Upload folder using huggingface_hub

training_checkpoints/checkpoint-2400/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-2400/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": [
+    "query",
+    "value",
+    "dense",
+    "key"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

training_checkpoints/checkpoint-2400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0051babe471bc408d3ec4f6a2caa3406f3f6a7f55179fcebe45a25a13d6bcb
+size 104549068

training_checkpoints/checkpoint-2400/added_tokens.json

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

training_checkpoints/checkpoint-2400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61636c3d0c5a89ecb317c2019fcf3bf8f419871a251b3a859efa9b585fcf1764
+size 21646778

training_checkpoints/checkpoint-2400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef0506012dcb5a11818b2f315b0aed7e4e1fe703422f5033754a0ed2e854b64
+size 14244

training_checkpoints/checkpoint-2400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e148d8aa9ee6fba677da24cd9589db9b2fa7bbfa9dbd694102b5142f294d6b
+size 1064

training_checkpoints/checkpoint-2400/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-2400/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-2400/trainer_state.json

@@ -0,0 +1,373 @@
+{
+  "best_metric": 0.6233079593854421,
+  "best_model_checkpoint": "legal-bert-lora/checkpoint-2400",
+  "epoch": 14.930015552099533,
+  "eval_steps": 500,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6421378776142526,
+      "eval_f1_macro": 0.31136748304755507,
+      "eval_f1_micro": 0.6421378776142526,
+      "eval_f1_weighted": 0.5878444491981866,
+      "eval_loss": 1.2986136674880981,
+      "eval_macro_fpr": 0.038355184603561555,
+      "eval_macro_sensitivity": 0.3626666520341733,
+      "eval_macro_specificity": 0.973015566130753,
+      "eval_precision": 0.5562686061065911,
+      "eval_precision_macro": 0.28263839276699676,
+      "eval_recall": 0.6421378776142526,
+      "eval_recall_macro": 0.3626666520341733,
+      "eval_runtime": 30.9334,
+      "eval_samples_per_second": 41.735,
+      "eval_steps_per_second": 5.237,
+      "eval_weighted_fpr": 0.0382830626450116,
+      "eval_weighted_sensitivity": 0.6421378776142526,
+      "eval_weighted_specificity": 0.9530956143470434,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7273431448489543,
+      "eval_f1_macro": 0.3888935561593279,
+      "eval_f1_micro": 0.7273431448489543,
+      "eval_f1_weighted": 0.692588019918852,
+      "eval_loss": 0.8961567282676697,
+      "eval_macro_fpr": 0.026458628520528476,
+      "eval_macro_sensitivity": 0.4470621473688688,
+      "eval_macro_specificity": 0.9797244740763676,
+      "eval_precision": 0.6748056644368075,
+      "eval_precision_macro": 0.3629498453077369,
+      "eval_recall": 0.7273431448489543,
+      "eval_recall_macro": 0.4470621473688688,
+      "eval_runtime": 32.9563,
+      "eval_samples_per_second": 39.173,
+      "eval_steps_per_second": 4.916,
+      "eval_weighted_fpr": 0.026077937472218107,
+      "eval_weighted_sensitivity": 0.7273431448489543,
+      "eval_weighted_specificity": 0.96852396629656,
+      "step": 321
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7412858249419055,
+      "eval_f1_macro": 0.40405445997881334,
+      "eval_f1_micro": 0.7412858249419055,
+      "eval_f1_weighted": 0.7108608148557795,
+      "eval_loss": 0.781432032585144,
+      "eval_macro_fpr": 0.024530771232909164,
+      "eval_macro_sensitivity": 0.4561075059687207,
+      "eval_macro_specificity": 0.980770943968583,
+      "eval_precision": 0.710424889718612,
+      "eval_precision_macro": 0.3984726833381553,
+      "eval_recall": 0.7412858249419055,
+      "eval_recall_macro": 0.4561075059687207,
+      "eval_runtime": 39.931,
+      "eval_samples_per_second": 32.331,
