "eval_macro_specificity": 0.9788744549045134,
+      "eval_precision": 0.6896842532804647,
+      "eval_precision_macro": 0.3892290687521846,
+      "eval_recall": 0.7172734314484895,
+      "eval_recall_macro": 0.44215864388540455,
+      "eval_runtime": 32.4222,
+      "eval_samples_per_second": 39.818,
+      "eval_steps_per_second": 4.997,
+      "eval_weighted_fpr": 0.027383899767424412,
+      "eval_weighted_sensitivity": 0.7172734314484895,
+      "eval_weighted_specificity": 0.9658433921192108,
+      "step": 643
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.740798341109383e-05,
+      "loss": 0.7816,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7544539116963594,
+      "eval_f1_macro": 0.47513531679703136,
+      "eval_f1_micro": 0.7544539116963594,
+      "eval_f1_weighted": 0.7304002619527014,
+      "eval_loss": 0.7113391757011414,
+      "eval_macro_fpr": 0.023051270843305598,
+      "eval_macro_sensitivity": 0.5054156753128263,
+      "eval_macro_specificity": 0.9817050378554314,
+      "eval_precision": 0.7491876907285084,
+      "eval_precision_macro": 0.5281699878111706,
+      "eval_recall": 0.7544539116963594,
+      "eval_recall_macro": 0.5054156753128263,
+      "eval_runtime": 33.6622,
+      "eval_samples_per_second": 38.352,
+      "eval_steps_per_second": 4.813,
+      "eval_weighted_fpr": 0.02271912850283093,
+      "eval_weighted_sensitivity": 0.7544539116963594,
+      "eval_weighted_specificity": 0.9711216561351127,
+      "step": 1286
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.6111975116640746e-05,
+      "loss": 0.6956,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7986057319907048,
+      "eval_f1_macro": 0.5439483491438576,
+      "eval_f1_micro": 0.7986057319907048,
+      "eval_f1_weighted": 0.7833451448204543,
+      "eval_loss": 0.6460158824920654,
+      "eval_macro_fpr": 0.01844352926124183,
+      "eval_macro_sensitivity": 0.5700868724489073,
+      "eval_macro_specificity": 0.9848453217277398,
+      "eval_precision": 0.7793241511142787,
+      "eval_precision_macro": 0.5435553848320287,
+      "eval_recall": 0.7986057319907048,
+      "eval_recall_macro": 0.5700868724489073,
+      "eval_runtime": 33.205,
+      "eval_samples_per_second": 38.88,
+      "eval_steps_per_second": 4.879,
+      "eval_weighted_fpr": 0.01769429699196951,
+      "eval_weighted_sensitivity": 0.7986057319907048,
+      "eval_weighted_specificity": 0.974074093925392,
+      "step": 1929
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.481596682218767e-05,
+      "loss": 0.6117,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.3519958527734576e-05,
+      "loss": 0.4942,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8109992254066615,
+      "eval_f1_macro": 0.641318903734146,
+      "eval_f1_micro": 0.8109992254066615,
+      "eval_f1_weighted": 0.8036671817127167,
+      "eval_loss": 0.6429558992385864,
+      "eval_macro_fpr": 0.016902452669854486,
+      "eval_macro_sensitivity": 0.6670193163886222,
+      "eval_macro_specificity": 0.9858199536379567,
+      "eval_precision": 0.8014184747492699,
+      "eval_precision_macro": 0.6315294283267076,
+      "eval_recall": 0.8109992254066615,
+      "eval_recall_macro": 0.6670193163886222,
+      "eval_runtime": 34.2851,
+      "eval_samples_per_second": 37.655,
+      "eval_steps_per_second": 4.725,
+      "eval_weighted_fpr": 0.016373641121997046,
+      "eval_weighted_sensitivity": 0.8109992254066615,
+      "eval_weighted_specificity": 0.9763000791626885,
+      "step": 2572
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 4.22239502332815e-05,
