Upload distil-bert-finetuned

README.md

@@ -1,13 +1,23 @@
-
 ---
 language: en
 license: mit
 datasets:
-  - jigsaw-toxic-comment-classification-challenge
-  - kaggle/jigsaw-toxic-comment-classification-challenge
+- jigsaw-toxic-comment-classification-challenge
+- kaggle/jigsaw-toxic-comment-classification-challenge
 tags:
-  - text-classification
+- text-classification
+base_model: google-bert/bert-base-uncased
+library_name: peft
 ---
 
 # Toxicity Detection Model
+train_runtime': 482.6954'  
+r = 4
+num_train_epochs=1
+optim="adamw_torch_fused", 
+lr_scheduler_type="cosine",
+metric_for_best_model="f1",
+
+### Framework versions
 
+- PEFT 0.14.0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "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": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc29c67b80557f0dfe81160dfd9841efffa364385b4b42d827c00a4027bd0090
+size 602824

checkpoint-500/adapter_config.json

@@ -22,7 +22,7 @@
     "score"
   ],
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

checkpoint-500/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df7a59b2e59b6b639b82c72cdd18ccb7309a95c7b7d5a47c6fecae1255befd0
-size 1192672
+oid sha256:fc29c67b80557f0dfe81160dfd9841efffa364385b4b42d827c00a4027bd0090
+size 602824

checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd3d5b8183c61469fc2936f9e067ed38ec258562f9be61c8570102ddb723f7e
-size 2413946
+oid sha256:72b4c62818d8e79e34c9486f18fa80c44afb3618176eb356329fe48e23415d24
+size 1235002

checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b9614a2dd8f1965903f3dc783597c25015cd179e3da6d1cc11d739cb2103d05
-size 14244
+oid sha256:05f5fdd0cfcea8f3ac838eb43dadfd60975a9aa89d70703dfaf554fd5ea5e3e8
+size 14180

checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a442c0f20a8da08e2b2b7a33abdac2007403dde5fa0084e79471b284681b29
+oid sha256:1a40ecfa3f3fd838108dc1603326181f7cc7fa9cd66a24dab20698df0575be28
 size 1064

checkpoint-500/trainer_state.json

@@ -1,8 +1,7 @@
 {
-  "best_global_step": 500,
-  "best_metric": 0.12810905277729034,
-  "best_model_checkpoint": "google-bert/bert-base-uncased_latest/checkpoint-500",
-  "epoch": 0.39154267815191857,
+  "best_metric": 0.883764705882353,
+  "best_model_checkpoint": "bert-LoRA/checkpoint-500",
+  "epoch": 0.6161429451632778,
   "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
@@ -10,29 +9,57 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.39154267815191857,
-      "grad_norm": 1.3777742385864258,
-      "learning_rate": 4.347428869746802e-05,
-      "loss": 0.2151,
+      "epoch": 0.12322858903265557,
+      "grad_norm": 2.5762908458709717,
+      "learning_rate": 1e-05,
+      "loss": 0.7124,
+      "step": 100
+    },
+    {
+      "epoch": 0.24645717806531114,
+      "grad_norm": 3.903473377227783,
+      "learning_rate": 2e-05,
+      "loss": 0.6804,
+      "step": 200
+    },
+    {
+      "epoch": 0.36968576709796674,
+      "grad_norm": 4.333084583282471,
+      "learning_rate": 3e-05,
+      "loss": 0.6274,
+      "step": 300
+    },
+    {
+      "epoch": 0.4929143561306223,
+      "grad_norm": 10.088882446289062,
+      "learning_rate": 4e-05,
+      "loss": 0.4321,
+      "step": 400
+    },
+    {
+      "epoch": 0.6161429451632778,
+      "grad_norm": 3.7033872604370117,
+      "learning_rate": 5e-05,
+      "loss": 0.3077,
       "step": 500
     },
     {
-      "epoch": 0.39154267815191857,
-      "eval_accuracy": 0.9516841610527965,
-      "eval_f1": 0.7489417127971345,
-      "eval_loss": 0.12810905277729034,
-      "eval_precision": 0.8234872896527032,
-      "eval_recall": 0.686772170797253,
-      "eval_runtime": 82.1616,
-      "eval_samples_per_second": 388.442,
-      "eval_steps_per_second": 24.281,
+      "epoch": 0.6161429451632778,
+      "eval_accuracy": 0.8858243451463791,
+      "eval_f1": 0.883764705882353,
+      "eval_loss": 0.2827303111553192,
+      "eval_precision": 0.8985645933014355,
+      "eval_recall": 0.8694444444444445,
+      "eval_runtime": 48.1088,
+      "eval_samples_per_second": 134.903,
+      "eval_steps_per_second": 8.439,
       "step": 500
     }
   ],
-  "logging_steps": 500,
-  "max_steps": 3831,
+  "logging_steps": 100,
+  "max_steps": 811,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
@@ -55,8 +82,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3300271872000000.0,
-  "train_batch_size": 100,
+  "total_flos": 2108550119424000.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094009b6e63cdb02a335427acf4545c4b9788823bf1f8f8537cf5251b590de83
-size 5368
+oid sha256:e66a5f8399f7cf85d254aef6e14b135f4577bf05d32f2eb057b94bdb12a73065
+size 5240

