diff --git a/.gitattributes b/.gitattributes index b392005b3296aa50cc8dda1519597cf17d74e123..ed8d7e630d5b246190c15cd8964df2070c7a7cfa 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1471,3 +1471,12 @@ gemma-2-9b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_b gemma-2-9b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.1-num-2157-sd-1/checkpoint-812/tokenizer.json filter=lfs diff=lfs merge=lfs -text gemma-2-9b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.1-num-2157-sd-1/checkpoint-928/tokenizer.json filter=lfs diff=lfs merge=lfs -text gemma-2-9b-it_int4_flare-headlines_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.1-num-2157-sd-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06e2b9c8e1c8f00ab6934853f4d299e61022d85f --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808f2b059adbf3ea787ca2f58743ccecae7d69ce8521399359da0bb1c5085761 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06e2b9c8e1c8f00ab6934853f4d299e61022d85f --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808f2b059adbf3ea787ca2f58743ccecae7d69ce8521399359da0bb1c5085761 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1ca0c0dd14ae1c667a921431fcc46db89669490 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd25079e646006c93fbffa5952f51b03fc274afdc72fc4347d182dcab6a024ba +size 72886458 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a4da741cf0d296497684fa370dad72fb129c3f1 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2829a6b526230537b8d85b35417ea403b612e97c3894b8b604bcddc50123bea6 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7fd8e4ba4b264f9b50146bc4836cfa9687798ccd --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff44319dcd4c0a7513b00ca43bf411b1c81748c9e99d634dda448a976c61386 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..11c93ccb00cc692232bbce9cf0e4de414ce0d4a4 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/trainer_state.json @@ -0,0 +1,182 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 2.0, + "eval_steps": 10, + "global_step": 194, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9964566651863040.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..864677f489634cc4f3290bcee27f319bc4cf251a --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2c023227361c4659c78a0d6fdf5a76fc5cb8895e7d14e02a93e63451724334 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed9c16b3f94d9e4318797dc89e3e5e0d10c8c579 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fdee7f8566dabe8adb2f5fc1314f2568588ecafde115c0ffb13d7af5f6b4027 +size 72886650 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..dccebf663799756046253c7b6dce326f50ebed5c --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8da35711f210242dc26612e5dfd745bdb69a0de3123302d95c1df6fe36ce3c +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1640f4b18033f4c6fb3e7db9031d15a90a1de826 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6246fdebc78e7c180be66194d437fe040abbaf4367116307886bca6879e4235 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c9b321576dbba5119519f0cc01059e4c22623614 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/trainer_state.json @@ -0,0 +1,260 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 3.0, + "eval_steps": 10, + "global_step": 291, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.4016205370426178, + "learning_rate": 0.0002, + "loss": 1.053, + "step": 200 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.4537462592124939, + "learning_rate": 0.0002, + "loss": 0.9378, + "step": 210 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.43585601449012756, + "learning_rate": 0.0002, + "loss": 0.9556, + "step": 220 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.5386906862258911, + "learning_rate": 0.0002, + "loss": 0.9689, + "step": 230 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.722528874874115, + "learning_rate": 0.0002, + "loss": 0.9812, + "step": 240 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.5693188309669495, + "learning_rate": 0.0002, + "loss": 0.9751, + "step": 250 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.5479232668876648, + "learning_rate": 0.0002, + "loss": 0.9881, + "step": 260 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.6799434423446655, + "learning_rate": 0.0002, + "loss": 1.0062, + "step": 270 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.6431379318237305, + "learning_rate": 0.0002, + "loss": 0.9774, + "step": 280 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.49573859572410583, + "learning_rate": 0.0002, + "loss": 1.0239, + "step": 290 + }, + { + "epoch": 3.0, + "eval_loss": 1.2014847993850708, + "eval_runtime": 24.8828, + "eval_samples_per_second": 3.938, + "eval_steps_per_second": 0.522, + "step": 291 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.494684997779456e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-291/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e3cf577a910e71a0e908b34795c9aaf2583d8fd --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f4687b6b1e3e36f7cfa3ae1ccde80109d5236c8267284a212bea03bf4f0160 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..884fedfca0b2aa3ce1f3d31df0f8e95236cc0e75 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912bcbf11f86674f7af0ac5070aa62298b408deb7c265a7acb39d5f6e2425495 +size 72886650 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d2a21df1cedbc047a525eb8d0feb27173144eca --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39060228d46f8a71ed5df5a40e651051b3a2ce56d12f5adfc47612353c38e120 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ced4cdbf47848e0943a90007202b26ec2b3b3bd9 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52582990db554d60d3d549d806f0d4a4622596f43e5654ded7c33b820dbc2d84 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..751b956ea07bd737e5076fec56db6db8d898e461 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/trainer_state.json @@ -0,0 +1,331 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 4.0, + "eval_steps": 10, + "global_step": 388, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.4016205370426178, + "learning_rate": 0.0002, + "loss": 1.053, + "step": 200 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.4537462592124939, + "learning_rate": 0.0002, + "loss": 0.9378, + "step": 210 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.43585601449012756, + "learning_rate": 0.0002, + "loss": 0.9556, + "step": 220 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.5386906862258911, + "learning_rate": 0.0002, + "loss": 0.9689, + "step": 230 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.722528874874115, + "learning_rate": 0.0002, + "loss": 0.9812, + "step": 240 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.5693188309669495, + "learning_rate": 0.0002, + "loss": 0.9751, + "step": 250 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.5479232668876648, + "learning_rate": 0.0002, + "loss": 0.9881, + "step": 260 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.6799434423446655, + "learning_rate": 0.0002, + "loss": 1.0062, + "step": 270 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.6431379318237305, + "learning_rate": 0.0002, + "loss": 0.9774, + "step": 280 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.49573859572410583, + "learning_rate": 0.0002, + "loss": 1.0239, + "step": 290 + }, + { + "epoch": 3.0, + "eval_loss": 1.2014847993850708, + "eval_runtime": 24.8828, + "eval_samples_per_second": 3.938, + "eval_steps_per_second": 0.522, + "step": 291 + }, + { + "epoch": 3.0927835051546393, + "grad_norm": 0.8711708784103394, + "learning_rate": 0.0002, + "loss": 0.8643, + "step": 300 + }, + { + "epoch": 3.195876288659794, + "grad_norm": 0.8786052465438843, + "learning_rate": 0.0002, + "loss": 0.8139, + "step": 310 + }, + { + "epoch": 3.2989690721649483, + "grad_norm": 0.6987330913543701, + "learning_rate": 0.0002, + "loss": 0.8154, + "step": 320 + }, + { + "epoch": 3.402061855670103, + "grad_norm": 0.9661340713500977, + "learning_rate": 0.0002, + "loss": 0.8414, + "step": 330 + }, + { + "epoch": 3.5051546391752577, + "grad_norm": 0.7045658230781555, + "learning_rate": 0.0002, + "loss": 0.8318, + "step": 340 + }, + { + "epoch": 3.6082474226804124, + "grad_norm": 0.7941751480102539, + "learning_rate": 0.0002, + "loss": 0.7918, + "step": 350 + }, + { + "epoch": 3.711340206185567, + "grad_norm": 0.8815844655036926, + "learning_rate": 0.0002, + "loss": 0.8477, + "step": 360 + }, + { + "epoch": 3.8144329896907214, + "grad_norm": 0.6258918046951294, + "learning_rate": 0.0002, + "loss": 0.828, + "step": 370 + }, + { + "epoch": 3.917525773195876, + "grad_norm": 0.7246745228767395, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 380 + }, + { + "epoch": 4.0, + "eval_loss": 1.2927078008651733, + "eval_runtime": 10.5547, + "eval_samples_per_second": 9.285, + "eval_steps_per_second": 1.232, + "step": 388 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.992913330372608e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-388/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ffc81553affc96059eb884ed3b5a9283223cf1ce --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60da3126e0a2b1dbed6bbef5153e836dd6d11d38e978300e1209de64a3835f98 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..88c1f935229acd44ebe0fcebd263496a2afae4cb --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf3d59ea7833056765b2df4417ecb0079f3aa5b1f70e3be8ccecadf4c819c46 +size 72886650 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba6fba182aa36219c65335fc89da52b1fa9e1e9b --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07f5db565a5a39e8ae0ace5a38bf5f8814aecb407e5e4eb8e38d709ba5e4a354 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbaa9b5729bdc2f017b2a0f3b39f56d77045c1fc --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cbee9cdcd41e19d3cf4574ee31f2f1b34f5c33b24f67842764ead4bf90b6422 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..507408db5f5c1967972ac70b61e15645a7db46d0 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/trainer_state.json @@ -0,0 +1,409 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 5.0, + "eval_steps": 10, + "global_step": 485, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.4016205370426178, + "learning_rate": 0.0002, + "loss": 1.053, + "step": 200 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.4537462592124939, + "learning_rate": 0.0002, + "loss": 0.9378, + "step": 210 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.43585601449012756, + "learning_rate": 0.0002, + "loss": 0.9556, + "step": 220 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.5386906862258911, + "learning_rate": 0.0002, + "loss": 0.9689, + "step": 230 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.722528874874115, + "learning_rate": 0.0002, + "loss": 0.9812, + "step": 240 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.5693188309669495, + "learning_rate": 0.0002, + "loss": 0.9751, + "step": 250 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.5479232668876648, + "learning_rate": 0.0002, + "loss": 0.9881, + "step": 260 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.6799434423446655, + "learning_rate": 0.0002, + "loss": 1.0062, + "step": 270 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.6431379318237305, + "learning_rate": 0.0002, + "loss": 0.9774, + "step": 280 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.49573859572410583, + "learning_rate": 0.0002, + "loss": 1.0239, + "step": 290 + }, + { + "epoch": 3.0, + "eval_loss": 1.2014847993850708, + "eval_runtime": 24.8828, + "eval_samples_per_second": 3.938, + "eval_steps_per_second": 0.522, + "step": 291 + }, + { + "epoch": 3.0927835051546393, + "grad_norm": 0.8711708784103394, + "learning_rate": 0.0002, + "loss": 0.8643, + "step": 300 + }, + { + "epoch": 3.195876288659794, + "grad_norm": 0.8786052465438843, + "learning_rate": 0.0002, + "loss": 0.8139, + "step": 310 + }, + { + "epoch": 3.2989690721649483, + "grad_norm": 0.6987330913543701, + "learning_rate": 0.0002, + "loss": 0.8154, + "step": 320 + }, + { + "epoch": 3.402061855670103, + "grad_norm": 0.9661340713500977, + "learning_rate": 0.0002, + "loss": 0.8414, + "step": 330 + }, + { + "epoch": 3.5051546391752577, + "grad_norm": 0.7045658230781555, + "learning_rate": 0.0002, + "loss": 0.8318, + "step": 340 + }, + { + "epoch": 3.6082474226804124, + "grad_norm": 0.7941751480102539, + "learning_rate": 0.0002, + "loss": 0.7918, + "step": 350 + }, + { + "epoch": 3.711340206185567, + "grad_norm": 0.8815844655036926, + "learning_rate": 0.0002, + "loss": 0.8477, + "step": 360 + }, + { + "epoch": 3.8144329896907214, + "grad_norm": 