+      "loss": 0.4088,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8319132455460883,
+      "eval_f1_macro": 0.7458887908906745,
+      "eval_f1_micro": 0.8319132455460883,
+      "eval_f1_weighted": 0.8254435175521364,
+      "eval_loss": 0.7148057222366333,
+      "eval_macro_fpr": 0.015014171873602745,
+      "eval_macro_sensitivity": 0.7444010739541649,
+      "eval_macro_specificity": 0.9871775908314393,
+      "eval_precision": 0.8301095647411415,
+      "eval_precision_macro": 0.795128331887366,
+      "eval_recall": 0.8319132455460883,
+      "eval_recall_macro": 0.7444010739541649,
+      "eval_runtime": 32.6496,
+      "eval_samples_per_second": 39.541,
+      "eval_steps_per_second": 4.962,
+      "eval_weighted_fpr": 0.014226709499770536,
+      "eval_weighted_sensitivity": 0.8319132455460883,
+      "eval_weighted_specificity": 0.9757506169255016,
+      "step": 3215
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 4.092794193882841e-05,
+      "loss": 0.3722,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8319132455460883,
+      "eval_f1_macro": 0.7581556537237687,
+      "eval_f1_micro": 0.8319132455460883,
+      "eval_f1_weighted": 0.8284954274383471,
+      "eval_loss": 0.7203006744384766,
+      "eval_macro_fpr": 0.014862611036154928,
+      "eval_macro_sensitivity": 0.7604143289637364,
+      "eval_macro_specificity": 0.9873237068761225,
+      "eval_precision": 0.8282196199964869,
+      "eval_precision_macro": 0.7594204389852343,
+      "eval_recall": 0.8319132455460883,
+      "eval_recall_macro": 0.7604143289637364,
+      "eval_runtime": 32.5293,
+      "eval_samples_per_second": 39.687,
+      "eval_steps_per_second": 4.98,
+      "eval_weighted_fpr": 0.014226709499770536,
+      "eval_weighted_sensitivity": 0.8319132455460883,
+      "eval_weighted_specificity": 0.9779423575957491,
+      "step": 3858
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 3.963193364437533e-05,
+      "loss": 0.3518,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.833592534992224e-05,
+      "loss": 0.3088,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.748587043102148,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.8202672850983224,
+      "eval_loss": 0.7796419858932495,
+      "eval_macro_fpr": 0.015766934174909337,
+      "eval_macro_sensitivity": 0.7436163865406156,
+      "eval_macro_specificity": 0.986554823310482,
+      "eval_precision": 0.8283195435686048,
+      "eval_precision_macro": 0.7927343403715958,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7436163865406156,
+      "eval_runtime": 33.9886,
+      "eval_samples_per_second": 37.983,
+      "eval_steps_per_second": 4.766,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.9764788175116066,
+      "step": 4501
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 3.7039917055469156e-05,
+      "loss": 0.245,
+      "step": 5000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.7408588571905798,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8134714190372911,
+      "eval_loss": 0.8731526136398315,
+      "eval_macro_fpr": 0.016323302917471562,
+      "eval_macro_sensitivity": 0.7403464639779053,
+      "eval_macro_specificity": 0.98626453049897,
+      "eval_precision": 0.8170725248278505,
+      "eval_precision_macro": 0.7696333486311014,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7403464639779053,
+      "eval_runtime": 32.6647,
+      "eval_samples_per_second": 39.523,
+      "eval_steps_per_second": 4.959,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9752227986929156,
+      "step": 5144
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 3.574390876101607e-05,
+      "loss": 0.2331,
