add model

README.md

@@ -92,7 +92,7 @@ import torch
 base_model_name = "microsoft/deberta-v3-base"
 model_name = "trapoom555/ThaiSafetyClassifier"
 
-tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 base_model = AutoModelForSequenceClassification.from_pretrained(base_model_name, num_labels=2)
 model = PeftModel.from_pretrained(base_model, model_name)
 model.eval()

added_tokens.json

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

checkpoint-3519/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/deberta-v3-base
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-3519/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value_proj",
+    "key_proj",
+    "query_proj",
+    "dense"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3519/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6823a95b86d40de7bb13e3358d508f589f0fcc587a4a7dbe650312378f720dd6
+size 5384856

checkpoint-3519/added_tokens.json

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

checkpoint-3519/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9fda48ad4327d3c10b7b32ff9cf0bc2eda74e34b6a01f34a29fb6bd0d1b559
+size 10851770

checkpoint-3519/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9df1d292c0d67176f9e11569c0861798ebb26b80ff407b01b1d81bd1d952b8d
+size 14244

checkpoint-3519/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c443b74f8c7bc88e4f001c022dad014ca170623a6004ad5599805d43ce6e4367
+size 1064

checkpoint-3519/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
+  }
+}

checkpoint-3519/spm.model

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

checkpoint-3519/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": true,
+  "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"
+}

