add lora_v21_seed_45 (V2.2 H100 canonical run)

lora_v21_seed_45/README.md

@@ -0,0 +1,206 @@
+---
+base_model: microsoft/deberta-v3-base
+library_name: peft
+tags:
+- base_model:adapter:microsoft/deberta-v3-base
+- lora
+- transformers
+---
+
+# 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 0.19.1

lora_v21_seed_45/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "pooler",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value_proj",
+    "query_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora_v21_seed_45/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdfc99586a2f997ce36d0a5492d28585b3a6d1e71829498ff1ff1b385db7a2fb
+size 3555616

lora_v21_seed_45/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

lora_v21_seed_45/class_weights.json

@@ -0,0 +1 @@
+{"class_0": 0.6787749528884888, "class_1": 1.8984063863754272}

lora_v21_seed_45/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

lora_v21_seed_45/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

lora_v21_seed_45/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

lora_v21_seed_45/train_config.json

@@ -0,0 +1,25 @@
+{
+  "base_model": "microsoft/deberta-v3-base",
+  "max_length": 512,
+  "lora_r": 8,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "lora_target_modules": [
+    "query_proj",
+    "value_proj"
+  ],
+  "lora_modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "learning_rate": 0.0002,
+  "weight_decay": 0.01,
+  "num_epochs": 8,
+  "batch_size": 8,
+  "grad_accumulation": 2,
+  "warmup_ratio": 0.06,
+  "fp16": true,
+  "gradient_checkpointing": true,
+  "class_weighted_loss": true,
+  "early_stopping_patience": 2
+}

