Upload folder using huggingface_hub

all_runs/checkpoint-2089/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: facebook/bart-large
+---
+
+# 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

all_runs/checkpoint-2089/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/bart-large",
+  "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": [
+    "fc1",
+    "q_proj",
+    "dense",
+    "k_proj",
+    "out_proj",
+    "fc2",
+    "v_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

all_runs/checkpoint-2089/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b45ed08530e95a6ea210900aa8db955ed97da03847794c0a1ec67d87595690d
+size 34854640

all_runs/checkpoint-2089/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088c81a9af9a4d7a7b07c2232ebf98e8aab43779d49eea806953755adef240bb
+size 69927198

all_runs/checkpoint-2089/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611deed44e5294d9bee72738cc1811c68f9011f0e631a14629c986c626a44127
+size 14244

all_runs/checkpoint-2089/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d312c85e7710a02853d89e1740c738c65d9cbdf79808c54c9a567b89b1df7d
+size 1064

all_runs/checkpoint-2089/special_tokens_map.json

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

all_runs/checkpoint-2089/tokenizer_config.json

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

all_runs/checkpoint-2089/trainer_state.json

@@ -0,0 +1,329 @@
+{
+  "best_metric": 0.7393184269658342,
+  "best_model_checkpoint": "bart-base-lora/checkpoint-1125",
+  "epoch": 12.995334370139968,
+  "eval_steps": 500,
+  "global_step": 2089,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.715724244771495,
+      "eval_f1_macro": 0.3957532686340496,
+      "eval_f1_micro": 0.715724244771495,
+      "eval_f1_weighted": 0.6834645556416842,
+      "eval_loss": 0.9525313973426819,
+      "eval_macro_fpr": 0.028501626692807605,
+      "eval_macro_sensitivity": 0.4415906678049911,
+      "eval_macro_specificity": 0.9786637894661117,
+      "eval_precision": 0.6787596592263883,
+      "eval_precision_macro": 0.38751339695744513,
+      "eval_recall": 0.715724244771495,
+      "eval_recall_macro": 0.4415906678049911,
+      "eval_runtime": 120.9594,
+      "eval_samples_per_second": 10.673,
+      "eval_steps_per_second": 1.339,
+      "eval_weighted_fpr": 0.027587762158911525,
+      "eval_weighted_sensitivity": 0.715724244771495,
+      "eval_weighted_specificity": 0.9642325972201805,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7412858249419055,
+      "eval_f1_macro": 0.43370046411892155,
+      "eval_f1_micro": 0.7412858249419055,
+      "eval_f1_weighted": 0.7231329193382661,
+      "eval_loss": 0.7733433842658997,
+      "eval_macro_fpr": 0.025167370687133015,
+      "eval_macro_sensitivity": 0.4686708989603177,
+      "eval_macro_specificity": 0.9805374797463638,
+      "eval_precision": 0.729625861926521,
+      "eval_precision_macro": 0.4491323101141271,
+      "eval_recall": 0.7412858249419055,
+      "eval_recall_macro": 0.4686708989603177,
+      "eval_runtime": 119.8649,
+      "eval_samples_per_second": 10.77,
+      "eval_steps_per_second": 1.352,
+      "eval_weighted_fpr": 0.024322749781532187,
+      "eval_weighted_sensitivity": 0.7412858249419055,
+      "eval_weighted_specificity": 0.9667763712535515,
+      "step": 321
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7738187451587917,
+      "eval_f1_macro": 0.5270593942960143,
+      "eval_f1_micro": 0.7738187451587917,
+      "eval_f1_weighted": 0.7610767338978833,
+      "eval_loss": 0.7104586958885193,
+      "eval_macro_fpr": 0.021211805484311928,
+      "eval_macro_sensitivity": 0.5407847836684627,
+      "eval_macro_specificity": 0.9830897092527341,
+      "eval_precision": 0.7630858215778352,
+      "eval_precision_macro": 0.5565386466479504,
+      "eval_recall": 0.7738187451587917,
+      "eval_recall_macro": 0.5407847836684627,
+      "eval_runtime": 119.5419,
+      "eval_samples_per_second": 10.8,
+      "eval_steps_per_second": 1.355,
+      "eval_weighted_fpr": 0.020451043563524302,
+      "eval_weighted_sensitivity": 0.7738187451587917,
+      "eval_weighted_specificity": 0.9725268936322198,
+      "step": 482
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.08,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7575522850503486,
+      "eval_f1_macro": 0.5497163954183316,
+      "eval_f1_micro": 0.7575522850503486,