0.6258918046951294, + "learning_rate": 0.0002, + "loss": 0.828, + "step": 370 + }, + { + "epoch": 3.917525773195876, + "grad_norm": 0.7246745228767395, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 380 + }, + { + "epoch": 4.0, + "eval_loss": 1.2927078008651733, + "eval_runtime": 10.5547, + "eval_samples_per_second": 9.285, + "eval_steps_per_second": 1.232, + "step": 388 + }, + { + "epoch": 4.020618556701031, + "grad_norm": 0.725050151348114, + "learning_rate": 0.0002, + "loss": 0.8201, + "step": 390 + }, + { + "epoch": 4.123711340206185, + "grad_norm": 1.0035908222198486, + "learning_rate": 0.0002, + "loss": 0.6623, + "step": 400 + }, + { + "epoch": 4.22680412371134, + "grad_norm": 1.2170008420944214, + "learning_rate": 0.0002, + "loss": 0.6517, + "step": 410 + }, + { + "epoch": 4.329896907216495, + "grad_norm": 1.0720841884613037, + "learning_rate": 0.0002, + "loss": 0.6769, + "step": 420 + }, + { + "epoch": 4.43298969072165, + "grad_norm": 1.0538380146026611, + "learning_rate": 0.0002, + "loss": 0.6536, + "step": 430 + }, + { + "epoch": 4.536082474226804, + "grad_norm": 0.7770849466323853, + "learning_rate": 0.0002, + "loss": 0.676, + "step": 440 + }, + { + "epoch": 4.639175257731958, + "grad_norm": 0.9066935777664185, + "learning_rate": 0.0002, + "loss": 0.6632, + "step": 450 + }, + { + "epoch": 4.742268041237113, + "grad_norm": 0.7707642912864685, + "learning_rate": 0.0002, + "loss": 0.6738, + "step": 460 + }, + { + "epoch": 4.845360824742268, + "grad_norm": 0.8185567855834961, + "learning_rate": 0.0002, + "loss": 0.7144, + "step": 470 + }, + { + "epoch": 4.948453608247423, + "grad_norm": 0.9264892339706421, + "learning_rate": 0.0002, + "loss": 0.6495, + "step": 480 + }, + { + "epoch": 5.0, + "eval_loss": 1.3918720483779907, + "eval_runtime": 24.8943, + "eval_samples_per_second": 3.937, + "eval_steps_per_second": 0.522, + "step": 485 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.49114166296576e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-485/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c42b868e57730f5eb580668ff2530f52d90d1bc --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f99bae7c46136d49d09536b68926d608f2fe2d24556e9aab0705a5ae898f92 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8263e9521fb393805f15ebff2fec78c1984c7f0 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1632a3a5df981418fb7342c3df81ae8095cbc980eafba82e5cd13d1520ae91e6 +size 72886650 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa9fc3584a1b20c22b0ba19893f8150065b338ab --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba18f8842144cc14d92d52f53704ee900eed038db7820a724ee0adcac3362b3 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..faea43de54b174a3dfbcceb9bbe92431735e5af1 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97b2cb233066afff99cd537832f699744e12d178f8feb2f1c03e15ca1e9a4dfd +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2950d0a03ad46ab08ca47f98d8bf1950a29b247b --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/trainer_state.json @@ -0,0 +1,487 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 6.0, + "eval_steps": 10, + "global_step": 582, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.4016205370426178, + "learning_rate": 0.0002, + "loss": 1.053, + "step": 200 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.4537462592124939, + "learning_rate": 0.0002, + "loss": 0.9378, + "step": 210 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.43585601449012756, + "learning_rate": 0.0002, + "loss": 0.9556, + "step": 220 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.5386906862258911, + "learning_rate": 0.0002, + "loss": 0.9689, + "step": 230 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.722528874874115, + "learning_rate": 0.0002, + "loss": 0.9812, + "step": 240 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.5693188309669495, + "learning_rate": 0.0002, + "loss": 0.9751, + "step": 250 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.5479232668876648, + "learning_rate": 0.0002, + "loss": 0.9881, + "step": 260 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.6799434423446655, + "learning_rate": 0.0002, + "loss": 1.0062, + "step": 270 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.6431379318237305, + "learning_rate": 0.0002, + "loss": 0.9774, + "step": 280 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.49573859572410583, + "learning_rate": 0.0002, + "loss": 1.0239, + "step": 290 + }, + { + "epoch": 3.0, + "eval_loss": 1.2014847993850708, + "eval_runtime": 24.8828, + "eval_samples_per_second": 3.938, + "eval_steps_per_second": 0.522, + "step": 291 + }, + { + "epoch": 3.0927835051546393, + "grad_norm": 0.8711708784103394, + "learning_rate": 0.0002, + "loss": 0.8643, + "step": 300 + }, + { + "epoch": 3.195876288659794, + "grad_norm": 0.8786052465438843, + "learning_rate": 0.0002, + "loss": 0.8139, + "step": 310 + }, + { + "epoch": 3.2989690721649483, + "grad_norm": 0.6987330913543701, + "learning_rate": 0.0002, + "loss": 0.8154, + "step": 320 + }, + { + "epoch": 3.402061855670103, + "grad_norm": 0.9661340713500977, + "learning_rate": 0.0002, + "loss": 0.8414, + "step": 330 + }, + { + "epoch": 3.5051546391752577, + "grad_norm": 0.7045658230781555, + "learning_rate": 0.0002, + "loss": 0.8318, + "step": 340 + }, + { + "epoch": 3.6082474226804124, + "grad_norm": 0.7941751480102539, + "learning_rate": 0.0002, + "loss": 0.7918, + "step": 350 + }, + { + "epoch": 3.711340206185567, + "grad_norm": 0.8815844655036926, + "learning_rate": 0.0002, + "loss": 0.8477, + "step": 360 + }, + { + "epoch": 3.8144329896907214, + "grad_norm": 0.6258918046951294, + "learning_rate": 0.0002, + "loss": 0.828, + "step": 370 + }, + { + "epoch": 3.917525773195876, + "grad_norm": 0.7246745228767395, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 380 + }, + { + "epoch": 4.0, + "eval_loss": 1.2927078008651733, + "eval_runtime": 10.5547, + "eval_samples_per_second": 9.285, + "eval_steps_per_second": 1.232, + "step": 388 + }, + { + "epoch": 4.020618556701031, + "grad_norm": 0.725050151348114, + "learning_rate": 0.0002, + "loss": 0.8201, + "step": 390 + }, + { + "epoch": 4.123711340206185, + "grad_norm": 1.0035908222198486, + "learning_rate": 0.0002, + "loss": 0.6623, + "step": 400 + }, + { + "epoch": 4.22680412371134, + "grad_norm": 1.2170008420944214, + "learning_rate": 0.0002, + "loss": 0.6517, + "step": 410 + }, + { + "epoch": 4.329896907216495, + "grad_norm": 1.0720841884613037, + "learning_rate": 0.0002, + "loss": 0.6769, + "step": 420 + }, + { + "epoch": 4.43298969072165, + "grad_norm": 1.0538380146026611, + "learning_rate": 0.0002, + "loss": 0.6536, + "step": 430 + }, + { + "epoch": 4.536082474226804, + "grad_norm": 0.7770849466323853, + "learning_rate": 0.0002, + "loss": 0.676, + "step": 440 + }, + { + "epoch": 4.639175257731958, + "grad_norm": 0.9066935777664185, + "learning_rate": 0.0002, + "loss": 0.6632, + "step": 450 + }, + { + "epoch": 4.742268041237113, + "grad_norm": 0.7707642912864685, + "learning_rate": 0.0002, + "loss": 0.6738, + "step": 460 + }, + { + "epoch": 4.845360824742268, + "grad_norm": 0.8185567855834961, + "learning_rate": 0.0002, + "loss": 0.7144, + "step": 470 + }, + { + "epoch": 4.948453608247423, + "grad_norm": 0.9264892339706421, + "learning_rate": 0.0002, + "loss": 0.6495, + "step": 480 + }, + { + "epoch": 5.0, + "eval_loss": 1.3918720483779907, + "eval_runtime": 24.8943, + "eval_samples_per_second": 3.937, + "eval_steps_per_second": 0.522, + "step": 485 + }, + { + "epoch": 5.051546391752577, + "grad_norm": 1.0677416324615479, + "learning_rate": 0.0002, + "loss": 0.6318, + "step": 490 + }, + { + "epoch": 5.154639175257732, + "grad_norm": 1.1246110200881958, + "learning_rate": 0.0002, + "loss": 0.5416, + "step": 500 + }, + { + "epoch": 5.257731958762887, + "grad_norm": 1.4362645149230957, + "learning_rate": 0.0002, + "loss": 0.4953, + "step": 510 + }, + { + "epoch": 5.360824742268041, + "grad_norm": 1.143323540687561, + "learning_rate": 0.0002, + "loss": 0.5098, + "step": 520 + }, + { + "epoch": 5.463917525773196, + "grad_norm": 1.1483081579208374, + "learning_rate": 0.0002, + "loss": 0.4947, + "step": 530 + }, + { + "epoch": 5.56701030927835, + "grad_norm": 1.2788265943527222, + "learning_rate": 0.0002, + "loss": 0.5458, + "step": 540 + }, + { + "epoch": 5.670103092783505, + "grad_norm": 0.9921451807022095, + "learning_rate": 0.0002, + "loss": 0.5165, + "step": 550 + }, + { + "epoch": 5.77319587628866, + "grad_norm": 0.9654388427734375, + "learning_rate": 0.0002, + "loss": 0.5557, + "step": 560 + }, + { + "epoch": 5.876288659793815, + "grad_norm": 1.203700065612793, + "learning_rate": 0.0002, + "loss": 0.5468, + "step": 570 + }, + { + "epoch": 5.979381443298969, + "grad_norm": 1.0011067390441895, + "learning_rate": 0.0002, + "loss": 0.5596, + "step": 580 + }, + { + "epoch": 6.0, + "eval_loss": 1.6636911630630493, + "eval_runtime": 25.0718, + "eval_samples_per_second": 3.909, + "eval_steps_per_second": 0.519, + "step": 582 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.989369995558912e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-582/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..476ddaa25acb54a8716aa328a573d4d32aad7ce4 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14128fe64009e75a5ef81128fa075e40785ce4917db7aee1af2e9b1b8214b45 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebb4a8ebf2771f092fb2cbb941794b3e2d9683b0 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56376cb7b1d730ec2e1c4578eee17f89e0a253841e6c26bd2c9aeafde73a0299 +size 72886650 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..243df1d8d98ff2bf69423e8e4140d77a772a3371 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2df4d9ed3f266833de6e23c70a977f58253fa530b9ce8bc9151e6aedad1fa59 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..011bf12c3c7c9cf1e5331c8706701a7c9d3833c0 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49979e19d0716773472fc49fe2f05e5cdd6c3e2cc9dbbbfad293b805ba8f2634 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..3ecf6bb5e8dab911dafa8c1d3cf676de860143cb --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/trainer_state.json @@ -0,0 +1,558 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 7.0, + "eval_steps": 10, + "global_step": 679, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.4016205370426178, + "learning_rate": 0.0002, + "loss": 1.053, + "step": 200 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.4537462592124939, + "learning_rate": 0.0002, + "loss": 0.9378, + "step": 210 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.43585601449012756, + "learning_rate": 0.0002, + "loss": 0.9556, + "step": 220 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.5386906862258911, + "learning_rate": 0.0002, + "loss": 0.9689, + "step": 230 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.722528874874115, + "learning_rate": 0.0002, + "loss": 0.9812, + "step": 240 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.5693188309669495, + "learning_rate": 0.0002, + "loss": 0.9751, + "step": 250 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.5479232668876648, + "learning_rate": 0.0002, + "loss": 0.9881, + "step": 260 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.6799434423446655, + "learning_rate": 0.0002, + "loss": 1.0062, + "step": 270 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.6431379318237305, + "learning_rate": 0.0002, + "loss": 0.9774, + "step": 280 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.49573859572410583, + "learning_rate": 0.0002, + "loss": 1.0239, + "step": 290 + }, + { + "epoch": 3.0, + "eval_loss": 1.2014847993850708, + "eval_runtime": 24.8828, + "eval_samples_per_second": 3.938, + "eval_steps_per_second": 0.522, + "step": 291 + }, + { + "epoch": 3.0927835051546393, + "grad_norm": 0.8711708784103394, + "learning_rate": 0.0002, + "loss": 0.8643, + "step": 300 + }, + { + "epoch": 3.195876288659794, + "grad_norm": 0.8786052465438843, + "learning_rate": 0.0002, + "loss": 0.8139, + "step": 310 + }, + { + "epoch": 3.2989690721649483, + "grad_norm": 0.6987330913543701, + "learning_rate": 0.0002, + "loss": 0.8154, + "step": 320 + }, + { + "epoch": 3.402061855670103, + "grad_norm": 0.9661340713500977, + "learning_rate": 0.0002, + "loss": 0.8414, + "step": 330 + }, + { + "epoch": 3.5051546391752577, + "grad_norm": 0.7045658230781555, + "learning_rate": 0.0002, + "loss": 0.8318, + "step": 340 + }, + { + "epoch": 3.6082474226804124, + "grad_norm": 0.7941751480102539, + "learning_rate": 0.0002, + "loss": 0.7918, + "step": 350 + }, + { + "epoch": 3.711340206185567, + "grad_norm": 