add lora_no_notinject_seed_44 (V2.2 H100 canonical run)

lora_no_notinject_seed_44/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_no_notinject_seed_44/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": [
+    "query_proj",
+    "value_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_no_notinject_seed_44/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62f356537d1dfb101b71a35465acefb5ba78896969d336fb2108fce918b1766
+size 3555616

lora_no_notinject_seed_44/added_tokens.json

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

lora_no_notinject_seed_44/class_weights.json

@@ -0,0 +1 @@
+{"class_0": 0.6904400587081909, "class_1": 1.8127490282058716}

lora_no_notinject_seed_44/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_no_notinject_seed_44/spm.model

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

lora_no_notinject_seed_44/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_no_notinject_seed_44/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_no_notinject_seed_44/train_history.json

@@ -0,0 +1,407 @@
+[
+  {
+    "loss": 0.6887,
+    "grad_norm": 4.061190128326416,
+    "learning_rate": 6.428571428571429e-05,
+    "epoch": 0.17543859649122806,
+    "step": 10
+  },
+  {
+    "loss": 0.6874,
+    "grad_norm": 3.633615016937256,
+    "learning_rate": 0.00013571428571428572,
+    "epoch": 0.3508771929824561,
+    "step": 20
+  },
+  {
+    "loss": 0.6964,
+    "grad_norm": 1.1961857080459595,
+    "learning_rate": 0.00019953271028037384,
+    "epoch": 0.5263157894736842,
+    "step": 30
+  },
+  {
+    "loss": 0.6687,
+    "grad_norm": 4.15127420425415,
+    "learning_rate": 0.00019485981308411216,
+    "epoch": 0.7017543859649122,
+    "step": 40
+  },
+  {
+    "loss": 0.575,
+    "grad_norm": 3.3165602684020996,
+    "learning_rate": 0.00019018691588785046,
+    "epoch": 0.8771929824561403,
+    "step": 50
+  },
+  {
+    "eval_loss": 0.3386162519454956,
+    "eval_pr_auc": 0.9261158822051679,
+    "eval_runtime": 0.4929,
+    "eval_samples_per_second": 395.617,
+    "eval_steps_per_second": 50.72,
+    "epoch": 1.0,
+    "step": 57
+  },
+  {
+    "loss": 0.4487,
+    "grad_norm": 0.9778897762298584,
+    "learning_rate": 0.0001855140186915888,
+    "epoch": 1.0526315789473684,
+    "step": 60
+  },
+  {
+    "loss": 0.2419,
+    "grad_norm": 0.6682703495025635,
+    "learning_rate": 0.00018084112149532712,
+    "epoch": 1.2280701754385965,
+    "step": 70
+  },
+  {
+    "loss": 0.2453,
+    "grad_norm": 4.002679824829102,
+    "learning_rate": 0.00017616822429906544,
+    "epoch": 1.4035087719298245,
+    "step": 80
+  },
+  {
+    "loss": 0.2283,
+    "grad_norm": 2.052931308746338,
+    "learning_rate": 0.00017149532710280374,
+    "epoch": 1.5789473684210527,
+    "step": 90
+  },
+  {
+    "loss": 0.1296,
+    "grad_norm": 0.6094582080841064,
+    "learning_rate": 0.00016682242990654207,
+    "epoch": 1.7543859649122808,
+    "step": 100
+  },
+  {
+    "loss": 0.1399,
+    "grad_norm": 1.80945885181427,
+    "learning_rate": 0.00016214953271028037,
+    "epoch": 1.9298245614035088,
+    "step": 110
+  },
+  {
+    "eval_loss": 0.22613373398780823,
+    "eval_pr_auc": 0.9572293725690071,
+    "eval_runtime": 0.4,
+    "eval_samples_per_second": 487.501,
+    "eval_steps_per_second": 62.5,
+    "epoch": 2.0,
+    "step": 114
+  },
+  {
+    "loss": 0.1164,
+    "grad_norm": 3.2045722007751465,
+    "learning_rate": 0.0001574766355140187,
+    "epoch": 2.1052631578947367,
+    "step": 120
+  },
+  {
+    "loss": 0.1689,
+    "grad_norm": 0.23376516997814178,
+    "learning_rate": 0.000152803738317757,