checkpoint-811/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google-bert/bert-base-uncased
+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-811/adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "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": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-811/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcaa21aa10258ad235498952e1c501bda85c13e6f8b74a35d4c2f065ccbf726d
+size 602824

checkpoint-811/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d40f3bca4d162e2c099562eb325ec9893e670c9a16b1b45b76a567f1bdd8a2
+size 1235002

checkpoint-811/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cee06899cccf2ec90751c24c2b4781de247f6de1996bdb7ebf50bc84c1cbccd
+size 14180

checkpoint-811/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77364b19babba12f4b36f5768aeca87e37c49593a3a3046ef990f32a44ab444
+size 1064

checkpoint-811/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.883764705882353,
+  "best_model_checkpoint": "bert-LoRA/checkpoint-500",
+  "epoch": 0.9993838570548367,
+  "eval_steps": 500,
+  "global_step": 811,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12322858903265557,
+      "grad_norm": 2.5762908458709717,
+      "learning_rate": 1e-05,
+      "loss": 0.7124,
+      "step": 100
+    },
+    {
+      "epoch": 0.24645717806531114,
+      "grad_norm": 3.903473377227783,
+      "learning_rate": 2e-05,
+      "loss": 0.6804,
+      "step": 200
+    },
+    {
+      "epoch": 0.36968576709796674,
+      "grad_norm": 4.333084583282471,
+      "learning_rate": 3e-05,
+      "loss": 0.6274,
+      "step": 300
+    },
+    {
+      "epoch": 0.4929143561306223,
+      "grad_norm": 10.088882446289062,
+      "learning_rate": 4e-05,
+      "loss": 0.4321,
+      "step": 400
+    },
+    {
+      "epoch": 0.6161429451632778,
+      "grad_norm": 3.7033872604370117,
+      "learning_rate": 5e-05,
+      "loss": 0.3077,
+      "step": 500
+    },
+    {
+      "epoch": 0.6161429451632778,
+      "eval_accuracy": 0.8858243451463791,
+      "eval_f1": 0.883764705882353,
+      "eval_loss": 0.2827303111553192,
+      "eval_precision": 0.8985645933014355,
+      "eval_recall": 0.8694444444444445,
+      "eval_runtime": 48.1088,
+      "eval_samples_per_second": 134.903,
+      "eval_steps_per_second": 8.439,
+      "step": 500
+    },
+    {
+      "epoch": 0.7393715341959335,
+      "grad_norm": 6.849941730499268,
+      "learning_rate": 3.829316421201216e-05,
+      "loss": 0.2876,
+      "step": 600
+    },
+    {
+      "epoch": 0.862600123228589,
+      "grad_norm": 3.9304003715515137,
+      "learning_rate": 1.4136657181401669e-05,
+      "loss": 0.2557,
+      "step": 700
+    },
+    {
+      "epoch": 0.9858287122612446,
+      "grad_norm": 6.338980674743652,
+      "learning_rate": 1.5417978966698887e-07,
+      "loss": 0.2451,
+      "step": 800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 811,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3420068293705728.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-811/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66a5f8399f7cf85d254aef6e14b135f4577bf05d32f2eb057b94bdb12a73065
+size 5240

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 128
+      "Fixed": 256
     },
     "direction": "Right",
     "pad_to_multiple_of": null,