+      "step": 5500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8264910921766073,
+      "eval_f1_macro": 0.753016641591601,
+      "eval_f1_micro": 0.8264910921766073,
+      "eval_f1_weighted": 0.8260538424611459,
+      "eval_loss": 0.871034562587738,
+      "eval_macro_fpr": 0.015223198880351374,
+      "eval_macro_sensitivity": 0.7521384355359189,
+      "eval_macro_specificity": 0.9869379376488985,
+      "eval_precision": 0.8280339150697505,
+      "eval_precision_macro": 0.7595158765535532,
+      "eval_recall": 0.8264910921766073,
+      "eval_recall_macro": 0.7521384355359189,
+      "eval_runtime": 32.6231,
+      "eval_samples_per_second": 39.573,
+      "eval_steps_per_second": 4.966,
+      "eval_weighted_fpr": 0.014773776546629732,
+      "eval_weighted_sensitivity": 0.8264910921766073,
+      "eval_weighted_specificity": 0.9775779725568708,
+      "step": 5787
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 3.4447900466562985e-05,
+      "loss": 0.1878,
+      "step": 6000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.82571649883811,
+      "eval_f1_macro": 0.7588436992559459,
+      "eval_f1_micro": 0.82571649883811,
+      "eval_f1_weighted": 0.8239752092365729,
+      "eval_loss": 0.9866135120391846,
+      "eval_macro_fpr": 0.015306627243977184,
+      "eval_macro_sensitivity": 0.7603889662202937,
+      "eval_macro_specificity": 0.9869690054538824,
+      "eval_precision": 0.8260731585047043,
+      "eval_precision_macro": 0.7672111037553849,
+      "eval_recall": 0.82571649883811,
+      "eval_recall_macro": 0.7603889662202937,
+      "eval_runtime": 33.5564,
+      "eval_samples_per_second": 38.473,
+      "eval_steps_per_second": 4.828,
+      "eval_weighted_fpr": 0.01485246550927454,
+      "eval_weighted_sensitivity": 0.82571649883811,
+      "eval_weighted_specificity": 0.9788185829701274,
+      "step": 6430
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 3.315189217210991e-05,
+      "loss": 0.1934,
+      "step": 6500
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 3.1855883877656815e-05,
+      "loss": 0.1627,
+      "step": 7000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.82571649883811,
+      "eval_f1_macro": 0.767473750579757,
+      "eval_f1_micro": 0.82571649883811,
+      "eval_f1_weighted": 0.8233713451484083,
+      "eval_loss": 1.0529617071151733,
+      "eval_macro_fpr": 0.015351918387195561,
+      "eval_macro_sensitivity": 0.7711152769110098,
+      "eval_macro_specificity": 0.9869581108070966,
+      "eval_precision": 0.8268711216555169,
+      "eval_precision_macro": 0.7706107626580333,
+      "eval_recall": 0.82571649883811,
+      "eval_recall_macro": 0.7711152769110098,
+      "eval_runtime": 32.7851,
+      "eval_samples_per_second": 39.378,
+      "eval_steps_per_second": 4.941,
+      "eval_weighted_fpr": 0.01485246550927454,
+      "eval_weighted_sensitivity": 0.82571649883811,
+      "eval_weighted_specificity": 0.9786551632683399,
+      "step": 7073
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 3.0559875583203736e-05,
+      "loss": 0.1301,
+      "step": 7500
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8264910921766073,
+      "eval_f1_macro": 0.7575609282906195,
+      "eval_f1_micro": 0.8264910921766073,
+      "eval_f1_weighted": 0.8227831044737154,
+      "eval_loss": 1.1041574478149414,
+      "eval_macro_fpr": 0.015507747324292978,
+      "eval_macro_sensitivity": 0.7586841377838723,
+      "eval_macro_specificity": 0.986855053135477,
+      "eval_precision": 0.8246142974152224,
+      "eval_precision_macro": 0.7633072608154402,
+      "eval_recall": 0.8264910921766073,