0.8815844655036926, + "learning_rate": 0.0002, + "loss": 0.8477, + "step": 360 + }, + { + "epoch": 3.8144329896907214, + "grad_norm": 0.6258918046951294, + "learning_rate": 0.0002, + "loss": 0.828, + "step": 370 + }, + { + "epoch": 3.917525773195876, + "grad_norm": 0.7246745228767395, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 380 + }, + { + "epoch": 4.0, + "eval_loss": 1.2927078008651733, + "eval_runtime": 10.5547, + "eval_samples_per_second": 9.285, + "eval_steps_per_second": 1.232, + "step": 388 + }, + { + "epoch": 4.020618556701031, + "grad_norm": 0.725050151348114, + "learning_rate": 0.0002, + "loss": 0.8201, + "step": 390 + }, + { + "epoch": 4.123711340206185, + "grad_norm": 1.0035908222198486, + "learning_rate": 0.0002, + "loss": 0.6623, + "step": 400 + }, + { + "epoch": 4.22680412371134, + "grad_norm": 1.2170008420944214, + "learning_rate": 0.0002, + "loss": 0.6517, + "step": 410 + }, + { + "epoch": 4.329896907216495, + "grad_norm": 1.0720841884613037, + "learning_rate": 0.0002, + "loss": 0.6769, + "step": 420 + }, + { + "epoch": 4.43298969072165, + "grad_norm": 1.0538380146026611, + "learning_rate": 0.0002, + "loss": 0.6536, + "step": 430 + }, + { + "epoch": 4.536082474226804, + "grad_norm": 0.7770849466323853, + "learning_rate": 0.0002, + "loss": 0.676, + "step": 440 + }, + { + "epoch": 4.639175257731958, + "grad_norm": 0.9066935777664185, + "learning_rate": 0.0002, + "loss": 0.6632, + "step": 450 + }, + { + "epoch": 4.742268041237113, + "grad_norm": 0.7707642912864685, + "learning_rate": 0.0002, + "loss": 0.6738, + "step": 460 + }, + { + "epoch": 4.845360824742268, + "grad_norm": 0.8185567855834961, + "learning_rate": 0.0002, + "loss": 0.7144, + "step": 470 + }, + { + "epoch": 4.948453608247423, + "grad_norm": 0.9264892339706421, + "learning_rate": 0.0002, + "loss": 0.6495, + "step": 480 + }, + { + "epoch": 5.0, + "eval_loss": 1.3918720483779907, + "eval_runtime": 24.8943, + "eval_samples_per_second": 3.937, + "eval_steps_per_second": 0.522, + "step": 485 + }, + { + "epoch": 5.051546391752577, + "grad_norm": 1.0677416324615479, + "learning_rate": 0.0002, + "loss": 0.6318, + "step": 490 + }, + { + "epoch": 5.154639175257732, + "grad_norm": 1.1246110200881958, + "learning_rate": 0.0002, + "loss": 0.5416, + "step": 500 + }, + { + "epoch": 5.257731958762887, + "grad_norm": 1.4362645149230957, + "learning_rate": 0.0002, + "loss": 0.4953, + "step": 510 + }, + { + "epoch": 5.360824742268041, + "grad_norm": 1.143323540687561, + "learning_rate": 0.0002, + "loss": 0.5098, + "step": 520 + }, + { + "epoch": 5.463917525773196, + "grad_norm": 1.1483081579208374, + "learning_rate": 0.0002, + "loss": 0.4947, + "step": 530 + }, + { + "epoch": 5.56701030927835, + "grad_norm": 1.2788265943527222, + "learning_rate": 0.0002, + "loss": 0.5458, + "step": 540 + }, + { + "epoch": 5.670103092783505, + "grad_norm": 0.9921451807022095, + "learning_rate": 0.0002, + "loss": 0.5165, + "step": 550 + }, + { + "epoch": 5.77319587628866, + "grad_norm": 0.9654388427734375, + "learning_rate": 0.0002, + "loss": 0.5557, + "step": 560 + }, + { + "epoch": 5.876288659793815, + "grad_norm": 1.203700065612793, + "learning_rate": 0.0002, + "loss": 0.5468, + "step": 570 + }, + { + "epoch": 5.979381443298969, + "grad_norm": 1.0011067390441895, + "learning_rate": 0.0002, + "loss": 0.5596, + "step": 580 + }, + { + "epoch": 6.0, + "eval_loss": 1.6636911630630493, + "eval_runtime": 25.0718, + "eval_samples_per_second": 3.909, + "eval_steps_per_second": 0.519, + "step": 582 + }, + { + "epoch": 6.082474226804123, + "grad_norm": 1.3850897550582886, + "learning_rate": 0.0002, + "loss": 0.4129, + "step": 590 + }, + { + "epoch": 6.185567010309279, + "grad_norm": 1.2155243158340454, + "learning_rate": 0.0002, + "loss": 0.3656, + "step": 600 + }, + { + "epoch": 6.288659793814433, + "grad_norm": 1.149451494216919, + "learning_rate": 0.0002, + "loss": 0.3775, + "step": 610 + }, + { + "epoch": 6.391752577319588, + "grad_norm": 1.4000080823898315, + "learning_rate": 0.0002, + "loss": 0.4071, + "step": 620 + }, + { + "epoch": 6.494845360824742, + "grad_norm": 1.2047293186187744, + "learning_rate": 0.0002, + "loss": 0.3944, + "step": 630 + }, + { + "epoch": 6.597938144329897, + "grad_norm": 1.3094227313995361, + "learning_rate": 0.0002, + "loss": 0.4172, + "step": 640 + }, + { + "epoch": 6.701030927835052, + "grad_norm": 1.1890202760696411, + "learning_rate": 0.0002, + "loss": 0.4205, + "step": 650 + }, + { + "epoch": 6.804123711340206, + "grad_norm": 1.053261637687683, + "learning_rate": 0.0002, + "loss": 0.3944, + "step": 660 + }, + { + "epoch": 6.907216494845361, + "grad_norm": 1.2590222358703613, + "learning_rate": 0.0002, + "loss": 0.4419, + "step": 670 + }, + { + "epoch": 7.0, + "eval_loss": 1.7902696132659912, + "eval_runtime": 24.9138, + "eval_samples_per_second": 3.934, + "eval_steps_per_second": 0.522, + "step": 679 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.487598328152064e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-679/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a25b58b64e2265cba4d8533ab123c4a1a8561668 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba34cba1aaed9a485b44164b5ad3f75d6443460046061e16756a0eba578f21b +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1989ddbf0f9ad86d423e63b0ac5fa969343c9820 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928100c16113282557493e2665c72fb03cf89aa9a2229c91aa0f4886884d8d0b +size 72886650 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..3834818e5b2ca69bdedca21ff07453ef14b3732c --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb56ea68a63c3d2179cb82ba0aca1fe2383658cdaf36bef9454e16c594104502 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bbb5c04ed2350bdac9bef89b2ea16e15b6718cb --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a94731c4d3abe37fc2e6a02f538d43e36811ebae87938382055303676b58c972 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d264e4c6566858cee9827899ef4c97280b97cf7e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/trainer_state.json @@ -0,0 +1,636 @@ +{ + "best_metric": 1.1786428689956665, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", + "epoch": 8.0, + "eval_steps": 10, + "global_step": 776, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.39316999912261963, + "learning_rate": 0.0002, + "loss": 1.2027, + "step": 100 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.34155887365341187, + "learning_rate": 0.0002, + "loss": 1.1257, + "step": 110 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.43475863337516785, + "learning_rate": 0.0002, + "loss": 1.0775, + "step": 120 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.47940605878829956, + "learning_rate": 0.0002, + "loss": 1.0916, + "step": 130 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.42031461000442505, + "learning_rate": 0.0002, + "loss": 1.1242, + "step": 140 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.45062679052352905, + "learning_rate": 0.0002, + "loss": 1.1327, + "step": 150 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.39917513728141785, + "learning_rate": 0.0002, + "loss": 1.1186, + "step": 160 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.4017351567745209, + "learning_rate": 0.0002, + "loss": 1.0824, + "step": 170 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.4676169157028198, + "learning_rate": 0.0002, + "loss": 1.1553, + "step": 180 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.4058385491371155, + "learning_rate": 0.0002, + "loss": 1.1191, + "step": 190 + }, + { + "epoch": 2.0, + "eval_loss": 1.1786428689956665, + "eval_runtime": 24.6076, + "eval_samples_per_second": 3.983, + "eval_steps_per_second": 0.528, + "step": 194 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.4016205370426178, + "learning_rate": 0.0002, + "loss": 1.053, + "step": 200 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.4537462592124939, + "learning_rate": 0.0002, + "loss": 0.9378, + "step": 210 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.43585601449012756, + "learning_rate": 0.0002, + "loss": 0.9556, + "step": 220 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.5386906862258911, + "learning_rate": 0.0002, + "loss": 0.9689, + "step": 230 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.722528874874115, + "learning_rate": 0.0002, + "loss": 0.9812, + "step": 240 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.5693188309669495, + "learning_rate": 0.0002, + "loss": 0.9751, + "step": 250 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.5479232668876648, + "learning_rate": 0.0002, + "loss": 0.9881, + "step": 260 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.6799434423446655, + "learning_rate": 0.0002, + "loss": 1.0062, + "step": 270 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.6431379318237305, + "learning_rate": 0.0002, + "loss": 0.9774, + "step": 280 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.49573859572410583, + "learning_rate": 0.0002, + "loss": 1.0239, + "step": 290 + }, + { + "epoch": 3.0, + "eval_loss": 1.2014847993850708, + "eval_runtime": 24.8828, + "eval_samples_per_second": 3.938, + "eval_steps_per_second": 0.522, + "step": 291 + }, + { + "epoch": 3.0927835051546393, + "grad_norm": 0.8711708784103394, + "learning_rate": 0.0002, + "loss": 0.8643, + "step": 300 + }, + { + "epoch": 3.195876288659794, + "grad_norm": 0.8786052465438843, + "learning_rate": 0.0002, + "loss": 0.8139, + "step": 310 + }, + { + "epoch": 3.2989690721649483, + "grad_norm": 0.6987330913543701, + "learning_rate": 0.0002, + "loss": 0.8154, + "step": 320 + }, + { + "epoch": 3.402061855670103, + "grad_norm": 0.9661340713500977, + "learning_rate": 0.0002, + "loss": 0.8414, + "step": 330 + }, + { + "epoch": 3.5051546391752577, + "grad_norm": 0.7045658230781555, + "learning_rate": 0.0002, + "loss": 0.8318, + "step": 340 + }, + { + "epoch": 3.6082474226804124, + "grad_norm": 0.7941751480102539, + "learning_rate": 0.0002, + "loss": 0.7918, + "step": 350 + }, + { + "epoch": 3.711340206185567, + "grad_norm": 0.8815844655036926, + "learning_rate": 0.0002, + "loss": 0.8477, + "step": 360 + }, + { + "epoch": 3.8144329896907214, + "grad_norm": 0.6258918046951294, + "learning_rate": 0.0002, + "loss": 0.828, + "step": 370 + }, + { + "epoch": 3.917525773195876, + "grad_norm": 0.7246745228767395, + "learning_rate": 0.0002, + "loss": 0.8173, + "step": 380 + }, + { + "epoch": 4.0, + "eval_loss": 1.2927078008651733, + "eval_runtime": 10.5547, + "eval_samples_per_second": 9.285, + "eval_steps_per_second": 1.232, + "step": 388 + }, + { + "epoch": 4.020618556701031, + "grad_norm": 0.725050151348114, + "learning_rate": 0.0002, + "loss": 0.8201, + "step": 390 + }, + { + "epoch": 4.123711340206185, + "grad_norm": 1.0035908222198486, + "learning_rate": 0.0002, + "loss": 0.6623, + "step": 400 + }, + { + "epoch": 4.22680412371134, + "grad_norm": 1.2170008420944214, + "learning_rate": 0.0002, + "loss": 0.6517, + "step": 410 + }, + { + "epoch": 4.329896907216495, + "grad_norm": 1.0720841884613037, + "learning_rate": 0.0002, + "loss": 0.6769, + "step": 420 + }, + { + "epoch": 4.43298969072165, + "grad_norm": 1.0538380146026611, + "learning_rate": 0.0002, + "loss": 0.6536, + "step": 430 + }, + { + "epoch": 4.536082474226804, + "grad_norm": 0.7770849466323853, + "learning_rate": 0.0002, + "loss": 0.676, + "step": 440 + }, + { + "epoch": 4.639175257731958, + "grad_norm": 0.9066935777664185, + "learning_rate": 0.0002, + "loss": 0.6632, + "step": 450 + }, + { + "epoch": 4.742268041237113, + "grad_norm": 0.7707642912864685, + "learning_rate": 0.0002, + "loss": 0.6738, + "step": 460 + }, + { + "epoch": 4.845360824742268, + "grad_norm": 0.8185567855834961, + "learning_rate": 0.0002, + "loss": 0.7144, + "step": 470 + }, + { + "epoch": 4.948453608247423, + "grad_norm": 0.9264892339706421, + "learning_rate": 0.0002, + "loss": 0.6495, + "step": 480 + }, + { + "epoch": 5.0, + "eval_loss": 1.3918720483779907, + "eval_runtime": 24.8943, + "eval_samples_per_second": 3.937, + "eval_steps_per_second": 0.522, + "step": 485 + }, + { + "epoch": 5.051546391752577, + "grad_norm": 1.0677416324615479, + "learning_rate": 0.0002, + "loss": 0.6318, + "step": 490 + }, + { + "epoch": 5.154639175257732, + "grad_norm": 1.1246110200881958, + "learning_rate": 0.0002, + "loss": 0.5416, + "step": 500 + }, + { + "epoch": 5.257731958762887, + "grad_norm": 1.4362645149230957, + "learning_rate": 0.0002, + "loss": 0.4953, + "step": 510 + }, + { + "epoch": 5.360824742268041, + "grad_norm": 1.143323540687561, + "learning_rate": 0.0002, + "loss": 0.5098, + "step": 520 + }, + { + "epoch": 5.463917525773196, + "grad_norm": 