+      "eval_steps_per_second": 4.057,
+      "eval_weighted_fpr": 0.024322749781532187,
+      "eval_weighted_sensitivity": 0.7412858249419055,
+      "eval_weighted_specificity": 0.9702783345868383,
+      "step": 482
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.2548,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7381874515879163,
+      "eval_f1_macro": 0.4122148246767375,
+      "eval_f1_micro": 0.7381874515879164,
+      "eval_f1_weighted": 0.7112039681421287,
+      "eval_loss": 0.7648358345031738,
+      "eval_macro_fpr": 0.025400921422273737,
+      "eval_macro_sensitivity": 0.4496029265691551,
+      "eval_macro_specificity": 0.9802926483932133,
+      "eval_precision": 0.7157524333095121,
+      "eval_precision_macro": 0.42727818666817063,
+      "eval_recall": 0.7381874515879163,
+      "eval_recall_macro": 0.4496029265691551,
+      "eval_runtime": 32.8339,
+      "eval_samples_per_second": 39.319,
+      "eval_steps_per_second": 4.934,
+      "eval_weighted_fpr": 0.024707602339181286,
+      "eval_weighted_sensitivity": 0.7381874515879163,
+      "eval_weighted_specificity": 0.9662022743102826,
+      "step": 643
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7451587916343919,
+      "eval_f1_macro": 0.41197057704153306,
+      "eval_f1_micro": 0.745158791634392,
+      "eval_f1_weighted": 0.7132510342008067,
+      "eval_loss": 0.7329303026199341,
+      "eval_macro_fpr": 0.02475342533454581,
+      "eval_macro_sensitivity": 0.4569200029284667,
+      "eval_macro_specificity": 0.9807956690333189,
+      "eval_precision": 0.7105362318393594,
+      "eval_precision_macro": 0.4161968802708754,
+      "eval_recall": 0.7451587916343919,
+      "eval_recall_macro": 0.4569200029284667,
+      "eval_runtime": 32.9353,
+      "eval_samples_per_second": 39.198,
+      "eval_steps_per_second": 4.919,
+      "eval_weighted_fpr": 0.023845763571790968,
+      "eval_weighted_sensitivity": 0.7451587916343919,
+      "eval_weighted_specificity": 0.9667762438653926,
+      "step": 803
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7567776917118513,
+      "eval_f1_macro": 0.4503557410457486,
+      "eval_f1_micro": 0.7567776917118513,
+      "eval_f1_weighted": 0.7423563743688452,
+      "eval_loss": 0.743047297000885,
+      "eval_macro_fpr": 0.022902966086653806,
+      "eval_macro_sensitivity": 0.48677177072496847,
+      "eval_macro_specificity": 0.9818525702731864,
+      "eval_precision": 0.7546602500248394,
+      "eval_precision_macro": 0.46270927804131506,
+      "eval_recall": 0.7567776917118513,
+      "eval_recall_macro": 0.48677177072496847,
+      "eval_runtime": 35.5356,
+      "eval_samples_per_second": 36.33,
+      "eval_steps_per_second": 4.559,
+      "eval_weighted_fpr": 0.022441395082904516,
+      "eval_weighted_sensitivity": 0.7567776917118513,
+      "eval_weighted_specificity": 0.9710108623859445,
+      "step": 964
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.6432,
+      "step": 1000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.772269558481797,
+      "eval_f1_macro": 0.5175006262467735,
+      "eval_f1_micro": 0.772269558481797,
+      "eval_f1_weighted": 0.7578481216972976,
+      "eval_loss": 0.7300274968147278,
+      "eval_macro_fpr": 0.02134328767934931,
+      "eval_macro_sensitivity": 0.5411462581156664,
+      "eval_macro_specificity": 0.98297476620379,
+      "eval_precision": 0.7523775635605143,
+      "eval_precision_macro": 0.5180467722428242,
+      "eval_recall": 0.772269558481797,
+      "eval_recall_macro": 0.5411462581156664,
+      "eval_runtime": 38.2021,
+      "eval_samples_per_second": 33.794,
+      "eval_steps_per_second": 4.241,
+      "eval_weighted_fpr": 0.0206286836935167,
+      "eval_weighted_sensitivity": 0.772269558481797,