+      "eval_recall_macro": 0.7586841377838723,
+      "eval_runtime": 33.2755,
+      "eval_samples_per_second": 38.797,
+      "eval_steps_per_second": 4.868,
+      "eval_weighted_fpr": 0.014773776546629732,
+      "eval_weighted_sensitivity": 0.8264910921766073,
+      "eval_weighted_specificity": 0.9763347048555474,
+      "step": 7716
+    },
+    {
+      "epoch": 12.44,
+      "learning_rate": 2.926386728875065e-05,
+      "loss": 0.1291,
+      "step": 8000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8233927188226181,
+      "eval_f1_macro": 0.7580847580681433,
+      "eval_f1_micro": 0.8233927188226181,
+      "eval_f1_weighted": 0.8211060746900526,
+      "eval_loss": 1.1460882425308228,
+      "eval_macro_fpr": 0.015717446624001503,
+      "eval_macro_sensitivity": 0.7612688033602836,
+      "eval_macro_specificity": 0.9866762703086498,
+      "eval_precision": 0.8215196709960565,
+      "eval_precision_macro": 0.7582432160976473,
+      "eval_recall": 0.8233927188226181,
+      "eval_recall_macro": 0.7612688033602836,
+      "eval_runtime": 32.7655,
+      "eval_samples_per_second": 39.401,
+      "eval_steps_per_second": 4.944,
+      "eval_weighted_fpr": 0.015089344804765056,
+      "eval_weighted_sensitivity": 0.8233927188226181,
+      "eval_weighted_specificity": 0.9767513358071301,
+      "step": 8359
+    },
+    {
+      "epoch": 13.22,
+      "learning_rate": 2.7967858994297562e-05,
+      "loss": 0.1213,
+      "step": 8500
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 2.667185069984448e-05,
+      "loss": 0.11,
+      "step": 9000
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8226181254841208,
+      "eval_f1_macro": 0.7627437208061313,
+      "eval_f1_micro": 0.8226181254841208,
+      "eval_f1_weighted": 0.819453013970647,
+      "eval_loss": 1.1837199926376343,
+      "eval_macro_fpr": 0.01587279795090152,
+      "eval_macro_sensitivity": 0.7575723645459792,
+      "eval_macro_specificity": 0.98654524509664,
+      "eval_precision": 0.8182318569400476,
+      "eval_precision_macro": 0.7716010744976882,
+      "eval_recall": 0.8226181254841208,
+      "eval_recall_macro": 0.7575723645459792,
+      "eval_runtime": 32.1143,
+      "eval_samples_per_second": 40.2,
+      "eval_steps_per_second": 5.044,
+      "eval_weighted_fpr": 0.01516857653838511,
+      "eval_weighted_sensitivity": 0.8226181254841208,
+      "eval_weighted_specificity": 0.9755605509654802,
+      "step": 9002
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 2.53758424053914e-05,
+      "loss": 0.0863,
+      "step": 9500
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.7497899545528302,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.818300724101517,
+      "eval_loss": 1.2020219564437866,
+      "eval_macro_fpr": 0.01596050778819386,
+      "eval_macro_sensitivity": 0.7457545376125337,
+      "eval_macro_specificity": 0.9864813469122803,
+      "eval_precision": 0.8185478073118013,
+      "eval_precision_macro": 0.7615551574586096,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7457545376125337,
+      "eval_runtime": 32.9172,
+      "eval_samples_per_second": 39.22,
+      "eval_steps_per_second": 4.921,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.9753766715385808,
+      "step": 9645
+    },
+    {
+      "epoch": 15.55,
+      "learning_rate": 2.4079834110938313e-05,
+      "loss": 0.0735,
+      "step": 10000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.7516626482517895,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8167711468473488,
+      "eval_loss": 1.2490901947021484,
+      "eval_macro_fpr": 0.01615903013896019,
+      "eval_macro_sensitivity": 0.7463866263442519,