1.1483081579208374, + "learning_rate": 0.0002, + "loss": 0.4947, + "step": 530 + }, + { + "epoch": 5.56701030927835, + "grad_norm": 1.2788265943527222, + "learning_rate": 0.0002, + "loss": 0.5458, + "step": 540 + }, + { + "epoch": 5.670103092783505, + "grad_norm": 0.9921451807022095, + "learning_rate": 0.0002, + "loss": 0.5165, + "step": 550 + }, + { + "epoch": 5.77319587628866, + "grad_norm": 0.9654388427734375, + "learning_rate": 0.0002, + "loss": 0.5557, + "step": 560 + }, + { + "epoch": 5.876288659793815, + "grad_norm": 1.203700065612793, + "learning_rate": 0.0002, + "loss": 0.5468, + "step": 570 + }, + { + "epoch": 5.979381443298969, + "grad_norm": 1.0011067390441895, + "learning_rate": 0.0002, + "loss": 0.5596, + "step": 580 + }, + { + "epoch": 6.0, + "eval_loss": 1.6636911630630493, + "eval_runtime": 25.0718, + "eval_samples_per_second": 3.909, + "eval_steps_per_second": 0.519, + "step": 582 + }, + { + "epoch": 6.082474226804123, + "grad_norm": 1.3850897550582886, + "learning_rate": 0.0002, + "loss": 0.4129, + "step": 590 + }, + { + "epoch": 6.185567010309279, + "grad_norm": 1.2155243158340454, + "learning_rate": 0.0002, + "loss": 0.3656, + "step": 600 + }, + { + "epoch": 6.288659793814433, + "grad_norm": 1.149451494216919, + "learning_rate": 0.0002, + "loss": 0.3775, + "step": 610 + }, + { + "epoch": 6.391752577319588, + "grad_norm": 1.4000080823898315, + "learning_rate": 0.0002, + "loss": 0.4071, + "step": 620 + }, + { + "epoch": 6.494845360824742, + "grad_norm": 1.2047293186187744, + "learning_rate": 0.0002, + "loss": 0.3944, + "step": 630 + }, + { + "epoch": 6.597938144329897, + "grad_norm": 1.3094227313995361, + "learning_rate": 0.0002, + "loss": 0.4172, + "step": 640 + }, + { + "epoch": 6.701030927835052, + "grad_norm": 1.1890202760696411, + "learning_rate": 0.0002, + "loss": 0.4205, + "step": 650 + }, + { + "epoch": 6.804123711340206, + "grad_norm": 1.053261637687683, + "learning_rate": 0.0002, + "loss": 0.3944, + "step": 660 + }, + { + "epoch": 6.907216494845361, + "grad_norm": 1.2590222358703613, + "learning_rate": 0.0002, + "loss": 0.4419, + "step": 670 + }, + { + "epoch": 7.0, + "eval_loss": 1.7902696132659912, + "eval_runtime": 24.9138, + "eval_samples_per_second": 3.934, + "eval_steps_per_second": 0.522, + "step": 679 + }, + { + "epoch": 7.010309278350515, + "grad_norm": 0.8764763474464417, + "learning_rate": 0.0002, + "loss": 0.4379, + "step": 680 + }, + { + "epoch": 7.11340206185567, + "grad_norm": 1.3551478385925293, + "learning_rate": 0.0002, + "loss": 0.2885, + "step": 690 + }, + { + "epoch": 7.216494845360825, + "grad_norm": 1.3741779327392578, + "learning_rate": 0.0002, + "loss": 0.2866, + "step": 700 + }, + { + "epoch": 7.319587628865979, + "grad_norm": 1.2713068723678589, + "learning_rate": 0.0002, + "loss": 0.3048, + "step": 710 + }, + { + "epoch": 7.422680412371134, + "grad_norm": 1.341278314590454, + "learning_rate": 0.0002, + "loss": 0.3065, + "step": 720 + }, + { + "epoch": 7.525773195876289, + "grad_norm": 1.2904815673828125, + "learning_rate": 0.0002, + "loss": 0.3214, + "step": 730 + }, + { + "epoch": 7.628865979381443, + "grad_norm": 1.3972225189208984, + "learning_rate": 0.0002, + "loss": 0.3169, + "step": 740 + }, + { + "epoch": 7.731958762886598, + "grad_norm": 1.1128023862838745, + "learning_rate": 0.0002, + "loss": 0.3374, + "step": 750 + }, + { + "epoch": 7.835051546391752, + "grad_norm": 1.3514678478240967, + "learning_rate": 0.0002, + "loss": 0.3285, + "step": 760 + }, + { + "epoch": 7.938144329896907, + "grad_norm": 1.2585015296936035, + "learning_rate": 0.0002, + "loss": 0.3263, + "step": 770 + }, + { + "epoch": 8.0, + "eval_loss": 2.042968273162842, + "eval_runtime": 24.8647, + "eval_samples_per_second": 3.941, + "eval_steps_per_second": 0.523, + "step": 776 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 3.985826660745216e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-776/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/README.md b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/README.md new file mode 100644 index 0000000000000000000000000000000000000000..503a34a03e25483aa99213835fd87bfc8289a3fe --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.13.1 \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/adapter_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e98db163734cc03f7a8f8b3f720d3a2befdf7453 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/adapter_config.json @@ -0,0 +1,29 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 32, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/adapter_model.safetensors b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..280ce0f97d198a82abead3c96b81fe481bde5bee --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcba5bf3e6ce2025f2204351e471a00fff18578d6f5225429f6f58de464daa41 +size 143153376 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/optimizer.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4e64da80499926d13977a9c704507d34ab82419 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c5fe057c1bad7d2a41c4c1317b3da9ee0526d42fa749c689ca8f3b8c1f7e4fc +size 72886458 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/rng_state.pth b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3df5a48996db367f19a37dc3d542bc9785eceaa --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64ba8a6ad5bad380525bc3eebb15e6342746cbb274e4066dc9a4b9e01cf6df5 +size 14244 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/scheduler.pt b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e39dbf40e6c17b0ed0f5edc57ebb19ce407ef97 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec63c921cadfde903806c6417bfb326435a1cad877da8cc71aa6032f773130b0 +size 1064 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/trainer_state.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..3fc83825b806d516d05afbbf924aa28763b2dd21 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/trainer_state.json @@ -0,0 +1,104 @@ +{ + "best_metric": 1.2023634910583496, + "best_model_checkpoint": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97", + "epoch": 1.0, + "eval_steps": 10, + "global_step": 97, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.10309278350515463, + "grad_norm": 0.4288032054901123, + "learning_rate": 0.0002, + "loss": 2.2176, + "step": 10 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.7525845170021057, + "learning_rate": 0.0002, + "loss": 1.7102, + "step": 20 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.366604208946228, + "learning_rate": 0.0002, + "loss": 1.354, + "step": 30 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.35952436923980713, + "learning_rate": 0.0002, + "loss": 1.3155, + "step": 40 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.3427760899066925, + "learning_rate": 0.0002, + "loss": 1.2403, + "step": 50 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.35099881887435913, + "learning_rate": 0.0002, + "loss": 1.238, + "step": 60 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.30796730518341064, + "learning_rate": 0.0002, + "loss": 1.2201, + "step": 70 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.37101054191589355, + "learning_rate": 0.0002, + "loss": 1.2433, + "step": 80 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.37658801674842834, + "learning_rate": 0.0002, + "loss": 1.2536, + "step": 90 + }, + { + "epoch": 1.0, + "eval_loss": 1.2023634910583496, + "eval_runtime": 24.9372, + "eval_samples_per_second": 3.93, + "eval_steps_per_second": 0.521, + "step": 97 + } + ], + "logging_steps": 10, + "max_steps": 776, + "num_input_tokens_seen": 0, + "num_train_epochs": 8, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4982283325931520.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/special_tokens_map.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0acb52c84d6ea33178bee426ec6706bfba8ba637 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.model b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer_config.json b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1aa249f4dc9f84e87ad8983458e7800ae5bf5454 --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/training_args.bin b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe96056efb01e0cbf39aad87fd835edb0158cb8e --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70103afaee8068b7fa7c504c73ce03f49d6e78317b794a86aec3e13d61f9eded +size 5560 diff --git a/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/training_log.jsonl b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/training_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a4d8b3eb0ab9678dd403c7198c7cfcfbf6ac139f --- /dev/null +++ b/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/training_log.jsonl @@ -0,0 +1,15 @@ +{"epoch": 1.0, "step": 97, "epoch_duration": 387.46892261505127, "total_accumulated_duration": 387.46892261505127, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 11696.9921875}, "avg_memory_reserved": {"GPU_0": 12758.0}, "peak_memory_reserved": {"GPU_0": 12758.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "N/A", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}]} +{"epoch": 2.0, "step": 194, "epoch_duration": 338.79733538627625, "total_accumulated_duration": 677.517591714859, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}]} +{"epoch": 2.0, "step": 194, "epoch_duration": 384.63939142227173, "total_accumulated_duration": 772.108314037323, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-97", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}]} +{"epoch": 3.0, "step": 291, "epoch_duration": 338.79183435440063, "total_accumulated_duration": 1016.3094260692596, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1784135103225708, "eval_runtime": 22.2253, "eval_samples_per_second": 4.409, "eval_steps_per_second": 0.585, "epoch": 2.0, "step": 194}, {"loss": 1.0539, "grad_norm": 0.4118919372558594, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.937, "grad_norm": 0.4499684274196625, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9578, "grad_norm": 0.44620391726493835, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9723, "grad_norm": 0.5299099683761597, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9839, "grad_norm": 0.7105165719985962, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9746, "grad_norm": 0.55884850025177, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9885, "grad_norm": 0.5572164058685303, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0038, "grad_norm": 0.6684932708740234, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9797, "grad_norm": 0.6159946918487549, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.025, "grad_norm": 0.49401140213012695, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}]} +{"epoch": 3.0, "step": 291, "epoch_duration": 387.6328454017639, "total_accumulated_duration": 1159.741159439087, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1786428689956665, "eval_runtime": 24.6076, "eval_samples_per_second": 3.983, "eval_steps_per_second": 0.528, "epoch": 2.0, "step": 194}, {"loss": 1.053, "grad_norm": 0.4016205370426178, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.9378, "grad_norm": 0.4537462592124939, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9556, "grad_norm": 0.43585601449012756, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9689, "grad_norm": 0.5386906862258911, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9812, "grad_norm": 0.722528874874115, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9751, "grad_norm": 0.5693188309669495, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9881, "grad_norm": 0.5479232668876648, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0062, "grad_norm": 0.6799434423446655, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9774, "grad_norm": 0.6431379318237305, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.0239, "grad_norm": 0.49573859572410583, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}]} +{"epoch": 4.0, "step": 388, "epoch_duration": 339.47233986854553, "total_accumulated_duration": 1355.7817659378052, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1784135103225708, "eval_runtime": 22.2253, "eval_samples_per_second": 4.409, "eval_steps_per_second": 0.585, "epoch": 2.0, "step": 194}, {"loss": 1.0539, "grad_norm": 0.4118919372558594, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.937, "grad_norm": 0.4499684274196625, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9578, "grad_norm": 0.44620391726493835, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9723, "grad_norm": 