checkpoint-3519/trainer_state.json

@@ -0,0 +1,288 @@
+{
+  "best_metric": 0.6391554702495201,
+  "best_model_checkpoint": "models/safety-classifier-gpt41/checkpoint-3519",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3519,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09974424552429667,
+      "grad_norm": 0.4263969659805298,
+      "learning_rate": 8.297872340425533e-05,
+      "loss": 0.1391,
+      "step": 117
+    },
+    {
+      "epoch": 0.19948849104859334,
+      "grad_norm": 0.27834752202033997,
+      "learning_rate": 0.00016595744680851065,
+      "loss": 0.1218,
+      "step": 234
+    },
+    {
+      "epoch": 0.29923273657289,
+      "grad_norm": 0.6282734274864197,
+      "learning_rate": 0.00019687074829931973,
+      "loss": 0.1102,
+      "step": 351
+    },
+    {
+      "epoch": 0.3989769820971867,
+      "grad_norm": 0.44432786107063293,
+      "learning_rate": 0.00019156462585034014,
+      "loss": 0.105,
+      "step": 468
+    },
+    {
+      "epoch": 0.49872122762148335,
+      "grad_norm": 0.2723007798194885,
+      "learning_rate": 0.00018625850340136055,
+      "loss": 0.1079,
+      "step": 585
+    },
+    {
+      "epoch": 0.59846547314578,
+      "grad_norm": 0.48778554797172546,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.1054,
+      "step": 702
+    },
+    {
+      "epoch": 0.6982097186700768,
+      "grad_norm": 0.25881531834602356,
+      "learning_rate": 0.00017564625850340136,
+      "loss": 0.1086,
+      "step": 819
+    },
+    {
+      "epoch": 0.7979539641943734,
+      "grad_norm": 0.25694021582603455,
+      "learning_rate": 0.0001703401360544218,
+      "loss": 0.1048,
+      "step": 936
+    },
+    {
+      "epoch": 0.8976982097186701,
+      "grad_norm": 0.4252418279647827,
+      "learning_rate": 0.0001650340136054422,
+      "loss": 0.1034,
+      "step": 1053
+    },
+    {
+      "epoch": 0.9974424552429667,
+      "grad_norm": 0.41715288162231445,
+      "learning_rate": 0.00015972789115646259,
+      "loss": 0.1021,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6956707187033483,
+      "eval_f1": 0.5335076822491011,
+      "eval_loss": 0.11207349003870727,
+      "eval_precision": 0.38894184938036225,
+      "eval_recall": 0.8491155046826223,
+      "eval_runtime": 29.5167,
+      "eval_samples_per_second": 158.859,
+      "eval_steps_per_second": 4.98,
+      "step": 1173
+    },
+    {
+      "epoch": 1.0971867007672633,
+      "grad_norm": 0.28545722365379333,
+      "learning_rate": 0.000154421768707483,
+      "loss": 0.1003,
+      "step": 1287
+    },
+    {
+      "epoch": 1.19693094629156,
+      "grad_norm": 0.4745310842990875,
+      "learning_rate": 0.0001491156462585034,
+      "loss": 0.1009,
+      "step": 1404
+    },
+    {
+      "epoch": 1.2966751918158568,
+      "grad_norm": 0.375118225812912,
+      "learning_rate": 0.0001438095238095238,
+      "loss": 0.097,
+      "step": 1521
+    },
+    {
+      "epoch": 1.3964194373401535,
+      "grad_norm": 0.30696073174476624,
+      "learning_rate": 0.00013850340136054422,
+      "loss": 0.1,
+      "step": 1638
+    },
+    {
+      "epoch": 1.49616368286445,
+      "grad_norm": 1.0406877994537354,
+      "learning_rate": 0.00013319727891156463,
+      "loss": 0.0907,
+      "step": 1755
+    },
+    {
+      "epoch": 1.5959079283887467,
+      "grad_norm": 0.3132568299770355,
+      "learning_rate": 0.00012789115646258506,
+      "loss": 0.0905,
+      "step": 1872