+      "eval_macro_specificity": 0.9862838939338255,
+      "eval_precision": 0.816010692122711,
+      "eval_precision_macro": 0.7620383054800749,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7463866263442519,
+      "eval_runtime": 33.245,
+      "eval_samples_per_second": 38.833,
+      "eval_steps_per_second": 4.873,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9755132502157504,
+      "step": 10288
+    },
+    {
+      "epoch": 16.33,
+      "learning_rate": 2.2783825816485228e-05,
+      "loss": 0.0802,
+      "step": 10500
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.8164213787761425,
+      "eval_f1_macro": 0.7483467346361333,
+      "eval_f1_micro": 0.8164213787761425,
+      "eval_f1_weighted": 0.8152034106224548,
+      "eval_loss": 1.3287584781646729,
+      "eval_macro_fpr": 0.016411109243053838,
+      "eval_macro_sensitivity": 0.7530689671982778,
+      "eval_macro_specificity": 0.986197275429763,
+      "eval_precision": 0.8164986233001753,
+      "eval_precision_macro": 0.7471296868733558,
+      "eval_recall": 0.8164213787761425,
+      "eval_recall_macro": 0.7530689671982778,
+      "eval_runtime": 32.4097,
+      "eval_samples_per_second": 39.834,
+      "eval_steps_per_second": 4.999,
+      "eval_weighted_fpr": 0.01580737677582872,
+      "eval_weighted_sensitivity": 0.8164213787761425,
+      "eval_weighted_specificity": 0.9765377526703035,
+      "step": 10931
+    },
+    {
+      "epoch": 17.11,
+      "learning_rate": 2.1487817522032143e-05,
+      "loss": 0.0517,
+      "step": 11000
+    },
+    {
+      "epoch": 17.88,
+      "learning_rate": 2.0191809227579057e-05,
+      "loss": 0.0525,
+      "step": 11500
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8133230054221534,
+      "eval_f1_macro": 0.7486434952959435,
+      "eval_f1_micro": 0.8133230054221534,
+      "eval_f1_weighted": 0.8105673102840433,
+      "eval_loss": 1.3620411157608032,
+      "eval_macro_fpr": 0.016771971366343907,
+      "eval_macro_sensitivity": 0.747756174463169,
+      "eval_macro_specificity": 0.9859165137366713,
+      "eval_precision": 0.8127181738070712,
+      "eval_precision_macro": 0.7556869343254475,
+      "eval_recall": 0.8133230054221534,
+      "eval_recall_macro": 0.747756174463169,
+      "eval_runtime": 33.8455,
+      "eval_samples_per_second": 38.144,
+      "eval_steps_per_second": 4.786,
+      "eval_weighted_fpr": 0.016130111772973698,
+      "eval_weighted_sensitivity": 0.8133230054221534,
+      "eval_weighted_specificity": 0.9754247006279183,
+      "step": 11574
+    },
+    {
+      "epoch": 18.66,
+      "learning_rate": 1.8895800933125972e-05,
+      "loss": 0.0474,
+      "step": 12000
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.80243850868883,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8186882142398059,
+      "eval_loss": 1.3783087730407715,
+      "eval_macro_fpr": 0.01616653707794279,
+      "eval_macro_sensitivity": 0.7971845339149931,
+      "eval_macro_specificity": 0.9862841415250829,
+      "eval_precision": 0.8219853895924313,
+      "eval_precision_macro": 0.8153974354587618,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7971845339149931,
+      "eval_runtime": 34.0415,
+      "eval_samples_per_second": 37.924,
+      "eval_steps_per_second": 4.759,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9755169640846107,
+      "step": 12217
+    },
+    {
+      "epoch": 19.44,
+      "learning_rate": 1.7599792638672887e-05,
+      "loss": 0.0315,
+      "step": 12500
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8226181254841208,
+      "eval_f1_macro": 0.790748766871484,