lora_v21_seed_45/train_history.json

@@ -0,0 +1,428 @@
+[
+  {
+    "loss": 0.7008,
+    "grad_norm": 1.6835390329360962,
+    "learning_rate": 6.206896551724138e-05,
+    "epoch": 0.16666666666666666,
+    "step": 10
+  },
+  {
+    "loss": 0.6976,
+    "grad_norm": 1.1720629930496216,
+    "learning_rate": 0.00013103448275862068,
+    "epoch": 0.3333333333333333,
+    "step": 20
+  },
+  {
+    "loss": 0.6915,
+    "grad_norm": 1.8779666423797607,
+    "learning_rate": 0.0002,
+    "epoch": 0.5,
+    "step": 30
+  },
+  {
+    "loss": 0.681,
+    "grad_norm": 4.258940696716309,
+    "learning_rate": 0.00019556541019955653,
+    "epoch": 0.6666666666666666,
+    "step": 40
+  },
+  {
+    "loss": 0.637,
+    "grad_norm": 1.669708251953125,
+    "learning_rate": 0.00019113082039911309,
+    "epoch": 0.8333333333333334,
+    "step": 50
+  },
+  {
+    "loss": 0.5045,
+    "grad_norm": 2.4921090602874756,
+    "learning_rate": 0.00018669623059866964,
+    "epoch": 1.0,
+    "step": 60
+  },
+  {
+    "eval_loss": 0.38680821657180786,
+    "eval_pr_auc": 0.922113848519589,
+    "eval_runtime": 0.4804,
+    "eval_samples_per_second": 424.66,
+    "eval_steps_per_second": 54.123,
+    "epoch": 1.0,
+    "step": 60
+  },
+  {
+    "loss": 0.3147,
+    "grad_norm": 2.2998976707458496,
+    "learning_rate": 0.00018226164079822616,
+    "epoch": 1.1666666666666667,
+    "step": 70
+  },
+  {
+    "loss": 0.2106,
+    "grad_norm": 0.9478673934936523,
+    "learning_rate": 0.00017782705099778271,
+    "epoch": 1.3333333333333333,
+    "step": 80
+  },
+  {
+    "loss": 0.4153,
+    "grad_norm": 2.211520195007324,
+    "learning_rate": 0.00017339246119733924,
+    "epoch": 1.5,
+    "step": 90
+  },
+  {
+    "loss": 0.1793,
+    "grad_norm": 0.6265550851821899,
+    "learning_rate": 0.00016895787139689582,
+    "epoch": 1.6666666666666665,
+    "step": 100
+  },
+  {
+    "loss": 0.2251,
+    "grad_norm": 0.8771417140960693,
+    "learning_rate": 0.00016452328159645234,
+    "epoch": 1.8333333333333335,
+    "step": 110
+  },
+  {
+    "loss": 0.2688,
+    "grad_norm": 0.5613293647766113,
+    "learning_rate": 0.00016008869179600887,
+    "epoch": 2.0,
+    "step": 120
+  },
+  {
+    "eval_loss": 0.19772757589817047,
+    "eval_pr_auc": 0.9580288514660931,
+    "eval_runtime": 0.4007,
+    "eval_samples_per_second": 509.049,
+    "eval_steps_per_second": 64.879,
+    "epoch": 2.0,
+    "step": 120
+  },
+  {
+    "loss": 0.1171,
+    "grad_norm": 0.4529179036617279,
+    "learning_rate": 0.00015565410199556542,
+    "epoch": 2.1666666666666665,
+    "step": 130
+  },
+  {
+    "loss": 0.2049,
+    "grad_norm": 0.7560976147651672,
+    "learning_rate": 0.00015121951219512197,
+    "epoch": 2.3333333333333335,
+    "step": 140
+  },
+  {
+    "loss": 0.1763,
+    "grad_norm": 3.764814615249634,
+    "learning_rate": 0.0001467849223946785,
+    "epoch": 2.5,
+    "step": 150
+  },
+  {
+    "loss": 0.1502,
+    "grad_norm": 0.3239579498767853,
+    "learning_rate": 0.00014235033259423505,
+    "epoch": 2.6666666666666665,
+    "step": 160
+  },
+  {
+    "loss": 0.1717,
+    "grad_norm": 0.2796325385570526,
+    "learning_rate": 0.00013791574279379157,
+    "epoch": 2.8333333333333335,
+    "step": 170
+  },
+  {
+    "loss": 0.2059,
+    "grad_norm": 0.9186252355575562,
+    "learning_rate": 0.00013348115299334812,
+    "epoch": 3.0,
+    "step": 180
+  },
+  {
+    "eval_loss": 0.18136896193027496,
+    "eval_pr_auc": 0.9692257043567982,
+    "eval_runtime": 0.4033,
+    "eval_samples_per_second": 505.866,
+    "eval_steps_per_second": 64.473,
+    "epoch": 3.0,
+    "step": 180
+  },
+  {
+    "loss": 0.0671,
+    "grad_norm": 0.3994855284690857,
+    "learning_rate": 0.00012904656319290468,
+    "epoch": 3.1666666666666665,
+    "step": 190
+  },
+  {
+    "loss": 0.1077,
+    "grad_norm": 5.069406509399414,
+    "learning_rate": 0.0001246119733924612,
+    "epoch": 3.3333333333333335,
+    "step": 200
+  },
+  {
+    "loss": 0.163,
+    "grad_norm": 0.6471376419067383,
+    "learning_rate": 0.00012017738359201774,
+    "epoch": 3.5,
+    "step": 210
+  },
+  {
+    "loss": 0.1038,
+    "grad_norm": 0.20224113762378693,
+    "learning_rate": 0.00011574279379157429,
+    "epoch": 3.6666666666666665,
+    "step": 220
+  },
+  {
+    "loss": 0.121,
+    "grad_norm": 3.1991147994995117,
+    "learning_rate": 0.00011130820399113082,
+    "epoch": 3.8333333333333335,
+    "step": 230
+  },
+  {
+    "loss": 0.1008,
+    "grad_norm": 0.20365029573440552,
+    "learning_rate": 0.00010687361419068738,
+    "epoch": 4.0,
+    "step": 240
+  },
+  {
+    "eval_loss": 0.2102530300617218,
+    "eval_pr_auc": 0.9742538947286151,
+    "eval_runtime": 0.3965,
+    "eval_samples_per_second": 514.466,
+    "eval_steps_per_second": 65.569,
+    "epoch": 4.0,
+    "step": 240
+  },
+  {
+    "loss": 0.0438,
+    "grad_norm": 0.21605148911476135,
+    "learning_rate": 0.0001024390243902439,
+    "epoch": 4.166666666666667,
+    "step": 250
+  },
+  {
+    "loss": 0.0668,