0.5299099683761597, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9839, "grad_norm": 0.7105165719985962, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9746, "grad_norm": 0.55884850025177, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9885, "grad_norm": 0.5572164058685303, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0038, "grad_norm": 0.6684932708740234, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9797, "grad_norm": 0.6159946918487549, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.025, "grad_norm": 0.49401140213012695, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2017087936401367, "eval_runtime": 22.4466, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 3.0, "step": 291}, {"loss": 0.8631, "grad_norm": 0.8370884656906128, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8656013607978821, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8203, "grad_norm": 0.7293992042541504, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8426, "grad_norm": 0.9495164155960083, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8274, "grad_norm": 0.7297559976577759, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7962, "grad_norm": 0.8207106590270996, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8467, "grad_norm": 0.8857038021087646, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.8256, "grad_norm": 0.6602361798286438, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8188, "grad_norm": 0.7537974715232849, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}]} +{"epoch": 4.0, "step": 388, "epoch_duration": 320.2340507507324, "total_accumulated_duration": 1479.9752101898193, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1786428689956665, "eval_runtime": 24.6076, "eval_samples_per_second": 3.983, "eval_steps_per_second": 0.528, "epoch": 2.0, "step": 194}, {"loss": 1.053, "grad_norm": 0.4016205370426178, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.9378, "grad_norm": 0.4537462592124939, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9556, "grad_norm": 0.43585601449012756, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9689, "grad_norm": 0.5386906862258911, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9812, "grad_norm": 0.722528874874115, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9751, "grad_norm": 0.5693188309669495, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9881, "grad_norm": 0.5479232668876648, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0062, "grad_norm": 0.6799434423446655, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9774, "grad_norm": 0.6431379318237305, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.0239, "grad_norm": 0.49573859572410583, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2014847993850708, "eval_runtime": 24.8828, "eval_samples_per_second": 3.938, "eval_steps_per_second": 0.522, "epoch": 3.0, "step": 291}, {"loss": 0.8643, "grad_norm": 0.8711708784103394, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8786052465438843, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8154, "grad_norm": 0.6987330913543701, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8414, "grad_norm": 0.9661340713500977, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8318, "grad_norm": 0.7045658230781555, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7918, "grad_norm": 0.7941751480102539, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8477, "grad_norm": 0.8815844655036926, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.828, "grad_norm": 0.6258918046951294, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8173, "grad_norm": 0.7246745228767395, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}]} +{"epoch": 5.0, "step": 485, "epoch_duration": 338.69260811805725, "total_accumulated_duration": 1694.4743740558624, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1784135103225708, "eval_runtime": 22.2253, "eval_samples_per_second": 4.409, "eval_steps_per_second": 0.585, "epoch": 2.0, "step": 194}, {"loss": 1.0539, "grad_norm": 0.4118919372558594, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.937, "grad_norm": 0.4499684274196625, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9578, "grad_norm": 0.44620391726493835, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9723, "grad_norm": 0.5299099683761597, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9839, "grad_norm": 0.7105165719985962, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9746, "grad_norm": 0.55884850025177, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9885, "grad_norm": 0.5572164058685303, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0038, "grad_norm": 0.6684932708740234, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9797, "grad_norm": 0.6159946918487549, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.025, "grad_norm": 0.49401140213012695, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2017087936401367, "eval_runtime": 22.4466, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 3.0, "step": 291}, {"loss": 0.8631, "grad_norm": 0.8370884656906128, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8656013607978821, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8203, "grad_norm": 0.7293992042541504, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8426, "grad_norm": 0.9495164155960083, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8274, "grad_norm": 0.7297559976577759, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7962, "grad_norm": 0.8207106590270996, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8467, "grad_norm": 0.8857038021087646, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.8256, "grad_norm": 0.6602361798286438, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8188, "grad_norm": 0.7537974715232849, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2891193628311157, "eval_runtime": 22.4452, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 4.0, "step": 388}, {"loss": 0.8255, "grad_norm": 0.7143073081970215, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6763, "grad_norm": 0.9357417821884155, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6579, "grad_norm": 1.178428053855896, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6855, "grad_norm": 0.9423320293426514, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6489, "grad_norm": 1.144408106803894, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.6721, "grad_norm": 0.7632341980934143, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6656, "grad_norm": 0.8697758316993713, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6762, "grad_norm": 0.7262584567070007, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7136, "grad_norm": 0.8023588061332703, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6611, "grad_norm": 0.8013685941696167, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}]} +{"epoch": 5.0, "step": 485, "epoch_duration": 274.53032088279724, "total_accumulated_duration": 1754.5055310726166, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1786428689956665, "eval_runtime": 24.6076, "eval_samples_per_second": 3.983, "eval_steps_per_second": 0.528, "epoch": 2.0, "step": 194}, {"loss": 1.053, "grad_norm": 0.4016205370426178, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.9378, "grad_norm": 0.4537462592124939, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9556, "grad_norm": 0.43585601449012756, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9689, "grad_norm": 0.5386906862258911, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9812, "grad_norm": 0.722528874874115, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9751, "grad_norm": 0.5693188309669495, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9881, "grad_norm": 0.5479232668876648, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0062, "grad_norm": 0.6799434423446655, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9774, "grad_norm": 0.6431379318237305, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.0239, "grad_norm": 0.49573859572410583, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2014847993850708, "eval_runtime": 24.8828, "eval_samples_per_second": 3.938, "eval_steps_per_second": 0.522, "epoch": 3.0, "step": 291}, {"loss": 0.8643, "grad_norm": 0.8711708784103394, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8786052465438843, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8154, "grad_norm": 0.6987330913543701, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8414, "grad_norm": 0.9661340713500977, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8318, "grad_norm": 0.7045658230781555, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7918, "grad_norm": 0.7941751480102539, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8477, "grad_norm": 0.8815844655036926, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.828, "grad_norm": 0.6258918046951294, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8173, "grad_norm": 0.7246745228767395, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2927078008651733, "eval_runtime": 10.5547, "eval_samples_per_second": 9.285, "eval_steps_per_second": 1.232, "epoch": 4.0, "step": 388}, {"loss": 0.8201, "grad_norm": 0.725050151348114, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6623, "grad_norm": 1.0035908222198486, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6517, "grad_norm": 1.2170008420944214, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6769, "grad_norm": 1.0720841884613037, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6536, "grad_norm": 1.0538380146026611, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.676, "grad_norm": 0.7770849466323853, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6632, "grad_norm": 0.9066935777664185, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6738, "grad_norm": 0.7707642912864685, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7144, "grad_norm": 0.8185567855834961, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6495, "grad_norm": 0.9264892339706421, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}]} +{"epoch": 6.0, "step": 582, "epoch_duration": 339.1646935939789, "total_accumulated_duration": 2033.6390676498413, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1784135103225708, "eval_runtime": 22.2253, "eval_samples_per_second": 4.409, "eval_steps_per_second": 0.585, "epoch": 2.0, "step": 194}, {"loss": 1.0539, "grad_norm": 0.4118919372558594, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.937, "grad_norm": 0.4499684274196625, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9578, "grad_norm": 0.44620391726493835, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9723, "grad_norm": 0.5299099683761597, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9839, "grad_norm": 0.7105165719985962, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9746, "grad_norm": 0.55884850025177, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9885, "grad_norm": 0.5572164058685303, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0038, "grad_norm": 0.6684932708740234, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9797, "grad_norm": 0.6159946918487549, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.025, "grad_norm": 0.49401140213012695, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2017087936401367, "eval_runtime": 22.4466, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 3.0, "step": 291}, {"loss": 0.8631, "grad_norm": 0.8370884656906128, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8656013607978821, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8203, "grad_norm": 0.7293992042541504, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8426, "grad_norm": 0.9495164155960083, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8274, "grad_norm": 0.7297559976577759, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7962, "grad_norm": 0.8207106590270996, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8467, "grad_norm": 0.8857038021087646, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.8256, "grad_norm": 0.6602361798286438, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8188, "grad_norm": 0.7537974715232849, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2891193628311157, "eval_runtime": 22.4452, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 4.0, "step": 388}, {"loss": 0.8255, "grad_norm": 0.7143073081970215, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6763, "grad_norm": 0.9357417821884155, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6579, "grad_norm": 