+      "eval_weighted_specificity": 0.9723519345750513,
+      "step": 1125
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7699457784663052,
+      "eval_f1_macro": 0.512343990681717,
+      "eval_f1_micro": 0.7699457784663051,
+      "eval_f1_weighted": 0.7555735603556318,
+      "eval_loss": 0.7212091684341431,
+      "eval_macro_fpr": 0.021584067239714805,
+      "eval_macro_sensitivity": 0.5396538304003057,
+      "eval_macro_specificity": 0.9828444142044448,
+      "eval_precision": 0.7514419747862876,
+      "eval_precision_macro": 0.5096106646255758,
+      "eval_recall": 0.7699457784663052,
+      "eval_recall_macro": 0.5396538304003057,
+      "eval_runtime": 32.2114,
+      "eval_samples_per_second": 40.079,
+      "eval_steps_per_second": 5.029,
+      "eval_weighted_fpr": 0.0208963624850489,
+      "eval_weighted_sensitivity": 0.7699457784663052,
+      "eval_weighted_specificity": 0.972720434600368,
+      "step": 1286
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7838884585592564,
+      "eval_f1_macro": 0.5279543664583783,
+      "eval_f1_micro": 0.7838884585592564,
+      "eval_f1_weighted": 0.7689732348128614,
+      "eval_loss": 0.6910194158554077,
+      "eval_macro_fpr": 0.020019128373318984,
+      "eval_macro_sensitivity": 0.5565954789834968,
+      "eval_macro_specificity": 0.9837782640304022,
+      "eval_precision": 0.7634272015982886,
+      "eval_precision_macro": 0.5216991000769746,
+      "eval_recall": 0.7838884585592564,
+      "eval_recall_macro": 0.5565954789834968,
+      "eval_runtime": 32.0206,
+      "eval_samples_per_second": 40.318,
+      "eval_steps_per_second": 5.059,
+      "eval_weighted_fpr": 0.019311967882605384,
+      "eval_weighted_sensitivity": 0.7838884585592564,
+      "eval_weighted_specificity": 0.9727855018967767,
+      "step": 1446
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.4841,
+      "step": 1500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7877614252517429,
+      "eval_f1_macro": 0.5495324917554609,
+      "eval_f1_micro": 0.7877614252517429,
+      "eval_f1_weighted": 0.7776375085558,
+      "eval_loss": 0.7121981382369995,
+      "eval_macro_fpr": 0.019504320709131964,
+      "eval_macro_sensitivity": 0.5776673358851873,
+      "eval_macro_specificity": 0.9841714965132778,
+      "eval_precision": 0.7732104340520375,
+      "eval_precision_macro": 0.5355484846658871,
+      "eval_recall": 0.7877614252517429,
+      "eval_recall_macro": 0.5776673358851873,
+      "eval_runtime": 33.0059,
+      "eval_samples_per_second": 39.114,
+      "eval_steps_per_second": 4.908,
+      "eval_weighted_fpr": 0.01888092613009923,
+      "eval_weighted_sensitivity": 0.7877614252517429,
+      "eval_weighted_specificity": 0.9748110224474253,
+      "step": 1607
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7916343919442292,
+      "eval_f1_macro": 0.5562780051556154,
+      "eval_f1_micro": 0.7916343919442292,
+      "eval_f1_weighted": 0.7804853293305261,
+      "eval_loss": 0.6812628507614136,
+      "eval_macro_fpr": 0.019142781930172804,
+      "eval_macro_sensitivity": 0.5765462767448893,
+      "eval_macro_specificity": 0.9844026085499723,
+      "eval_precision": 0.7781614931218286,
+      "eval_precision_macro": 0.5712026501913576,
+      "eval_recall": 0.7916343919442292,
+      "eval_recall_macro": 0.5765462767448893,
+      "eval_runtime": 32.8409,
+      "eval_samples_per_second": 39.311,
+      "eval_steps_per_second": 4.933,
+      "eval_weighted_fpr": 0.01845372847636688,
+      "eval_weighted_sensitivity": 0.7916343919442292,
+      "eval_weighted_specificity": 0.9744047363053557,
+      "step": 1768
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7978311386522076,
+      "eval_f1_macro": 0.6091855900661244,