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.4280431866645813,
+      "learning_rate": 0.00012258503401360544,
+      "loss": 0.0952,
+      "step": 1989
+    },
+    {
+      "epoch": 1.7953964194373402,
+      "grad_norm": 0.7637690305709839,
+      "learning_rate": 0.00011727891156462585,
+      "loss": 0.0962,
+      "step": 2106
+    },
+    {
+      "epoch": 1.895140664961637,
+      "grad_norm": 0.4497227966785431,
+      "learning_rate": 0.00011197278911564626,
+      "loss": 0.0952,
+      "step": 2223
+    },
+    {
+      "epoch": 1.9948849104859336,
+      "grad_norm": 0.8150501251220703,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.0925,
+      "step": 2340
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8328001706120708,
+      "eval_f1": 0.6087824351297405,
+      "eval_loss": 0.08943241893450823,
+      "eval_precision": 0.5848513902205177,
+      "eval_recall": 0.6347554630593132,
+      "eval_runtime": 28.6966,
+      "eval_samples_per_second": 163.399,
+      "eval_steps_per_second": 5.123,
+      "step": 2346
+    },
+    {
+      "epoch": 2.0946291560102304,
+      "grad_norm": 0.6674602031707764,
+      "learning_rate": 0.00010136054421768707,
+      "loss": 0.0848,
+      "step": 2457
+    },
+    {
+      "epoch": 2.1943734015345266,
+      "grad_norm": 0.6307544112205505,
+      "learning_rate": 9.60544217687075e-05,
+      "loss": 0.0915,
+      "step": 2574
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.3149726092815399,
+      "learning_rate": 9.074829931972789e-05,
+      "loss": 0.0881,
+      "step": 2691
+    },
+    {
+      "epoch": 2.39386189258312,
+      "grad_norm": 0.8826068043708801,
+      "learning_rate": 8.54421768707483e-05,
+      "loss": 0.0899,
+      "step": 2808
+    },
+    {
+      "epoch": 2.493606138107417,
+      "grad_norm": 0.3497423231601715,
+      "learning_rate": 8.013605442176872e-05,
+      "loss": 0.0867,
+      "step": 2925
+    },
+    {
+      "epoch": 2.5933503836317136,
+      "grad_norm": 0.4942176640033722,
+      "learning_rate": 7.482993197278913e-05,
+      "loss": 0.0878,
+      "step": 3042
+    },
+    {
+      "epoch": 2.6930946291560103,
+      "grad_norm": 0.6147931218147278,
+      "learning_rate": 6.952380952380952e-05,
+      "loss": 0.0826,
+      "step": 3159
+    },
+    {
+      "epoch": 2.792838874680307,
+      "grad_norm": 0.42120879888534546,
+      "learning_rate": 6.421768707482993e-05,
+      "loss": 0.0868,
+      "step": 3276
+    },
+    {
+      "epoch": 2.8925831202046037,
+      "grad_norm": 0.6062323451042175,
+      "learning_rate": 5.8911564625850346e-05,
+      "loss": 0.0831,
+      "step": 3393
+    },
+    {
+      "epoch": 2.9923273657289,
+      "grad_norm": 0.7976586222648621,
+      "learning_rate": 5.360544217687075e-05,
+      "loss": 0.0838,
+      "step": 3510
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8396246534442312,
+      "eval_f1": 0.6391554702495201,
+      "eval_loss": 0.08481446683795528,
+      "eval_precision": 0.5930543187889582,
+      "eval_recall": 0.6930280957336108,
+      "eval_runtime": 28.8664,
+      "eval_samples_per_second": 162.438,
+      "eval_steps_per_second": 5.092,
+      "step": 3519
+    }
+  ],
+  "logging_steps": 117,
+  "max_steps": 4692,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5037586926129152e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3519/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88469318d71fd6fdbc650d6636dde694f4e2f07d83de351996a297eb050dc96c
+size 5304