1.178428053855896, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6855, "grad_norm": 0.9423320293426514, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6489, "grad_norm": 1.144408106803894, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.6721, "grad_norm": 0.7632341980934143, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6656, "grad_norm": 0.8697758316993713, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6762, "grad_norm": 0.7262584567070007, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7136, "grad_norm": 0.8023588061332703, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6611, "grad_norm": 0.8013685941696167, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}, {"eval_loss": 1.4029510021209717, "eval_runtime": 22.3419, "eval_samples_per_second": 4.386, "eval_steps_per_second": 0.582, "epoch": 5.0, "step": 485}, {"loss": 0.6311, "grad_norm": 1.0058369636535645, "learning_rate": 0.0002, "epoch": 5.051546391752577, "step": 490}, {"loss": 0.5504, "grad_norm": 1.2407437562942505, "learning_rate": 0.0002, "epoch": 5.154639175257732, "step": 500}, {"loss": 0.5039, "grad_norm": 1.7065143585205078, "learning_rate": 0.0002, "epoch": 5.257731958762887, "step": 510}, {"loss": 0.5177, "grad_norm": 1.3471814393997192, "learning_rate": 0.0002, "epoch": 5.360824742268041, "step": 520}, {"loss": 0.5002, "grad_norm": 1.0459239482879639, "learning_rate": 0.0002, "epoch": 5.463917525773196, "step": 530}, {"loss": 0.5436, "grad_norm": 1.1456974744796753, "learning_rate": 0.0002, "epoch": 5.56701030927835, "step": 540}, {"loss": 0.5217, "grad_norm": 0.9514049291610718, "learning_rate": 0.0002, "epoch": 5.670103092783505, "step": 550}, {"loss": 0.5565, "grad_norm": 0.9391697645187378, "learning_rate": 0.0002, "epoch": 5.77319587628866, "step": 560}, {"loss": 0.5608, "grad_norm": 1.2081618309020996, "learning_rate": 0.0002, "epoch": 5.876288659793815, "step": 570}, {"loss": 0.5706, "grad_norm": 0.9605330228805542, "learning_rate": 0.0002, "epoch": 5.979381443298969, "step": 580}]} +{"epoch": 6.0, "step": 582, "epoch_duration": 389.2548403739929, "total_accumulated_duration": 2143.7603714466095, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1786428689956665, "eval_runtime": 24.6076, "eval_samples_per_second": 3.983, "eval_steps_per_second": 0.528, "epoch": 2.0, "step": 194}, {"loss": 1.053, "grad_norm": 0.4016205370426178, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.9378, "grad_norm": 0.4537462592124939, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9556, "grad_norm": 0.43585601449012756, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9689, "grad_norm": 0.5386906862258911, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9812, "grad_norm": 0.722528874874115, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9751, "grad_norm": 0.5693188309669495, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9881, "grad_norm": 0.5479232668876648, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0062, "grad_norm": 0.6799434423446655, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9774, "grad_norm": 0.6431379318237305, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.0239, "grad_norm": 0.49573859572410583, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2014847993850708, "eval_runtime": 24.8828, "eval_samples_per_second": 3.938, "eval_steps_per_second": 0.522, "epoch": 3.0, "step": 291}, {"loss": 0.8643, "grad_norm": 0.8711708784103394, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8786052465438843, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8154, "grad_norm": 0.6987330913543701, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8414, "grad_norm": 0.9661340713500977, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8318, "grad_norm": 0.7045658230781555, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7918, "grad_norm": 0.7941751480102539, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8477, "grad_norm": 0.8815844655036926, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.828, "grad_norm": 0.6258918046951294, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8173, "grad_norm": 0.7246745228767395, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2927078008651733, "eval_runtime": 10.5547, "eval_samples_per_second": 9.285, "eval_steps_per_second": 1.232, "epoch": 4.0, "step": 388}, {"loss": 0.8201, "grad_norm": 0.725050151348114, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6623, "grad_norm": 1.0035908222198486, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6517, "grad_norm": 1.2170008420944214, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6769, "grad_norm": 1.0720841884613037, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6536, "grad_norm": 1.0538380146026611, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.676, "grad_norm": 0.7770849466323853, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6632, "grad_norm": 0.9066935777664185, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6738, "grad_norm": 0.7707642912864685, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7144, "grad_norm": 0.8185567855834961, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6495, "grad_norm": 0.9264892339706421, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}, {"eval_loss": 1.3918720483779907, "eval_runtime": 24.8943, "eval_samples_per_second": 3.937, "eval_steps_per_second": 0.522, "epoch": 5.0, "step": 485}, {"loss": 0.6318, "grad_norm": 1.0677416324615479, "learning_rate": 0.0002, "epoch": 5.051546391752577, "step": 490}, {"loss": 0.5416, "grad_norm": 1.1246110200881958, "learning_rate": 0.0002, "epoch": 5.154639175257732, "step": 500}, {"loss": 0.4953, "grad_norm": 1.4362645149230957, "learning_rate": 0.0002, "epoch": 5.257731958762887, "step": 510}, {"loss": 0.5098, "grad_norm": 1.143323540687561, "learning_rate": 0.0002, "epoch": 5.360824742268041, "step": 520}, {"loss": 0.4947, "grad_norm": 1.1483081579208374, "learning_rate": 0.0002, "epoch": 5.463917525773196, "step": 530}, {"loss": 0.5458, "grad_norm": 1.2788265943527222, "learning_rate": 0.0002, "epoch": 5.56701030927835, "step": 540}, {"loss": 0.5165, "grad_norm": 0.9921451807022095, "learning_rate": 0.0002, "epoch": 5.670103092783505, "step": 550}, {"loss": 0.5557, "grad_norm": 0.9654388427734375, "learning_rate": 0.0002, "epoch": 5.77319587628866, "step": 560}, {"loss": 0.5468, "grad_norm": 1.203700065612793, "learning_rate": 0.0002, "epoch": 5.876288659793815, "step": 570}, {"loss": 0.5596, "grad_norm": 1.0011067390441895, "learning_rate": 0.0002, "epoch": 5.979381443298969, "step": 580}]} +{"epoch": 7.0, "step": 679, "epoch_duration": 339.3658721446991, "total_accumulated_duration": 2373.0049397945404, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1784135103225708, "eval_runtime": 22.2253, "eval_samples_per_second": 4.409, "eval_steps_per_second": 0.585, "epoch": 2.0, "step": 194}, {"loss": 1.0539, "grad_norm": 0.4118919372558594, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.937, "grad_norm": 0.4499684274196625, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9578, "grad_norm": 0.44620391726493835, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9723, "grad_norm": 0.5299099683761597, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9839, "grad_norm": 0.7105165719985962, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9746, "grad_norm": 0.55884850025177, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9885, "grad_norm": 0.5572164058685303, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0038, "grad_norm": 0.6684932708740234, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9797, "grad_norm": 0.6159946918487549, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.025, "grad_norm": 0.49401140213012695, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2017087936401367, "eval_runtime": 22.4466, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 3.0, "step": 291}, {"loss": 0.8631, "grad_norm": 0.8370884656906128, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8656013607978821, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8203, "grad_norm": 0.7293992042541504, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8426, "grad_norm": 0.9495164155960083, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8274, "grad_norm": 0.7297559976577759, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7962, "grad_norm": 0.8207106590270996, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8467, "grad_norm": 0.8857038021087646, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.8256, "grad_norm": 0.6602361798286438, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8188, "grad_norm": 0.7537974715232849, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2891193628311157, "eval_runtime": 22.4452, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 4.0, "step": 388}, {"loss": 0.8255, "grad_norm": 0.7143073081970215, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6763, "grad_norm": 0.9357417821884155, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6579, "grad_norm": 1.178428053855896, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6855, "grad_norm": 0.9423320293426514, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6489, "grad_norm": 1.144408106803894, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.6721, "grad_norm": 0.7632341980934143, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6656, "grad_norm": 0.8697758316993713, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6762, "grad_norm": 0.7262584567070007, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7136, "grad_norm": 0.8023588061332703, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6611, "grad_norm": 0.8013685941696167, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}, {"eval_loss": 1.4029510021209717, "eval_runtime": 22.3419, "eval_samples_per_second": 4.386, "eval_steps_per_second": 0.582, "epoch": 5.0, "step": 485}, {"loss": 0.6311, "grad_norm": 1.0058369636535645, "learning_rate": 0.0002, "epoch": 5.051546391752577, "step": 490}, {"loss": 0.5504, "grad_norm": 1.2407437562942505, "learning_rate": 0.0002, "epoch": 5.154639175257732, "step": 500}, {"loss": 0.5039, "grad_norm": 1.7065143585205078, "learning_rate": 0.0002, "epoch": 5.257731958762887, "step": 510}, {"loss": 0.5177, "grad_norm": 1.3471814393997192, "learning_rate": 0.0002, "epoch": 5.360824742268041, "step": 520}, {"loss": 0.5002, "grad_norm": 1.0459239482879639, "learning_rate": 0.0002, "epoch": 5.463917525773196, "step": 530}, {"loss": 0.5436, "grad_norm": 1.1456974744796753, "learning_rate": 0.0002, "epoch": 5.56701030927835, "step": 540}, {"loss": 0.5217, "grad_norm": 0.9514049291610718, "learning_rate": 0.0002, "epoch": 5.670103092783505, "step": 550}, {"loss": 0.5565, "grad_norm": 0.9391697645187378, "learning_rate": 0.0002, "epoch": 5.77319587628866, "step": 560}, {"loss": 0.5608, "grad_norm": 1.2081618309020996, "learning_rate": 0.0002, "epoch": 5.876288659793815, "step": 570}, {"loss": 0.5706, "grad_norm": 0.9605330228805542, "learning_rate": 0.0002, "epoch": 5.979381443298969, "step": 580}, {"eval_loss": 1.6101187467575073, "eval_runtime": 22.3681, "eval_samples_per_second": 4.381, "eval_steps_per_second": 0.581, "epoch": 6.0, "step": 582}, {"loss": 0.4236, "grad_norm": 1.5738919973373413, "learning_rate": 0.0002, "epoch": 6.082474226804123, "step": 590}, {"loss": 0.3765, "grad_norm": 1.0564768314361572, "learning_rate": 0.0002, "epoch": 6.185567010309279, "step": 600}, {"loss": 0.3882, "grad_norm": 1.140144944190979, "learning_rate": 0.0002, "epoch": 6.288659793814433, "step": 610}, {"loss": 0.4132, "grad_norm": 1.3245387077331543, "learning_rate": 0.0002, "epoch": 6.391752577319588, "step": 620}, {"loss": 0.3983, "grad_norm": 1.4748698472976685, "learning_rate": 0.0002, "epoch": 6.494845360824742, "step": 630}, {"loss": 0.4325, "grad_norm": 1.2935385704040527, "learning_rate": 0.0002, "epoch": 6.597938144329897, "step": 640}, {"loss": 0.4159, "grad_norm": 1.351747751235962, "learning_rate": 0.0002, "epoch": 6.701030927835052, "step": 650}, {"loss": 0.3904, "grad_norm": 1.1485822200775146, "learning_rate": 0.0002, "epoch": 6.804123711340206, "step": 660}, {"loss": 0.4495, "grad_norm": 1.2450836896896362, "learning_rate": 0.0002, "epoch": 6.907216494845361, "step": 670}]} +{"epoch": 7.0, "step": 679, "epoch_duration": 388.99473118782043, "total_accumulated_duration": 2532.75510263443, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1786428689956665, "eval_runtime": 24.6076, "eval_samples_per_second": 3.983, "eval_steps_per_second": 0.528, "epoch": 2.0, "step": 194}, {"loss": 1.053, "grad_norm": 