+      "eval_f1_micro": 0.8226181254841208,
+      "eval_f1_weighted": 0.8231232301620584,
+      "eval_loss": 1.400423288345337,
+      "eval_macro_fpr": 0.015694178732213588,
+      "eval_macro_sensitivity": 0.7910027660234611,
+      "eval_macro_specificity": 0.986694893115232,
+      "eval_precision": 0.8265938735422171,
+      "eval_precision_macro": 0.8011102381814037,
+      "eval_recall": 0.8226181254841208,
+      "eval_recall_macro": 0.7910027660234611,
+      "eval_runtime": 33.3314,
+      "eval_samples_per_second": 38.732,
+      "eval_steps_per_second": 4.86,
+      "eval_weighted_fpr": 0.01516857653838511,
+      "eval_weighted_sensitivity": 0.8226181254841208,
+      "eval_weighted_specificity": 0.9778052712443601,
+      "step": 12860
+    },
+    {
+      "epoch": 20.22,
+      "learning_rate": 1.6303784344219805e-05,
+      "loss": 0.0379,
+      "step": 13000
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 1.500777604976672e-05,
+      "loss": 0.0325,
+      "step": 13500
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.7920531234982356,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8182432240494799,
+      "eval_loss": 1.4682910442352295,
+      "eval_macro_fpr": 0.016122147142737502,
+      "eval_macro_sensitivity": 0.7876294399760013,
+      "eval_macro_specificity": 0.9863487423677417,
+      "eval_precision": 0.8197947092422727,
+      "eval_precision_macro": 0.8030038288855238,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7876294399760013,
+      "eval_runtime": 34.2442,
+      "eval_samples_per_second": 37.7,
+      "eval_steps_per_second": 4.731,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9764859767244947,
+      "step": 13503
+    },
+    {
+      "epoch": 21.77,
+      "learning_rate": 1.3711767755313634e-05,
+      "loss": 0.0192,
+      "step": 14000
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.8249419054996127,
+      "eval_f1_macro": 0.7504682467692924,
+      "eval_f1_micro": 0.8249419054996127,
+      "eval_f1_weighted": 0.8224843150628982,
+      "eval_loss": 1.4677306413650513,
+      "eval_macro_fpr": 0.015516813070862829,
+      "eval_macro_sensitivity": 0.7482417751600471,
+      "eval_macro_specificity": 0.9867827508352239,
+      "eval_precision": 0.822350100430648,
+      "eval_precision_macro": 0.7598136028014526,
+      "eval_recall": 0.8249419054996127,
+      "eval_recall_macro": 0.7482417751600471,
+      "eval_runtime": 33.3005,
+      "eval_samples_per_second": 38.768,
+      "eval_steps_per_second": 4.865,
+      "eval_weighted_fpr": 0.014931289640591967,
+      "eval_weighted_sensitivity": 0.8249419054996127,
+      "eval_weighted_specificity": 0.9767993570287478,
+      "step": 14146
+    },
+    {
+      "epoch": 22.55,
+      "learning_rate": 1.241575946086055e-05,
+      "loss": 0.0235,
+      "step": 14500
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.8210689388071263,
+      "eval_f1_macro": 0.7982424827677612,
+      "eval_f1_micro": 0.8210689388071263,
+      "eval_f1_weighted": 0.8200360215658509,
+      "eval_loss": 1.461044192314148,
+      "eval_macro_fpr": 0.015961243701792225,
+      "eval_macro_sensitivity": 0.7941468508731113,
+      "eval_macro_specificity": 0.9865072289274195,
+      "eval_precision": 0.8221421544465105,
+      "eval_precision_macro": 0.8090167733884126,
+      "eval_recall": 0.8210689388071263,
+      "eval_recall_macro": 0.7941468508731113,
+      "eval_runtime": 33.2007,
+      "eval_samples_per_second": 38.885,
+      "eval_steps_per_second": 4.879,
+      "eval_weighted_fpr": 0.015327450069670227,
+      "eval_weighted_sensitivity": 0.8210689388071263,