+    "epoch": 2.280701754385965,
+    "step": 130
+  },
+  {
+    "loss": 0.0418,
+    "grad_norm": 0.22388669848442078,
+    "learning_rate": 0.00014813084112149532,
+    "epoch": 2.456140350877193,
+    "step": 140
+  },
+  {
+    "loss": 0.1249,
+    "grad_norm": 0.07678008824586868,
+    "learning_rate": 0.00014345794392523365,
+    "epoch": 2.6315789473684212,
+    "step": 150
+  },
+  {
+    "loss": 0.226,
+    "grad_norm": 2.6810173988342285,
+    "learning_rate": 0.00013878504672897198,
+    "epoch": 2.807017543859649,
+    "step": 160
+  },
+  {
+    "loss": 0.1536,
+    "grad_norm": 2.843109130859375,
+    "learning_rate": 0.0001341121495327103,
+    "epoch": 2.982456140350877,
+    "step": 170
+  },
+  {
+    "eval_loss": 0.23242069780826569,
+    "eval_pr_auc": 0.9662168334208976,
+    "eval_runtime": 0.4006,
+    "eval_samples_per_second": 486.787,
+    "eval_steps_per_second": 62.409,
+    "epoch": 3.0,
+    "step": 171
+  },
+  {
+    "loss": 0.1127,
+    "grad_norm": 4.275485992431641,
+    "learning_rate": 0.0001294392523364486,
+    "epoch": 3.1578947368421053,
+    "step": 180
+  },
+  {
+    "loss": 0.1373,
+    "grad_norm": 0.07983385771512985,
+    "learning_rate": 0.00012476635514018693,
+    "epoch": 3.3333333333333335,
+    "step": 190
+  },
+  {
+    "loss": 0.1013,
+    "grad_norm": 0.9692642092704773,
+    "learning_rate": 0.00012009345794392523,
+    "epoch": 3.5087719298245617,
+    "step": 200
+  },
+  {
+    "loss": 0.0705,
+    "grad_norm": 0.08510085940361023,
+    "learning_rate": 0.00011542056074766357,
+    "epoch": 3.6842105263157894,
+    "step": 210
+  },
+  {
+    "loss": 0.1536,
+    "grad_norm": 6.433497905731201,
+    "learning_rate": 0.00011074766355140187,
+    "epoch": 3.8596491228070176,
+    "step": 220
+  },
+  {
+    "eval_loss": 0.2279708832502365,
+    "eval_pr_auc": 0.9704648336068118,
+    "eval_runtime": 0.3997,
+    "eval_samples_per_second": 487.812,
+    "eval_steps_per_second": 62.54,
+    "epoch": 4.0,
+    "step": 228
+  },
+  {
+    "loss": 0.2147,
+    "grad_norm": 1.1425399780273438,
+    "learning_rate": 0.0001060747663551402,
+    "epoch": 4.035087719298246,
+    "step": 230
+  },
+  {
+    "loss": 0.1755,
+    "grad_norm": 0.14083075523376465,
+    "learning_rate": 0.00010140186915887851,
+    "epoch": 4.2105263157894735,
+    "step": 240
+  },
+  {
+    "loss": 0.101,
+    "grad_norm": 4.074350833892822,
+    "learning_rate": 9.672897196261684e-05,
+    "epoch": 4.385964912280702,
+    "step": 250
+  },
+  {
+    "loss": 0.0844,
+    "grad_norm": 1.57571542263031,
+    "learning_rate": 9.205607476635515e-05,
+    "epoch": 4.56140350877193,
+    "step": 260
+  },
+  {
+    "loss": 0.0341,
+    "grad_norm": 0.7043826580047607,
+    "learning_rate": 8.738317757009346e-05,
+    "epoch": 4.7368421052631575,
+    "step": 270
+  },
+  {
+    "loss": 0.1383,
+    "grad_norm": 2.1482040882110596,
+    "learning_rate": 8.271028037383179e-05,
+    "epoch": 4.912280701754386,
+    "step": 280
+  },
+  {
+    "eval_loss": 0.1961831897497177,
+    "eval_pr_auc": 0.975209749373187,
+    "eval_runtime": 0.397,
+    "eval_samples_per_second": 491.19,
+    "eval_steps_per_second": 62.973,
+    "epoch": 5.0,
+    "step": 285
+  },
+  {
+    "loss": 0.0389,
+    "grad_norm": 0.9299774169921875,
+    "learning_rate": 7.80373831775701e-05,
+    "epoch": 5.087719298245614,
+    "step": 290
+  },
+  {
+    "loss": 0.0995,
+    "grad_norm": 0.6308706402778625,
+    "learning_rate": 7.336448598130842e-05,
+    "epoch": 5.2631578947368425,
+    "step": 300
+  },
+  {
+    "loss": 0.0343,