0.4016205370426178, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.9378, "grad_norm": 0.4537462592124939, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9556, "grad_norm": 0.43585601449012756, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9689, "grad_norm": 0.5386906862258911, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9812, "grad_norm": 0.722528874874115, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9751, "grad_norm": 0.5693188309669495, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9881, "grad_norm": 0.5479232668876648, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0062, "grad_norm": 0.6799434423446655, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9774, "grad_norm": 0.6431379318237305, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.0239, "grad_norm": 0.49573859572410583, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2014847993850708, "eval_runtime": 24.8828, "eval_samples_per_second": 3.938, "eval_steps_per_second": 0.522, "epoch": 3.0, "step": 291}, {"loss": 0.8643, "grad_norm": 0.8711708784103394, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8786052465438843, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8154, "grad_norm": 0.6987330913543701, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8414, "grad_norm": 0.9661340713500977, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8318, "grad_norm": 0.7045658230781555, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7918, "grad_norm": 0.7941751480102539, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8477, "grad_norm": 0.8815844655036926, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.828, "grad_norm": 0.6258918046951294, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8173, "grad_norm": 0.7246745228767395, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2927078008651733, "eval_runtime": 10.5547, "eval_samples_per_second": 9.285, "eval_steps_per_second": 1.232, "epoch": 4.0, "step": 388}, {"loss": 0.8201, "grad_norm": 0.725050151348114, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6623, "grad_norm": 1.0035908222198486, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6517, "grad_norm": 1.2170008420944214, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6769, "grad_norm": 1.0720841884613037, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6536, "grad_norm": 1.0538380146026611, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.676, "grad_norm": 0.7770849466323853, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6632, "grad_norm": 0.9066935777664185, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6738, "grad_norm": 0.7707642912864685, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7144, "grad_norm": 0.8185567855834961, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6495, "grad_norm": 0.9264892339706421, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}, {"eval_loss": 1.3918720483779907, "eval_runtime": 24.8943, "eval_samples_per_second": 3.937, "eval_steps_per_second": 0.522, "epoch": 5.0, "step": 485}, {"loss": 0.6318, "grad_norm": 1.0677416324615479, "learning_rate": 0.0002, "epoch": 5.051546391752577, "step": 490}, {"loss": 0.5416, "grad_norm": 1.1246110200881958, "learning_rate": 0.0002, "epoch": 5.154639175257732, "step": 500}, {"loss": 0.4953, "grad_norm": 1.4362645149230957, "learning_rate": 0.0002, "epoch": 5.257731958762887, "step": 510}, {"loss": 0.5098, "grad_norm": 1.143323540687561, "learning_rate": 0.0002, "epoch": 5.360824742268041, "step": 520}, {"loss": 0.4947, "grad_norm": 1.1483081579208374, "learning_rate": 0.0002, "epoch": 5.463917525773196, "step": 530}, {"loss": 0.5458, "grad_norm": 1.2788265943527222, "learning_rate": 0.0002, "epoch": 5.56701030927835, "step": 540}, {"loss": 0.5165, "grad_norm": 0.9921451807022095, "learning_rate": 0.0002, "epoch": 5.670103092783505, "step": 550}, {"loss": 0.5557, "grad_norm": 0.9654388427734375, "learning_rate": 0.0002, "epoch": 5.77319587628866, "step": 560}, {"loss": 0.5468, "grad_norm": 1.203700065612793, "learning_rate": 0.0002, "epoch": 5.876288659793815, "step": 570}, {"loss": 0.5596, "grad_norm": 1.0011067390441895, "learning_rate": 0.0002, "epoch": 5.979381443298969, "step": 580}, {"eval_loss": 1.6636911630630493, "eval_runtime": 25.0718, "eval_samples_per_second": 3.909, "eval_steps_per_second": 0.519, "epoch": 6.0, "step": 582}, {"loss": 0.4129, "grad_norm": 1.3850897550582886, "learning_rate": 0.0002, "epoch": 6.082474226804123, "step": 590}, {"loss": 0.3656, "grad_norm": 1.2155243158340454, "learning_rate": 0.0002, "epoch": 6.185567010309279, "step": 600}, {"loss": 0.3775, "grad_norm": 1.149451494216919, "learning_rate": 0.0002, "epoch": 6.288659793814433, "step": 610}, {"loss": 0.4071, "grad_norm": 1.4000080823898315, "learning_rate": 0.0002, "epoch": 6.391752577319588, "step": 620}, {"loss": 0.3944, "grad_norm": 1.2047293186187744, "learning_rate": 0.0002, "epoch": 6.494845360824742, "step": 630}, {"loss": 0.4172, "grad_norm": 1.3094227313995361, "learning_rate": 0.0002, "epoch": 6.597938144329897, "step": 640}, {"loss": 0.4205, "grad_norm": 1.1890202760696411, "learning_rate": 0.0002, "epoch": 6.701030927835052, "step": 650}, {"loss": 0.3944, "grad_norm": 1.053261637687683, "learning_rate": 0.0002, "epoch": 6.804123711340206, "step": 660}, {"loss": 0.4419, "grad_norm": 1.2590222358703613, "learning_rate": 0.0002, "epoch": 6.907216494845361, "step": 670}]} +{"epoch": 8.0, "step": 776, "epoch_duration": 285.29743933677673, "total_accumulated_duration": 2658.302379131317, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2174, "grad_norm": 0.4293819069862366, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7086, "grad_norm": 0.6495404839515686, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.3572, "grad_norm": 0.36839163303375244, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.317, "grad_norm": 0.3564961850643158, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2426, "grad_norm": 0.34568995237350464, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.2412, "grad_norm": 0.3361806869506836, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2235, "grad_norm": 0.30453819036483765, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.241, "grad_norm": 0.373199462890625, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2538, "grad_norm": 0.36725056171417236, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2026004791259766, "eval_runtime": 22.5286, "eval_samples_per_second": 4.35, "eval_steps_per_second": 0.577, "epoch": 1.0, "step": 97}, {"loss": 1.202, "grad_norm": 0.38232314586639404, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1248, "grad_norm": 0.33309781551361084, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0785, "grad_norm": 0.4665461778640747, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.46367886662483215, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1258, "grad_norm": 0.41917818784713745, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1306, "grad_norm": 0.447079062461853, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1165, "grad_norm": 0.3947353661060333, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0843, "grad_norm": 0.40281942486763, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1537, "grad_norm": 0.47708961367607117, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1179, "grad_norm": 0.4026329815387726, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1784135103225708, "eval_runtime": 22.2253, "eval_samples_per_second": 4.409, "eval_steps_per_second": 0.585, "epoch": 2.0, "step": 194}, {"loss": 1.0539, "grad_norm": 0.4118919372558594, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.937, "grad_norm": 0.4499684274196625, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9578, "grad_norm": 0.44620391726493835, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9723, "grad_norm": 0.5299099683761597, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9839, "grad_norm": 0.7105165719985962, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9746, "grad_norm": 0.55884850025177, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9885, "grad_norm": 0.5572164058685303, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0038, "grad_norm": 0.6684932708740234, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9797, "grad_norm": 0.6159946918487549, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.025, "grad_norm": 0.49401140213012695, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2017087936401367, "eval_runtime": 22.4466, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 3.0, "step": 291}, {"loss": 0.8631, "grad_norm": 0.8370884656906128, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8656013607978821, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8203, "grad_norm": 0.7293992042541504, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8426, "grad_norm": 0.9495164155960083, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8274, "grad_norm": 0.7297559976577759, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7962, "grad_norm": 0.8207106590270996, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8467, "grad_norm": 0.8857038021087646, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.8256, "grad_norm": 0.6602361798286438, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8188, "grad_norm": 0.7537974715232849, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2891193628311157, "eval_runtime": 22.4452, "eval_samples_per_second": 4.366, "eval_steps_per_second": 0.579, "epoch": 4.0, "step": 388}, {"loss": 0.8255, "grad_norm": 0.7143073081970215, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6763, "grad_norm": 0.9357417821884155, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6579, "grad_norm": 1.178428053855896, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6855, "grad_norm": 0.9423320293426514, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6489, "grad_norm": 1.144408106803894, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.6721, "grad_norm": 0.7632341980934143, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6656, "grad_norm": 0.8697758316993713, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6762, "grad_norm": 0.7262584567070007, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7136, "grad_norm": 0.8023588061332703, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6611, "grad_norm": 0.8013685941696167, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}, {"eval_loss": 1.4029510021209717, "eval_runtime": 22.3419, "eval_samples_per_second": 4.386, "eval_steps_per_second": 0.582, "epoch": 5.0, "step": 485}, {"loss": 0.6311, "grad_norm": 1.0058369636535645, "learning_rate": 0.0002, "epoch": 5.051546391752577, "step": 490}, {"loss": 0.5504, "grad_norm": 1.2407437562942505, "learning_rate": 0.0002, "epoch": 5.154639175257732, "step": 500}, {"loss": 0.5039, "grad_norm": 1.7065143585205078, "learning_rate": 0.0002, "epoch": 5.257731958762887, "step": 510}, {"loss": 0.5177, "grad_norm": 1.3471814393997192, "learning_rate": 0.0002, "epoch": 5.360824742268041, "step": 520}, {"loss": 0.5002, "grad_norm": 1.0459239482879639, "learning_rate": 0.0002, "epoch": 5.463917525773196, "step": 530}, {"loss": 0.5436, "grad_norm": 1.1456974744796753, "learning_rate": 0.0002, "epoch": 5.56701030927835, "step": 540}, {"loss": 0.5217, "grad_norm": 0.9514049291610718, "learning_rate": 0.0002, "epoch": 5.670103092783505, "step": 550}, {"loss": 0.5565, "grad_norm": 0.9391697645187378, "learning_rate": 0.0002, "epoch": 5.77319587628866, "step": 560}, {"loss": 0.5608, "grad_norm": 1.2081618309020996, "learning_rate": 0.0002, "epoch": 5.876288659793815, "step": 570}, {"loss": 0.5706, "grad_norm": 0.9605330228805542, "learning_rate": 0.0002, "epoch": 5.979381443298969, "step": 580}, {"eval_loss": 1.6101187467575073, "eval_runtime": 22.3681, "eval_samples_per_second": 4.381, "eval_steps_per_second": 0.581, "epoch": 6.0, "step": 582}, {"loss": 0.4236, "grad_norm": 1.5738919973373413, "learning_rate": 0.0002, "epoch": 6.082474226804123, "step": 590}, {"loss": 0.3765, "grad_norm": 1.0564768314361572, "learning_rate": 0.0002, "epoch": 6.185567010309279, "step": 600}, {"loss": 0.3882, "grad_norm": 1.140144944190979, "learning_rate": 0.0002, "epoch": 6.288659793814433, "step": 610}, {"loss": 0.4132, "grad_norm": 1.3245387077331543, "learning_rate": 0.0002, "epoch": 6.391752577319588, "step": 620}, {"loss": 0.3983, "grad_norm": 1.4748698472976685, "learning_rate": 0.0002, "epoch": 6.494845360824742, "step": 630}, {"loss": 0.4325, "grad_norm": 1.2935385704040527, "learning_rate": 