+      "eval_f1_weighted": 0.7437674055775699,
+      "eval_loss": 0.7538753151893616,
+      "eval_macro_fpr": 0.023393901824967867,
+      "eval_macro_sensitivity": 0.5613408412198008,
+      "eval_macro_specificity": 0.9817091819688993,
+      "eval_precision": 0.7583906478192325,
+      "eval_precision_macro": 0.5791225123984725,
+      "eval_recall": 0.7575522850503486,
+      "eval_recall_macro": 0.5613408412198008,
+      "eval_runtime": 120.3095,
+      "eval_samples_per_second": 10.731,
+      "eval_steps_per_second": 1.347,
+      "eval_weighted_fpr": 0.022349161013923598,
+      "eval_weighted_sensitivity": 0.7575522850503486,
+      "eval_weighted_specificity": 0.9680854444831427,
+      "step": 643
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7831138652207591,
+      "eval_f1_macro": 0.6353946839596228,
+      "eval_f1_micro": 0.783113865220759,
+      "eval_f1_weighted": 0.770250750407997,
+      "eval_loss": 0.6978110074996948,
+      "eval_macro_fpr": 0.020328728105215688,
+      "eval_macro_sensitivity": 0.6491872351233146,
+      "eval_macro_specificity": 0.983610303127039,
+      "eval_precision": 0.790031827496624,
+      "eval_precision_macro": 0.7409525878258343,
+      "eval_recall": 0.7831138652207591,
+      "eval_recall_macro": 0.6491872351233146,
+      "eval_runtime": 119.9411,
+      "eval_samples_per_second": 10.764,
+      "eval_steps_per_second": 1.351,
+      "eval_weighted_fpr": 0.019398642095053348,
+      "eval_weighted_sensitivity": 0.7831138652207591,
+      "eval_weighted_specificity": 0.9710406816848265,
+      "step": 803
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8156467854376452,
+      "eval_f1_macro": 0.686011065139391,
+      "eval_f1_micro": 0.8156467854376452,
+      "eval_f1_weighted": 0.8087620976325791,
+      "eval_loss": 0.5920090675354004,
+      "eval_macro_fpr": 0.016634568189926056,
+      "eval_macro_sensitivity": 0.6889168814632094,
+      "eval_macro_specificity": 0.9860196319752603,
+      "eval_precision": 0.8053079350996695,
+      "eval_precision_macro": 0.7051361586363433,
+      "eval_recall": 0.8156467854376452,
+      "eval_recall_macro": 0.6889168814632094,
+      "eval_runtime": 121.4244,
+      "eval_samples_per_second": 10.632,
+      "eval_steps_per_second": 1.334,
+      "eval_weighted_fpr": 0.01588785046728972,
+      "eval_weighted_sensitivity": 0.8156467854376452,
+      "eval_weighted_specificity": 0.974647694191258,
+      "step": 964
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.5581,
+      "step": 1000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.7393184269658342,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8146848849127107,
+      "eval_loss": 0.6230757236480713,
+      "eval_macro_fpr": 0.016206558639896132,
+      "eval_macro_sensitivity": 0.7424574536250088,
+      "eval_macro_specificity": 0.9863587851767341,
+      "eval_precision": 0.8177894369587694,
+      "eval_precision_macro": 0.7626654223433325,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7424574536250088,
+      "eval_runtime": 122.7775,
+      "eval_samples_per_second": 10.515,
+      "eval_steps_per_second": 1.319,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9766366188593788,
+      "step": 1125
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8140975987606507,
+      "eval_f1_macro": 0.7328585966804847,
+      "eval_f1_micro": 0.8140975987606507,
+      "eval_f1_weighted": 0.8088643288992207,
+      "eval_loss": 0.6290707588195801,
+      "eval_macro_fpr": 0.01671628651715199,
+      "eval_macro_sensitivity": 0.730719512015592,
+      "eval_macro_specificity": 0.985990627132147,
+      "eval_precision": 0.8133783130550384,
+      "eval_precision_macro": 0.7636063765511063,
+      "eval_recall": 0.8140975987606507,
+      "eval_recall_macro": 0.730719512015592,
+      "eval_runtime": 122.8754,
+      "eval_samples_per_second": 10.507,
+      "eval_steps_per_second": 1.318,
+      "eval_weighted_fpr": 0.016049217600641968,
+      "eval_weighted_sensitivity": 0.8140975987606507,
+      "eval_weighted_specificity": 0.975761808221554,
+      "step": 1286
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8241673121611154,
+      "eval_f1_macro": 0.7364711129039813,
+      "eval_f1_micro": 0.8241673121611154,
+      "eval_f1_weighted": 0.8190822404938951,
+      "eval_loss": 0.6226187348365784,
+      "eval_macro_fpr": 0.015759087941173786,