+    "grad_norm": 1.6332752704620361,
+    "learning_rate": 6.869158878504673e-05,
+    "epoch": 5.43859649122807,
+    "step": 310
+  },
+  {
+    "loss": 0.1511,
+    "grad_norm": 4.214924335479736,
+    "learning_rate": 6.401869158878506e-05,
+    "epoch": 5.614035087719298,
+    "step": 320
+  },
+  {
+    "loss": 0.0709,
+    "grad_norm": 0.0669264867901802,
+    "learning_rate": 5.934579439252337e-05,
+    "epoch": 5.7894736842105265,
+    "step": 330
+  },
+  {
+    "loss": 0.0903,
+    "grad_norm": 4.265206813812256,
+    "learning_rate": 5.467289719626168e-05,
+    "epoch": 5.964912280701754,
+    "step": 340
+  },
+  {
+    "eval_loss": 0.17461666464805603,
+    "eval_pr_auc": 0.9768544268730203,
+    "eval_runtime": 0.398,
+    "eval_samples_per_second": 489.894,
+    "eval_steps_per_second": 62.807,
+    "epoch": 6.0,
+    "step": 342
+  },
+  {
+    "loss": 0.0579,
+    "grad_norm": 0.16507357358932495,
+    "learning_rate": 5e-05,
+    "epoch": 6.140350877192983,
+    "step": 350
+  },
+  {
+    "loss": 0.0584,
+    "grad_norm": 2.491332530975342,
+    "learning_rate": 4.532710280373832e-05,
+    "epoch": 6.315789473684211,
+    "step": 360
+  },
+  {
+    "loss": 0.0608,
+    "grad_norm": 0.06606798619031906,
+    "learning_rate": 4.0654205607476636e-05,
+    "epoch": 6.491228070175438,
+    "step": 370
+  },
+  {
+    "loss": 0.123,
+    "grad_norm": 0.23950637876987457,
+    "learning_rate": 3.5981308411214956e-05,
+    "epoch": 6.666666666666667,
+    "step": 380
+  },
+  {
+    "loss": 0.0297,
+    "grad_norm": 0.20692545175552368,
+    "learning_rate": 3.130841121495327e-05,
+    "epoch": 6.842105263157895,
+    "step": 390
+  },
+  {
+    "eval_loss": 0.17639990150928497,
+    "eval_pr_auc": 0.9770536086128998,
+    "eval_runtime": 0.3993,
+    "eval_samples_per_second": 488.409,
+    "eval_steps_per_second": 62.617,
+    "epoch": 7.0,
+    "step": 399
+  },
+  {
+    "loss": 0.0292,
+    "grad_norm": 0.8547989130020142,
+    "learning_rate": 2.663551401869159e-05,
+    "epoch": 7.017543859649122,
+    "step": 400
+  },
+  {
+    "loss": 0.0696,
+    "grad_norm": 0.07230714708566666,
+    "learning_rate": 2.196261682242991e-05,
+    "epoch": 7.192982456140351,
+    "step": 410
+  },
+  {
+    "loss": 0.0364,
+    "grad_norm": 3.7542777061462402,
+    "learning_rate": 1.7289719626168225e-05,
+    "epoch": 7.368421052631579,
+    "step": 420
+  },
+  {
+    "loss": 0.0761,
+    "grad_norm": 2.323049545288086,
+    "learning_rate": 1.2616822429906542e-05,
+    "epoch": 7.543859649122807,
+    "step": 430
+  },
+  {
+    "loss": 0.0319,
+    "grad_norm": 0.1948048323392868,
+    "learning_rate": 7.94392523364486e-06,
+    "epoch": 7.719298245614035,
+    "step": 440
+  },
+  {
+    "loss": 0.1054,
+    "grad_norm": 2.3282456398010254,
+    "learning_rate": 3.2710280373831774e-06,
+    "epoch": 7.894736842105263,
+    "step": 450
+  },
+  {
+    "eval_loss": 0.1758670061826706,
+    "eval_pr_auc": 0.9772398724481051,
+    "eval_runtime": 0.3967,
+    "eval_samples_per_second": 491.583,
+    "eval_steps_per_second": 63.023,
+    "epoch": 8.0,
+    "step": 456
+  },
+  {
+    "train_runtime": 61.0606,
+    "train_samples_per_second": 119.226,
+    "train_steps_per_second": 7.468,
+    "total_flos": 379254045746640.0,
+    "train_loss": 0.17707449171626777,
+    "epoch": 8.0,
+    "step": 456
+  },
+  {
+    "eval_loss": 0.1758670061826706,
+    "eval_pr_auc": 0.9772398724481051,
+    "eval_runtime": 0.4,
+    "eval_samples_per_second": 487.478,
+    "eval_steps_per_second": 62.497,
+    "epoch": 8.0,
+    "step": 456
+  }
+]