+      "eval_weighted_specificity": 0.9765394951041704,
+      "step": 14789
+    },
+    {
+      "epoch": 23.33,
+      "learning_rate": 1.1119751166407467e-05,
+      "loss": 0.0142,
+      "step": 15000
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.8272656855151046,
+      "eval_f1_macro": 0.8053775485765992,
+      "eval_f1_micro": 0.8272656855151046,
+      "eval_f1_weighted": 0.8260073301759255,
+      "eval_loss": 1.4787285327911377,
+      "eval_macro_fpr": 0.015285581788252187,
+      "eval_macro_sensitivity": 0.7976771156226762,
+      "eval_macro_specificity": 0.98697730466137,
+      "eval_precision": 0.8269564036548859,
+      "eval_precision_macro": 0.8178610618244221,
+      "eval_recall": 0.8272656855151046,
+      "eval_recall_macro": 0.7976771156226762,
+      "eval_runtime": 36.1973,
+      "eval_samples_per_second": 35.666,
+      "eval_steps_per_second": 4.475,
+      "eval_weighted_fpr": 0.014695222405271829,
+      "eval_weighted_sensitivity": 0.8272656855151046,
+      "eval_weighted_specificity": 0.9773938844054487,
+      "step": 15432
+    },
+    {
+      "epoch": 24.11,
+      "learning_rate": 9.82374287195438e-06,
+      "loss": 0.0264,
+      "step": 15500
+    },
+    {
+      "epoch": 24.88,
+      "learning_rate": 8.527734577501296e-06,
+      "loss": 0.0172,
+      "step": 16000
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.8210689388071263,
+      "eval_f1_macro": 0.7736814612710297,
+      "eval_f1_micro": 0.8210689388071263,
+      "eval_f1_weighted": 0.8212069486680839,
+      "eval_loss": 1.53744375705719,
+      "eval_macro_fpr": 0.015881727761544794,
+      "eval_macro_sensitivity": 0.7710820164359298,
+      "eval_macro_specificity": 0.9865203329909208,
+      "eval_precision": 0.8230667484503933,
+      "eval_precision_macro": 0.7829593244195863,
+      "eval_recall": 0.8210689388071263,
+      "eval_recall_macro": 0.7710820164359298,
+      "eval_runtime": 33.4641,
+      "eval_samples_per_second": 38.579,
+      "eval_steps_per_second": 4.841,
+      "eval_weighted_fpr": 0.015327450069670227,
+      "eval_weighted_sensitivity": 0.8210689388071263,
+      "eval_weighted_specificity": 0.9767360560566842,
+      "step": 16075
+    },
+    {
+      "epoch": 25.66,
+      "learning_rate": 7.2317262830482126e-06,
+      "loss": 0.0097,
+      "step": 16500
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.8241673121611154,
+      "eval_f1_macro": 0.7953698534140774,
+      "eval_f1_micro": 0.8241673121611154,
+      "eval_f1_weighted": 0.8240229840561915,
+      "eval_loss": 1.5152949094772339,
+      "eval_macro_fpr": 0.015579870246960002,
+      "eval_macro_sensitivity": 0.7894178526148151,
+      "eval_macro_specificity": 0.9867556899393406,
+      "eval_precision": 0.8261915344820007,
+      "eval_precision_macro": 0.8105289229125964,
+      "eval_recall": 0.8241673121611154,
+      "eval_recall_macro": 0.7894178526148151,
+      "eval_runtime": 33.4276,
+      "eval_samples_per_second": 38.621,
+      "eval_steps_per_second": 4.846,
+      "eval_weighted_fpr": 0.015010249289162203,
+      "eval_weighted_sensitivity": 0.8241673121611154,
+      "eval_weighted_specificity": 0.9771680369289966,
+      "step": 16718
+    },
+    {
+      "epoch": 26.44,
+      "learning_rate": 5.935717988595127e-06,
+      "loss": 0.0109,
+      "step": 17000
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.7832357753675944,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.8213898811082008,
+      "eval_loss": 1.5565301179885864,
+      "eval_macro_fpr": 0.015839607724162985,
+      "eval_macro_sensitivity": 0.7848108295360633,