+      "eval_macro_sensitivity": 0.7340167949600996,
+      "eval_macro_specificity": 0.9866810242390173,
+      "eval_precision": 0.8212295601295609,
+      "eval_precision_macro": 0.7665878963082912,
+      "eval_recall": 0.8241673121611154,
+      "eval_recall_macro": 0.7340167949600996,
+      "eval_runtime": 119.2726,
+      "eval_samples_per_second": 10.824,
+      "eval_steps_per_second": 1.358,
+      "eval_weighted_fpr": 0.015010249289162203,
+      "eval_weighted_sensitivity": 0.8241673121611154,
+      "eval_weighted_specificity": 0.9760480514241424,
+      "step": 1446
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.3924,
+      "step": 1500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8109992254066615,
+      "eval_f1_macro": 0.7240137823928982,
+      "eval_f1_micro": 0.8109992254066615,
+      "eval_f1_weighted": 0.8047604071311991,
+      "eval_loss": 0.672822892665863,
+      "eval_macro_fpr": 0.017004063571327103,
+      "eval_macro_sensitivity": 0.7288750805513627,
+      "eval_macro_specificity": 0.9858130697255809,
+      "eval_precision": 0.8123042127541057,
+      "eval_precision_macro": 0.7417780746962291,
+      "eval_recall": 0.8109992254066615,
+      "eval_recall_macro": 0.7288750805513627,
+      "eval_runtime": 119.3649,
+      "eval_samples_per_second": 10.816,
+      "eval_steps_per_second": 1.357,
+      "eval_weighted_fpr": 0.016373641121997046,
+      "eval_weighted_sensitivity": 0.8109992254066615,
+      "eval_weighted_specificity": 0.976196820477052,
+      "step": 1607
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8094500387296669,
+      "eval_f1_macro": 0.7262574438118878,
+      "eval_f1_micro": 0.8094500387296669,
+      "eval_f1_weighted": 0.8026446222230169,
+      "eval_loss": 0.6805150508880615,
+      "eval_macro_fpr": 0.017269448415116812,
+      "eval_macro_sensitivity": 0.7303446738424816,
+      "eval_macro_specificity": 0.9856433903766489,
+      "eval_precision": 0.8123272064418959,
+      "eval_precision_macro": 0.7389776120628855,
+      "eval_recall": 0.8094500387296669,
+      "eval_recall_macro": 0.7303446738424816,
+      "eval_runtime": 119.049,
+      "eval_samples_per_second": 10.844,
+      "eval_steps_per_second": 1.361,
+      "eval_weighted_fpr": 0.016536703414896478,
+      "eval_weighted_sensitivity": 0.8094500387296669,
+      "eval_weighted_specificity": 0.9752008169200658,
+      "step": 1768
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8133230054221534,
+      "eval_f1_macro": 0.7283700928598721,
+      "eval_f1_micro": 0.8133230054221534,
+      "eval_f1_weighted": 0.8089952243674349,
+      "eval_loss": 0.670982301235199,
+      "eval_macro_fpr": 0.016803062086639158,
+      "eval_macro_sensitivity": 0.7306161057668827,
+      "eval_macro_specificity": 0.9859491188467968,
+      "eval_precision": 0.813705327621,
+      "eval_precision_macro": 0.7396207219727483,
+      "eval_recall": 0.8133230054221534,
+      "eval_recall_macro": 0.7306161057668827,
+      "eval_runtime": 179.3033,
+      "eval_samples_per_second": 7.2,
+      "eval_steps_per_second": 0.903,
+      "eval_weighted_fpr": 0.016130111772973698,
+      "eval_weighted_sensitivity": 0.8133230054221534,
+      "eval_weighted_specificity": 0.9759137772797981,
+      "step": 1929
+    },
+    {
+      "epoch": 12.44,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.2929,
+      "step": 2000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.73684785586885,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8150888108444543,
+      "eval_loss": 0.6740049719810486,
+      "eval_macro_fpr": 0.01621356652381048,
+      "eval_macro_sensitivity": 0.7360046444502426,
+      "eval_macro_specificity": 0.9863212120014355,
+      "eval_precision": 0.8169592155695241,
+      "eval_precision_macro": 0.7644187374870298,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7360046444502426,
+      "eval_runtime": 119.1613,
+      "eval_samples_per_second": 10.834,
+      "eval_steps_per_second": 1.36,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.9760730212298985,
+      "step": 2089
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2400,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 7.437850857000346e+16,
+  "trial_name": null,
+  "trial_params": null
+}

all_runs/checkpoint-2089/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cfeeb4079e0edbd60cad2df3b73a192a8e64f61f57cc52cfabb80fd9ff6105d
+size 4600