+      "eval_f1_micro": 0.7978311386522076,
+      "eval_f1_weighted": 0.792670799718178,
+      "eval_loss": 0.6844632029533386,
+      "eval_macro_fpr": 0.018374590871553166,
+      "eval_macro_sensitivity": 0.6226306971157384,
+      "eval_macro_specificity": 0.9849182887766558,
+      "eval_precision": 0.7921866196991937,
+      "eval_precision_macro": 0.6110720619206644,
+      "eval_recall": 0.7978311386522076,
+      "eval_recall_macro": 0.6226306971157384,
+      "eval_runtime": 35.566,
+      "eval_samples_per_second": 36.299,
+      "eval_steps_per_second": 4.555,
+      "eval_weighted_fpr": 0.017778080512226686,
+      "eval_weighted_sensitivity": 0.7978311386522076,
+      "eval_weighted_specificity": 0.975943192997628,
+      "step": 1929
+    },
+    {
+      "epoch": 12.44,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.3838,
+      "step": 2000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.7986057319907048,
+      "eval_f1_macro": 0.5954068998935002,
+      "eval_f1_micro": 0.7986057319907048,
+      "eval_f1_weighted": 0.7903483756475167,
+      "eval_loss": 0.6928977370262146,
+      "eval_macro_fpr": 0.0184204271351787,
+      "eval_macro_sensitivity": 0.6038340182662734,
+      "eval_macro_specificity": 0.9848585042092353,
+      "eval_precision": 0.7946985083189905,
+      "eval_precision_macro": 0.6346663909366547,
+      "eval_recall": 0.7986057319907048,
+      "eval_recall_macro": 0.6038340182662734,
+      "eval_runtime": 33.0309,
+      "eval_samples_per_second": 39.085,
+      "eval_steps_per_second": 4.905,
+      "eval_weighted_fpr": 0.01769429699196951,
+      "eval_weighted_sensitivity": 0.7986057319907048,
+      "eval_weighted_specificity": 0.9742718311478232,
+      "step": 2089
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.801704105344694,
+      "eval_f1_macro": 0.6173679522576865,
+      "eval_f1_micro": 0.801704105344694,
+      "eval_f1_weighted": 0.7952025212023197,
+      "eval_loss": 0.6928758025169373,
+      "eval_macro_fpr": 0.01800544482613472,
+      "eval_macro_sensitivity": 0.6269909571861924,
+      "eval_macro_specificity": 0.985137611575089,
+      "eval_precision": 0.7959796451639289,
+      "eval_precision_macro": 0.6369499539059621,
+      "eval_recall": 0.801704105344694,
+      "eval_recall_macro": 0.6269909571861924,
+      "eval_runtime": 32.8583,
+      "eval_samples_per_second": 39.29,
+      "eval_steps_per_second": 4.93,
+      "eval_weighted_fpr": 0.0173606401736064,
+      "eval_weighted_sensitivity": 0.801704105344694,
+      "eval_weighted_specificity": 0.9753600682816376,
+      "step": 2250
+    },
+    {
+      "epoch": 14.93,
+      "eval_accuracy": 0.8048024786986832,
+      "eval_f1_macro": 0.6233079593854421,
+      "eval_f1_micro": 0.804802478698683,
+      "eval_f1_weighted": 0.7978122721784159,
+      "eval_loss": 0.6840828061103821,
+      "eval_macro_fpr": 0.017694121611631287,
+      "eval_macro_sensitivity": 0.6315536711716451,
+      "eval_macro_specificity": 0.9853428489438554,
+      "eval_precision": 0.7955229182430892,
+      "eval_precision_macro": 0.6332000311054261,
+      "eval_recall": 0.8048024786986832,
+      "eval_recall_macro": 0.6315536711716451,
+      "eval_runtime": 32.8856,
+      "eval_samples_per_second": 39.257,
+      "eval_steps_per_second": 4.926,
+      "eval_weighted_fpr": 0.017029328287606435,
+      "eval_weighted_sensitivity": 0.8048024786986832,
+      "eval_weighted_specificity": 0.9753402554591518,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2400,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 2.082121538560819e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-2400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e37e1d0aec45f3692bb7a4c436045ab2c0731c0f9a577af785da6a2da60500
+size 4600