0.0002, "epoch": 6.597938144329897, "step": 640}, {"loss": 0.4159, "grad_norm": 1.351747751235962, "learning_rate": 0.0002, "epoch": 6.701030927835052, "step": 650}, {"loss": 0.3904, "grad_norm": 1.1485822200775146, "learning_rate": 0.0002, "epoch": 6.804123711340206, "step": 660}, {"loss": 0.4495, "grad_norm": 1.2450836896896362, "learning_rate": 0.0002, "epoch": 6.907216494845361, "step": 670}, {"eval_loss": 1.8123016357421875, "eval_runtime": 22.3641, "eval_samples_per_second": 4.382, "eval_steps_per_second": 0.581, "epoch": 7.0, "step": 679}, {"loss": 0.4447, "grad_norm": 0.8435681462287903, "learning_rate": 0.0002, "epoch": 7.010309278350515, "step": 680}, {"loss": 0.2921, "grad_norm": 1.6475778818130493, "learning_rate": 0.0002, "epoch": 7.11340206185567, "step": 690}, {"loss": 0.2851, "grad_norm": 1.3725197315216064, "learning_rate": 0.0002, "epoch": 7.216494845360825, "step": 700}, {"loss": 0.301, "grad_norm": 1.2913514375686646, "learning_rate": 0.0002, "epoch": 7.319587628865979, "step": 710}, {"loss": 0.3118, "grad_norm": 1.6019424200057983, "learning_rate": 0.0002, "epoch": 7.422680412371134, "step": 720}, {"loss": 0.3393, "grad_norm": 1.1962944269180298, "learning_rate": 0.0002, "epoch": 7.525773195876289, "step": 730}, {"loss": 0.3354, "grad_norm": 1.1493802070617676, "learning_rate": 0.0002, "epoch": 7.628865979381443, "step": 740}, {"loss": 0.3515, "grad_norm": 1.0846710205078125, "learning_rate": 0.0002, "epoch": 7.731958762886598, "step": 750}, {"loss": 0.3391, "grad_norm": 1.6179533004760742, "learning_rate": 0.0002, "epoch": 7.835051546391752, "step": 760}, {"loss": 0.3315, "grad_norm": 1.2175886631011963, "learning_rate": 0.0002, "epoch": 7.938144329896907, "step": 770}]} +{"epoch": 8.0, "step": 776, "epoch_duration": 388.5511484146118, "total_accumulated_duration": 2921.3062510490417, "gpu_info": {"GPU_0": "NVIDIA A100-PCIE-40GB"}, "memory_usage": {"avg_memory_usage": {"GPU_0": 7751.47119140625}, "peak_memory_usage": {"GPU_0": 19860.22314453125}, "avg_memory_reserved": {"GPU_0": 24486.0}, "peak_memory_reserved": {"GPU_0": 24752.0}, "total_memory": {"GPU_0": 40444.375}}, "best_checkpoint_path": "outputs-001/gemma-2-9b-it_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-1550-sd-42/checkpoint-194", "params": {"epochs": 8, "batch_size": 1, "learning_rate": 0.0002, "gradient_accumulation_steps": 2, "warmup_ratio": 0.03, "max_grad_norm": 0.3, "lora_alpha": 32, "lora_dropout": 0.05, "lora_r": 64, "tf32": true, "seed": 42}, "log_history": [{"loss": 2.2176, "grad_norm": 0.4288032054901123, "learning_rate": 0.0002, "epoch": 0.10309278350515463, "step": 10}, {"loss": 1.7102, "grad_norm": 0.7525845170021057, "learning_rate": 0.0002, "epoch": 0.20618556701030927, "step": 20}, {"loss": 1.354, "grad_norm": 0.366604208946228, "learning_rate": 0.0002, "epoch": 0.30927835051546393, "step": 30}, {"loss": 1.3155, "grad_norm": 0.35952436923980713, "learning_rate": 0.0002, "epoch": 0.41237113402061853, "step": 40}, {"loss": 1.2403, "grad_norm": 0.3427760899066925, "learning_rate": 0.0002, "epoch": 0.5154639175257731, "step": 50}, {"loss": 1.238, "grad_norm": 0.35099881887435913, "learning_rate": 0.0002, "epoch": 0.6185567010309279, "step": 60}, {"loss": 1.2201, "grad_norm": 0.30796730518341064, "learning_rate": 0.0002, "epoch": 0.7216494845360825, "step": 70}, {"loss": 1.2433, "grad_norm": 0.37101054191589355, "learning_rate": 0.0002, "epoch": 0.8247422680412371, "step": 80}, {"loss": 1.2536, "grad_norm": 0.37658801674842834, "learning_rate": 0.0002, "epoch": 0.9278350515463918, "step": 90}, {"eval_loss": 1.2023634910583496, "eval_runtime": 24.9372, "eval_samples_per_second": 3.93, "eval_steps_per_second": 0.521, "epoch": 1.0, "step": 97}, {"loss": 1.2027, "grad_norm": 0.39316999912261963, "learning_rate": 0.0002, "epoch": 1.0309278350515463, "step": 100}, {"loss": 1.1257, "grad_norm": 0.34155887365341187, "learning_rate": 0.0002, "epoch": 1.134020618556701, "step": 110}, {"loss": 1.0775, "grad_norm": 0.43475863337516785, "learning_rate": 0.0002, "epoch": 1.2371134020618557, "step": 120}, {"loss": 1.0916, "grad_norm": 0.47940605878829956, "learning_rate": 0.0002, "epoch": 1.3402061855670104, "step": 130}, {"loss": 1.1242, "grad_norm": 0.42031461000442505, "learning_rate": 0.0002, "epoch": 1.443298969072165, "step": 140}, {"loss": 1.1327, "grad_norm": 0.45062679052352905, "learning_rate": 0.0002, "epoch": 1.5463917525773194, "step": 150}, {"loss": 1.1186, "grad_norm": 0.39917513728141785, "learning_rate": 0.0002, "epoch": 1.6494845360824741, "step": 160}, {"loss": 1.0824, "grad_norm": 0.4017351567745209, "learning_rate": 0.0002, "epoch": 1.7525773195876289, "step": 170}, {"loss": 1.1553, "grad_norm": 0.4676169157028198, "learning_rate": 0.0002, "epoch": 1.8556701030927836, "step": 180}, {"loss": 1.1191, "grad_norm": 0.4058385491371155, "learning_rate": 0.0002, "epoch": 1.9587628865979383, "step": 190}, {"eval_loss": 1.1786428689956665, "eval_runtime": 24.6076, "eval_samples_per_second": 3.983, "eval_steps_per_second": 0.528, "epoch": 2.0, "step": 194}, {"loss": 1.053, "grad_norm": 0.4016205370426178, "learning_rate": 0.0002, "epoch": 2.0618556701030926, "step": 200}, {"loss": 0.9378, "grad_norm": 0.4537462592124939, "learning_rate": 0.0002, "epoch": 2.1649484536082473, "step": 210}, {"loss": 0.9556, "grad_norm": 0.43585601449012756, "learning_rate": 0.0002, "epoch": 2.268041237113402, "step": 220}, {"loss": 0.9689, "grad_norm": 0.5386906862258911, "learning_rate": 0.0002, "epoch": 2.3711340206185567, "step": 230}, {"loss": 0.9812, "grad_norm": 0.722528874874115, "learning_rate": 0.0002, "epoch": 2.4742268041237114, "step": 240}, {"loss": 0.9751, "grad_norm": 0.5693188309669495, "learning_rate": 0.0002, "epoch": 2.5773195876288657, "step": 250}, {"loss": 0.9881, "grad_norm": 0.5479232668876648, "learning_rate": 0.0002, "epoch": 2.680412371134021, "step": 260}, {"loss": 1.0062, "grad_norm": 0.6799434423446655, "learning_rate": 0.0002, "epoch": 2.783505154639175, "step": 270}, {"loss": 0.9774, "grad_norm": 0.6431379318237305, "learning_rate": 0.0002, "epoch": 2.88659793814433, "step": 280}, {"loss": 1.0239, "grad_norm": 0.49573859572410583, "learning_rate": 0.0002, "epoch": 2.9896907216494846, "step": 290}, {"eval_loss": 1.2014847993850708, "eval_runtime": 24.8828, "eval_samples_per_second": 3.938, "eval_steps_per_second": 0.522, "epoch": 3.0, "step": 291}, {"loss": 0.8643, "grad_norm": 0.8711708784103394, "learning_rate": 0.0002, "epoch": 3.0927835051546393, "step": 300}, {"loss": 0.8139, "grad_norm": 0.8786052465438843, "learning_rate": 0.0002, "epoch": 3.195876288659794, "step": 310}, {"loss": 0.8154, "grad_norm": 0.6987330913543701, "learning_rate": 0.0002, "epoch": 3.2989690721649483, "step": 320}, {"loss": 0.8414, "grad_norm": 0.9661340713500977, "learning_rate": 0.0002, "epoch": 3.402061855670103, "step": 330}, {"loss": 0.8318, "grad_norm": 0.7045658230781555, "learning_rate": 0.0002, "epoch": 3.5051546391752577, "step": 340}, {"loss": 0.7918, "grad_norm": 0.7941751480102539, "learning_rate": 0.0002, "epoch": 3.6082474226804124, "step": 350}, {"loss": 0.8477, "grad_norm": 0.8815844655036926, "learning_rate": 0.0002, "epoch": 3.711340206185567, "step": 360}, {"loss": 0.828, "grad_norm": 0.6258918046951294, "learning_rate": 0.0002, "epoch": 3.8144329896907214, "step": 370}, {"loss": 0.8173, "grad_norm": 0.7246745228767395, "learning_rate": 0.0002, "epoch": 3.917525773195876, "step": 380}, {"eval_loss": 1.2927078008651733, "eval_runtime": 10.5547, "eval_samples_per_second": 9.285, "eval_steps_per_second": 1.232, "epoch": 4.0, "step": 388}, {"loss": 0.8201, "grad_norm": 0.725050151348114, "learning_rate": 0.0002, "epoch": 4.020618556701031, "step": 390}, {"loss": 0.6623, "grad_norm": 1.0035908222198486, "learning_rate": 0.0002, "epoch": 4.123711340206185, "step": 400}, {"loss": 0.6517, "grad_norm": 1.2170008420944214, "learning_rate": 0.0002, "epoch": 4.22680412371134, "step": 410}, {"loss": 0.6769, "grad_norm": 1.0720841884613037, "learning_rate": 0.0002, "epoch": 4.329896907216495, "step": 420}, {"loss": 0.6536, "grad_norm": 1.0538380146026611, "learning_rate": 0.0002, "epoch": 4.43298969072165, "step": 430}, {"loss": 0.676, "grad_norm": 0.7770849466323853, "learning_rate": 0.0002, "epoch": 4.536082474226804, "step": 440}, {"loss": 0.6632, "grad_norm": 0.9066935777664185, "learning_rate": 0.0002, "epoch": 4.639175257731958, "step": 450}, {"loss": 0.6738, "grad_norm": 0.7707642912864685, "learning_rate": 0.0002, "epoch": 4.742268041237113, "step": 460}, {"loss": 0.7144, "grad_norm": 0.8185567855834961, "learning_rate": 0.0002, "epoch": 4.845360824742268, "step": 470}, {"loss": 0.6495, "grad_norm": 0.9264892339706421, "learning_rate": 0.0002, "epoch": 4.948453608247423, "step": 480}, {"eval_loss": 1.3918720483779907, "eval_runtime": 24.8943, "eval_samples_per_second": 3.937, "eval_steps_per_second": 0.522, "epoch": 5.0, "step": 485}, {"loss": 0.6318, "grad_norm": 1.0677416324615479, "learning_rate": 0.0002, "epoch": 5.051546391752577, "step": 490}, {"loss": 0.5416, "grad_norm": 1.1246110200881958, "learning_rate": 0.0002, "epoch": 5.154639175257732, "step": 500}, {"loss": 0.4953, "grad_norm": 1.4362645149230957, "learning_rate": 0.0002, "epoch": 5.257731958762887, "step": 510}, {"loss": 0.5098, "grad_norm": 1.143323540687561, "learning_rate": 0.0002, "epoch": 5.360824742268041, "step": 520}, {"loss": 0.4947, "grad_norm": 1.1483081579208374, "learning_rate": 0.0002, "epoch": 5.463917525773196, "step": 530}, {"loss": 0.5458, "grad_norm": 1.2788265943527222, "learning_rate": 0.0002, "epoch": 5.56701030927835, "step": 540}, {"loss": 0.5165, "grad_norm": 0.9921451807022095, "learning_rate": 0.0002, "epoch": 5.670103092783505, "step": 550}, {"loss": 0.5557, "grad_norm": 0.9654388427734375, "learning_rate": 0.0002, "epoch": 5.77319587628866, "step": 560}, {"loss": 0.5468, "grad_norm": 1.203700065612793, "learning_rate": 0.0002, "epoch": 5.876288659793815, "step": 570}, {"loss": 0.5596, "grad_norm": 1.0011067390441895, "learning_rate": 0.0002, "epoch": 5.979381443298969, "step": 580}, {"eval_loss": 1.6636911630630493, "eval_runtime": 25.0718, "eval_samples_per_second": 3.909, "eval_steps_per_second": 0.519, "epoch": 6.0, "step": 582}, {"loss": 0.4129, "grad_norm": 1.3850897550582886, "learning_rate": 0.0002, "epoch": 6.082474226804123, "step": 590}, {"loss": 0.3656, "grad_norm": 1.2155243158340454, "learning_rate": 0.0002, "epoch": 6.185567010309279, "step": 600}, {"loss": 0.3775, "grad_norm": 1.149451494216919, "learning_rate": 0.0002, "epoch": 6.288659793814433, "step": 610}, {"loss": 0.4071, "grad_norm": 1.4000080823898315, "learning_rate": 0.0002, "epoch": 6.391752577319588, "step": 620}, {"loss": 0.3944, "grad_norm": 1.2047293186187744, "learning_rate": 0.0002, "epoch": 6.494845360824742, "step": 630}, {"loss": 0.4172, "grad_norm": 1.3094227313995361, "learning_rate": 0.0002, "epoch": 6.597938144329897, "step": 640}, {"loss": 0.4205, "grad_norm": 1.1890202760696411, "learning_rate": 0.0002, "epoch": 6.701030927835052, "step": 650}, {"loss": 0.3944, "grad_norm": 1.053261637687683, "learning_rate": 0.0002, "epoch": 6.804123711340206, "step": 660}, {"loss": 0.4419, "grad_norm": 1.2590222358703613, "learning_rate": 0.0002, "epoch": 6.907216494845361, "step": 670}, {"eval_loss": 1.7902696132659912, "eval_runtime": 24.9138, "eval_samples_per_second": 3.934, "eval_steps_per_second": 0.522, "epoch": 7.0, "step": 679}, {"loss": 0.4379, "grad_norm": 0.8764763474464417, "learning_rate": 0.0002, "epoch": 7.010309278350515, "step": 680}, {"loss": 0.2885, "grad_norm": 1.3551478385925293, "learning_rate": 0.0002, "epoch": 7.11340206185567, "step": 690}, {"loss": 0.2866, "grad_norm": 1.3741779327392578, "learning_rate": 0.0002, "epoch": 7.216494845360825, "step": 700}, {"loss": 0.3048, "grad_norm": 1.2713068723678589, "learning_rate": 0.0002, "epoch": 7.319587628865979, "step": 710}, {"loss": 0.3065, "grad_norm": 1.341278314590454, "learning_rate": 0.0002, "epoch": 7.422680412371134, "step": 720}, {"loss": 0.3214, "grad_norm": 1.2904815673828125, "learning_rate": 0.0002, "epoch": 7.525773195876289, "step": 730}, {"loss": 0.3169, "grad_norm": 1.3972225189208984, "learning_rate": 0.0002, "epoch": 7.628865979381443, "step": 740}, {"loss": 0.3374, "grad_norm": 1.1128023862838745, "learning_rate": 0.0002, "epoch": 7.731958762886598, "step": 750}, {"loss": 0.3285, "grad_norm": 1.3514678478240967, "learning_rate": 0.0002, "epoch": 7.835051546391752, "step": 760}, {"loss": 0.3263, "grad_norm": 1.2585015296936035, "learning_rate": 0.0002, "epoch": 7.938144329896907, "step": 770}]}