+    "grad_norm": 0.0908743143081665,
+    "learning_rate": 9.800443458980046e-05,
+    "epoch": 4.333333333333333,
+    "step": 260
+  },
+  {
+    "loss": 0.0562,
+    "grad_norm": 3.6227610111236572,
+    "learning_rate": 9.356984478935698e-05,
+    "epoch": 4.5,
+    "step": 270
+  },
+  {
+    "loss": 0.139,
+    "grad_norm": 5.90009069442749,
+    "learning_rate": 8.913525498891354e-05,
+    "epoch": 4.666666666666667,
+    "step": 280
+  },
+  {
+    "loss": 0.1682,
+    "grad_norm": 0.26101890206336975,
+    "learning_rate": 8.470066518847007e-05,
+    "epoch": 4.833333333333333,
+    "step": 290
+  },
+  {
+    "loss": 0.0811,
+    "grad_norm": 0.08818994462490082,
+    "learning_rate": 8.026607538802661e-05,
+    "epoch": 5.0,
+    "step": 300
+  },
+  {
+    "eval_loss": 0.192447230219841,
+    "eval_pr_auc": 0.9751270173678214,
+    "eval_runtime": 0.4,
+    "eval_samples_per_second": 509.942,
+    "eval_steps_per_second": 64.993,
+    "epoch": 5.0,
+    "step": 300
+  },
+  {
+    "loss": 0.0439,
+    "grad_norm": 1.816786289215088,
+    "learning_rate": 7.583148558758315e-05,
+    "epoch": 5.166666666666667,
+    "step": 310
+  },
+  {
+    "loss": 0.0821,
+    "grad_norm": 0.1448965072631836,
+    "learning_rate": 7.139689578713969e-05,
+    "epoch": 5.333333333333333,
+    "step": 320
+  },
+  {
+    "loss": 0.0794,
+    "grad_norm": 0.19551332294940948,
+    "learning_rate": 6.696230598669624e-05,
+    "epoch": 5.5,
+    "step": 330
+  },
+  {
+    "loss": 0.0746,
+    "grad_norm": 0.09540294110774994,
+    "learning_rate": 6.252771618625277e-05,
+    "epoch": 5.666666666666667,
+    "step": 340
+  },
+  {
+    "loss": 0.1648,
+    "grad_norm": 0.11747663468122482,
+    "learning_rate": 5.809312638580932e-05,
+    "epoch": 5.833333333333333,
+    "step": 350
+  },
+  {
+    "loss": 0.0091,
+    "grad_norm": 1.0677231550216675,
+    "learning_rate": 5.365853658536586e-05,
+    "epoch": 6.0,
+    "step": 360
+  },
+  {
+    "eval_loss": 0.19510315358638763,
+    "eval_pr_auc": 0.9770272260812469,
+    "eval_runtime": 0.4071,
+    "eval_samples_per_second": 501.045,
+    "eval_steps_per_second": 63.859,
+    "epoch": 6.0,
+    "step": 360
+  },
+  {
+    "loss": 0.0846,
+    "grad_norm": 4.168880939483643,
+    "learning_rate": 4.92239467849224e-05,
+    "epoch": 6.166666666666667,
+    "step": 370
+  },
+  {
+    "loss": 0.0158,
+    "grad_norm": 0.09182658046483994,
+    "learning_rate": 4.478935698447894e-05,
+    "epoch": 6.333333333333333,
+    "step": 380
+  },
+  {
+    "loss": 0.0566,
+    "grad_norm": 1.1361926794052124,
+    "learning_rate": 4.035476718403548e-05,
+    "epoch": 6.5,
+    "step": 390
+  },
+  {
+    "loss": 0.1311,
+    "grad_norm": 3.7645211219787598,
+    "learning_rate": 3.5920177383592015e-05,
+    "epoch": 6.666666666666667,
+    "step": 400
+  },
+  {
+    "loss": 0.0141,
+    "grad_norm": 0.49836593866348267,
+    "learning_rate": 3.148558758314856e-05,
+    "epoch": 6.833333333333333,
+    "step": 410
+  },
+  {
+    "loss": 0.0381,
+    "grad_norm": 2.4308130741119385,
+    "learning_rate": 2.7050997782705102e-05,
+    "epoch": 7.0,
+    "step": 420
+  },
+  {
+    "eval_loss": 0.2070295661687851,
+    "eval_pr_auc": 0.9792026176606673,
+    "eval_runtime": 0.3966,
+    "eval_samples_per_second": 514.427,
+    "eval_steps_per_second": 65.564,
+    "epoch": 7.0,
+    "step": 420
+  },
+  {
+    "loss": 0.0194,
+    "grad_norm": 0.03615836799144745,
+    "learning_rate": 2.261640798226164e-05,
+    "epoch": 7.166666666666667,
+    "step": 430
+  },
+  {
+    "loss": 0.0575,
+    "grad_norm": 3.66750168800354,
+    "learning_rate": 1.8181818181818182e-05,
+    "epoch": 7.333333333333333,
+    "step": 440
+  },
+  {
+    "loss": 0.1944,
+    "grad_norm": 4.023026466369629,
+    "learning_rate": 1.3747228381374724e-05,
+    "epoch": 7.5,
+    "step": 450
+  },
+  {
+    "loss": 0.0305,
+    "grad_norm": 0.09852059185504913,
+    "learning_rate": 9.312638580931264e-06,
+    "epoch": 7.666666666666667,
+    "step": 460
+  },
+  {
+    "loss": 0.0189,
+    "grad_norm": 0.1663094162940979,
+    "learning_rate": 4.8780487804878055e-06,
+    "epoch": 7.833333333333333,
+    "step": 470
+  },
+  {
+    "loss": 0.0058,
+    "grad_norm": 0.06563691794872284,
+    "learning_rate": 4.434589800443459e-07,
+    "epoch": 8.0,
+    "step": 480
+  },
+  {
+    "eval_loss": 0.2041657716035843,
+    "eval_pr_auc": 0.9786156897267255,
+    "eval_runtime": 0.4007,
+    "eval_samples_per_second": 509.098,
+    "eval_steps_per_second": 64.885,
+    "epoch": 8.0,
+    "step": 480
+  },
+  {
+    "train_runtime": 61.9504,
+    "train_samples_per_second": 123.066,
+    "train_steps_per_second": 7.748,
+    "total_flos": 383113929070272.0,
+    "train_loss": 0.18523927949524174,
+    "epoch": 8.0,
+    "step": 480
+  },
+  {
+    "eval_loss": 0.2070295661687851,
+    "eval_pr_auc": 0.9792026176606673,
+    "eval_runtime": 0.4108,
+    "eval_samples_per_second": 496.556,
+    "eval_steps_per_second": 63.287,
+    "epoch": 8.0,
+    "step": 480
+  }
+]