checkpoint-4692/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/deberta-v3-base
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-4692/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value_proj",
+    "key_proj",
+    "query_proj",
+    "dense"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-4692/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a719de6f6c46c1a885f9550a31e40d07b74361225ae9b9e46e4321de1f73f1e
+size 5384856

checkpoint-4692/added_tokens.json

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

checkpoint-4692/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55d01042bfad3637cc7bf5cc10faa52480ed6f1a3803438b9ae91cc2f3dd110
+size 10851770

checkpoint-4692/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27f5c297c1e21140a1db26348e8b0237b7d02bfc3983dcf0491b62900bda13e
+size 14244

checkpoint-4692/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332b5fd628f7a1023e56f0518a1587106179be884ad5267398c0bd3fd4a2b739
+size 1064

checkpoint-4692/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
+  }
+}

checkpoint-4692/spm.model

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

checkpoint-4692/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": true,
+  "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"
+}

checkpoint-4692/trainer_state.json

@@ -0,0 +1,370 @@
+{
+  "best_metric": 0.6461538461538462,
+  "best_model_checkpoint": "models/safety-classifier-gpt41/checkpoint-4692",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4692,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09974424552429667,
+      "grad_norm": 0.4263969659805298,
+      "learning_rate": 8.297872340425533e-05,
+      "loss": 0.1391,
+      "step": 117
+    },
+    {
+      "epoch": 0.19948849104859334,
+      "grad_norm": 0.27834752202033997,
+      "learning_rate": 0.00016595744680851065,
+      "loss": 0.1218,
+      "step": 234
+    },
+    {
+      "epoch": 0.29923273657289,
+      "grad_norm": 0.6282734274864197,
+      "learning_rate": 0.00019687074829931973,
+      "loss": 0.1102,
+      "step": 351
+    },
+    {
+      "epoch": 0.3989769820971867,
+      "grad_norm": 0.44432786107063293,
+      "learning_rate": 0.00019156462585034014,
+      "loss": 0.105,
+      "step": 468
+    },
+    {
+      "epoch": 0.49872122762148335,
+      "grad_norm": 0.2723007798194885,
+      "learning_rate": 0.00018625850340136055,
+      "loss": 0.1079,
+      "step": 585
+    },
+    {
+      "epoch": 0.59846547314578,
+      "grad_norm": 0.48778554797172546,
+      "learning_rate": 0.00018095238095238095,
+      "loss": 0.1054,
+      "step": 702
+    },
+    {
+      "epoch": 0.6982097186700768,
+      "grad_norm": 0.25881531834602356,
+      "learning_rate": 0.00017564625850340136,
+      "loss": 0.1086,
+      "step": 819
+    },
+    {
+      "epoch": 0.7979539641943734,
+      "grad_norm": 0.25694021582603455,
+      "learning_rate": 0.0001703401360544218,
+      "loss": 0.1048,
+      "step": 936
+    },
+    {
+      "epoch": 0.8976982097186701,
+      "grad_norm": 0.4252418279647827,
+      "learning_rate": 0.0001650340136054422,
+      "loss": 0.1034,
+      "step": 1053
+    },
+    {
+      "epoch": 0.9974424552429667,
+      "grad_norm": 0.41715288162231445,
+      "learning_rate": 0.00015972789115646259,
+      "loss": 0.1021,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6956707187033483,
+      "eval_f1": 0.5335076822491011,
+      "eval_loss": 0.11207349003870727,
+      "eval_precision": 0.38894184938036225,
+      "eval_recall": 0.8491155046826223,
+      "eval_runtime": 29.5167,
+      "eval_samples_per_second": 158.859,
+      "eval_steps_per_second": 4.98,
+      "step": 1173
+    },
+    {
+      "epoch": 1.0971867007672633,
+      "grad_norm": 0.28545722365379333,
+      "learning_rate": 0.000154421768707483,
+      "loss": 0.1003,
+      "step": 1287
+    },
+    {
+      "epoch": 1.19693094629156,
+      "grad_norm": 0.4745310842990875,
+      "learning_rate": 0.0001491156462585034,
+      "loss": 0.1009,
+      "step": 1404
+    },
+    {
+      "epoch": 1.2966751918158568,
+      "grad_norm": 0.375118225812912,
+      "learning_rate": 0.0001438095238095238,
+      "loss": 0.097,
+      "step": 1521
+    },
+    {
+      "epoch": 1.3964194373401535,
+      "grad_norm": 0.30696073174476624,
+      "learning_rate": 0.00013850340136054422,
+      "loss": 0.1,
+      "step": 1638
+    },
+    {
+      "epoch": 1.49616368286445,
+      "grad_norm": 1.0406877994537354,
+      "learning_rate": 0.00013319727891156463,
+      "loss": 0.0907,
+      "step": 1755
+    },
+    {
+      "epoch": 1.5959079283887467,
+      "grad_norm": 0.3132568299770355,
+      "learning_rate": 0.00012789115646258506,
+      "loss": 0.0905,
+      "step": 1872
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.4280431866645813,
+      "learning_rate": 0.00012258503401360544,
+      "loss": 0.0952,
+      "step": 1989
+    },
+    {
+      "epoch": 1.7953964194373402,
+      "grad_norm": 0.7637690305709839,
+      "learning_rate": 0.00011727891156462585,
+      "loss": 0.0962,
+      "step": 2106
+    },
+    {
+      "epoch": 1.895140664961637,
+      "grad_norm": 0.4497227966785431,
+      "learning_rate": 0.00011197278911564626,
+      "loss": 0.0952,
+      "step": 2223
+    },
+    {
+      "epoch": 1.9948849104859336,
+      "grad_norm": 0.8150501251220703,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.0925,
+      "step": 2340