+      "eval_macro_specificity": 0.986592677250565,
+      "eval_precision": 0.8237176848869554,
+      "eval_precision_macro": 0.7875966471718512,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7848108295360633,
+      "eval_runtime": 33.2405,
+      "eval_samples_per_second": 38.838,
+      "eval_steps_per_second": 4.874,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.97704662661285,
+      "step": 17361
+    },
+    {
+      "epoch": 27.22,
+      "learning_rate": 4.639709694142043e-06,
+      "loss": 0.0064,
+      "step": 17500
+    },
+    {
+      "epoch": 27.99,
+      "learning_rate": 3.343701399688958e-06,
+      "loss": 0.0076,
+      "step": 18000
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.8226181254841208,
+      "eval_f1_macro": 0.783648952231859,
+      "eval_f1_micro": 0.8226181254841208,
+      "eval_f1_weighted": 0.8228638589414802,
+      "eval_loss": 1.557422161102295,
+      "eval_macro_fpr": 0.01573560188566711,
+      "eval_macro_sensitivity": 0.7843363412562832,
+      "eval_macro_specificity": 0.9866506596601482,
+      "eval_precision": 0.8246986736711477,
+      "eval_precision_macro": 0.7881629656731407,
+      "eval_recall": 0.8226181254841208,
+      "eval_recall_macro": 0.7843363412562832,
+      "eval_runtime": 33.6256,
+      "eval_samples_per_second": 38.393,
+      "eval_steps_per_second": 4.818,
+      "eval_weighted_fpr": 0.01516857653838511,
+      "eval_weighted_sensitivity": 0.8226181254841208,
+      "eval_weighted_specificity": 0.9771417694181015,
+      "step": 18004
+    },
+    {
+      "epoch": 28.77,
+      "learning_rate": 2.047693105235874e-06,
+      "loss": 0.006,
+      "step": 18500
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.8233927188226181,
+      "eval_f1_macro": 0.7788244439295663,
+      "eval_f1_micro": 0.8233927188226181,
+      "eval_f1_weighted": 0.8224098675510743,
+      "eval_loss": 1.5720834732055664,
+      "eval_macro_fpr": 0.015682018831512608,
+      "eval_macro_sensitivity": 0.7770926675896462,
+      "eval_macro_specificity": 0.9866835093529052,
+      "eval_precision": 0.82352724668375,
+      "eval_precision_macro": 0.786821807369651,
+      "eval_recall": 0.8233927188226181,
+      "eval_recall_macro": 0.7770926675896462,
+      "eval_runtime": 33.8208,
+      "eval_samples_per_second": 38.172,
+      "eval_steps_per_second": 4.79,
+      "eval_weighted_fpr": 0.015089344804765056,
+      "eval_weighted_sensitivity": 0.8233927188226181,
+      "eval_weighted_specificity": 0.9768599214709597,
+      "step": 18647
+    },
+    {
+      "epoch": 29.55,
+      "learning_rate": 7.516848107827891e-07,
+      "loss": 0.0035,
+      "step": 19000
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.8233927188226181,
+      "eval_f1_macro": 0.7823754242024741,
+      "eval_f1_micro": 0.8233927188226181,
+      "eval_f1_weighted": 0.822475952696802,
+      "eval_loss": 1.580277442932129,
+      "eval_macro_fpr": 0.015685112144519994,
+      "eval_macro_sensitivity": 0.7773850628105089,
+      "eval_macro_specificity": 0.9866711003077586,
+      "eval_precision": 0.8234378528901808,
+      "eval_precision_macro": 0.7941300591525826,
+      "eval_recall": 0.8233927188226181,
+      "eval_recall_macro": 0.7773850628105089,
+      "eval_runtime": 33.2164,
+      "eval_samples_per_second": 38.866,
+      "eval_steps_per_second": 4.877,
+      "eval_weighted_fpr": 0.015089344804765056,
+      "eval_weighted_sensitivity": 0.8233927188226181,
+      "eval_weighted_specificity": 0.97667378579376,
+      "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:bdaaee2ea8c5545699d181a8364cb087d92c47cb0d5f67dcc808085b20d2a66a
+size 4600