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8328001706120708,
+      "eval_f1": 0.6087824351297405,
+      "eval_loss": 0.08943241893450823,
+      "eval_precision": 0.5848513902205177,
+      "eval_recall": 0.6347554630593132,
+      "eval_runtime": 28.6966,
+      "eval_samples_per_second": 163.399,
+      "eval_steps_per_second": 5.123,
+      "step": 2346
+    },
+    {
+      "epoch": 2.0946291560102304,
+      "grad_norm": 0.6674602031707764,
+      "learning_rate": 0.00010136054421768707,
+      "loss": 0.0848,
+      "step": 2457
+    },
+    {
+      "epoch": 2.1943734015345266,
+      "grad_norm": 0.6307544112205505,
+      "learning_rate": 9.60544217687075e-05,
+      "loss": 0.0915,
+      "step": 2574
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.3149726092815399,
+      "learning_rate": 9.074829931972789e-05,
+      "loss": 0.0881,
+      "step": 2691
+    },
+    {
+      "epoch": 2.39386189258312,
+      "grad_norm": 0.8826068043708801,
+      "learning_rate": 8.54421768707483e-05,
+      "loss": 0.0899,
+      "step": 2808
+    },
+    {
+      "epoch": 2.493606138107417,
+      "grad_norm": 0.3497423231601715,
+      "learning_rate": 8.013605442176872e-05,
+      "loss": 0.0867,
+      "step": 2925
+    },
+    {
+      "epoch": 2.5933503836317136,
+      "grad_norm": 0.4942176640033722,
+      "learning_rate": 7.482993197278913e-05,
+      "loss": 0.0878,
+      "step": 3042
+    },
+    {
+      "epoch": 2.6930946291560103,
+      "grad_norm": 0.6147931218147278,
+      "learning_rate": 6.952380952380952e-05,
+      "loss": 0.0826,
+      "step": 3159
+    },
+    {
+      "epoch": 2.792838874680307,
+      "grad_norm": 0.42120879888534546,
+      "learning_rate": 6.421768707482993e-05,
+      "loss": 0.0868,
+      "step": 3276
+    },
+    {
+      "epoch": 2.8925831202046037,
+      "grad_norm": 0.6062323451042175,
+      "learning_rate": 5.8911564625850346e-05,
+      "loss": 0.0831,
+      "step": 3393
+    },
+    {
+      "epoch": 2.9923273657289,
+      "grad_norm": 0.7976586222648621,
+      "learning_rate": 5.360544217687075e-05,
+      "loss": 0.0838,
+      "step": 3510
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8396246534442312,
+      "eval_f1": 0.6391554702495201,
+      "eval_loss": 0.08481446683795528,
+      "eval_precision": 0.5930543187889582,
+      "eval_recall": 0.6930280957336108,
+      "eval_runtime": 28.8664,
+      "eval_samples_per_second": 162.438,
+      "eval_steps_per_second": 5.092,
+      "step": 3519
+    },
+    {
+      "epoch": 3.0920716112531967,
+      "grad_norm": 0.34886154532432556,
+      "learning_rate": 4.8299319727891155e-05,
+      "loss": 0.0829,
+      "step": 3627
+    },
+    {
+      "epoch": 3.1918158567774935,
+      "grad_norm": 0.3480125665664673,
+      "learning_rate": 4.299319727891157e-05,
+      "loss": 0.0796,
+      "step": 3744
+    },
+    {
+      "epoch": 3.29156010230179,
+      "grad_norm": 0.4952664077281952,
+      "learning_rate": 3.768707482993197e-05,
+      "loss": 0.0806,
+      "step": 3861
+    },
+    {
+      "epoch": 3.391304347826087,
+      "grad_norm": 0.31144797801971436,
+      "learning_rate": 3.2380952380952386e-05,
+      "loss": 0.0773,
+      "step": 3978
+    },
+    {
+      "epoch": 3.4910485933503836,
+      "grad_norm": 0.30885636806488037,
+      "learning_rate": 2.707482993197279e-05,
+      "loss": 0.0788,
+      "step": 4095
+    },
+    {
+      "epoch": 3.5907928388746804,
+      "grad_norm": 0.2984219491481781,
+      "learning_rate": 2.17687074829932e-05,
+      "loss": 0.0782,
+      "step": 4212
+    },
+    {
+      "epoch": 3.690537084398977,
+      "grad_norm": 1.0008522272109985,
+      "learning_rate": 1.6462585034013607e-05,
+      "loss": 0.0791,
+      "step": 4329
+    },
+    {
+      "epoch": 3.790281329923274,
+      "grad_norm": 0.46631908416748047,
+      "learning_rate": 1.1156462585034013e-05,
+      "loss": 0.0788,
+      "step": 4446
+    },
+    {
+      "epoch": 3.89002557544757,
+      "grad_norm": 0.37387174367904663,
+      "learning_rate": 5.8503401360544215e-06,
+      "loss": 0.0821,
+      "step": 4563
+    },
+    {
+      "epoch": 3.9897698209718673,
+      "grad_norm": 0.3423830568790436,
+      "learning_rate": 5.442176870748299e-07,
+      "loss": 0.0758,
+      "step": 4680
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.838131797824696,
+      "eval_f1": 0.6461538461538462,
+      "eval_loss": 0.08384101994242664,
+      "eval_precision": 0.5853040540540541,
+      "eval_recall": 0.7211238293444329,
+      "eval_runtime": 29.0972,
+      "eval_samples_per_second": 161.15,
+      "eval_steps_per_second": 5.052,
+      "step": 4692
+    }
+  ],
+  "logging_steps": 117,
+  "max_steps": 4692,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0050115901505536e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4692/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88469318d71fd6fdbc650d6636dde694f4e2f07d83de351996a297eb050dc96c
+size 5304

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "safe",
+    "1": "harmful"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "harmful": 1,
+    "safe": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03aa1e7ce2112c2183de6888c2cb111aeacf26e4c578cd7430a029175addbeec
+size 737719272

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
+  }
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": true,
+  "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"
+}