diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..539c81a98a090f8066e42caf8bf61389c76b0aa9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +gemma-2-2B-it-F16-LoRA.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-2b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ce9c5bf666df52c2a0425ad1b5a02251a031eb3b --- /dev/null +++ b/README.md @@ -0,0 +1,28 @@ +--- +language: fr +license: apache-2.0 +tags: + - gemma + - lora + - finetune + - chatbot +base_model: "google/gemma-2-2b-it" +library_name: "Axolotl" +--- + +# Mémé Ginette - LoRA Fine-tuné sur Gemma-2B-IT + +Ce modèle LoRA est un **exercice de fine-tuning** basé sur `google/gemma-2-2b-it` et entraîné avec **Axolotl**. +Le dataset a été **généré avec GPT-4o** et sert uniquement de **test expérimental**. + +## 📌 Détails techniques +- **Modèle de base** : `google/gemma-2-2b-it` +- **Méthode** : `QLoRA` +- **Dataset** : `Généré par GPT-4o pour un exercice de fine-tuning` +- **Format** : `GGUF LoRA` compatible avec `llama.cpp` + +## 🚀 Utilisation rapide +```bash +./llama-cli -m gemma-2-2b-it-Q8_0.gguf \ + --lora-scaled gemma-2-2b-it-LoRA/adapter_model.safetensors 1.0 \ + --mlock -p "Tu es un assistant utile." diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..16d13f2cf4bc5af463a7babc742a43dc76bd0ba6 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-2b-it", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "down_proj", + "gate_proj", + "up_proj", + "k_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d1c8e92a32aa281d46e6e8725b2b5dd6604509e --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a782f63cc9a1b25942cc1b6c6dfb940642b0e5112a44fd0717c078091839ab07 +size 83115256 diff --git a/checkpoint-120/README.md b/checkpoint-120/README.md new file mode 100644 index 0000000000000000000000000000000000000000..016ab2302388dbc76ea25a0c5b903b851ba5f7ef --- /dev/null +++ b/checkpoint-120/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-2b-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 0.14.0 \ No newline at end of file diff --git a/checkpoint-120/adapter_config.json b/checkpoint-120/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..16d13f2cf4bc5af463a7babc742a43dc76bd0ba6 --- /dev/null +++ b/checkpoint-120/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-2b-it", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "down_proj", + "gate_proj", + "up_proj", + "k_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-120/adapter_model.safetensors b/checkpoint-120/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52ce9cb8fd694de5462d371ba999531cc38ec1bf --- /dev/null +++ b/checkpoint-120/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ab96857d351afbe0c84d211de1a7f7f1f1092535e27643ff11258def3b1178 +size 83115256 diff --git a/checkpoint-120/optimizer.pt b/checkpoint-120/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..85e09bc967a90a23b26ade9f847b4338b63535e4 --- /dev/null +++ b/checkpoint-120/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0135872dada26089bb0ef2552d24d1ec017d84c04490143b664d51b7127562 +size 42608388 diff --git a/checkpoint-120/rng_state.pth b/checkpoint-120/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..00c5d1a70fc344c97d54468eb77ffbd7df47dad3 --- /dev/null +++ b/checkpoint-120/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30567345026d8d3d9a038d65c466a16aef0e5cccbf678ad07447c878d5ac1f22 +size 14244 diff --git a/checkpoint-120/scaler.pt b/checkpoint-120/scaler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5a4114bcd107a6f5b8b0b0d1822a481c2b7ae10 --- /dev/null +++ b/checkpoint-120/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578927bb1c801cdd14af41be9b1907db16bd1c7b35d8fc1fc2779e79adb5109e +size 988 diff --git a/checkpoint-120/scheduler.pt b/checkpoint-120/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..06da41c48311e696077ca4b2eba6dec02519a201 --- /dev/null +++ b/checkpoint-120/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c8bf2e1d2af2947b7b96e0f8cd0076fc2d8e0b54a668c4ba97628f9569997c +size 1064 diff --git a/checkpoint-120/special_tokens_map.json b/checkpoint-120/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-120/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "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": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-120/tokenizer.json b/checkpoint-120/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-120/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-120/tokenizer.model b/checkpoint-120/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-120/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-120/tokenizer_config.json b/checkpoint-120/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f363b51b217d3edc09ff81b12d5eda8d4039d5b6 --- /dev/null +++ b/checkpoint-120/tokenizer_config.json @@ -0,0 +1,2014 @@ +{ + "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": "", + "extra_special_tokens": {}, + "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/checkpoint-120/trainer_state.json b/checkpoint-120/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..92c1342796bf770c8a96b028cd72ed58fb4b0a67 --- /dev/null +++ b/checkpoint-120/trainer_state.json @@ -0,0 +1,453 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 120, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.016666666666666666, + "grad_norm": 4.380008697509766, + "learning_rate": 8.333333333333334e-06, + "loss": 3.8472, + "step": 2 + }, + { + "epoch": 0.03333333333333333, + "grad_norm": 5.4320220947265625, + "learning_rate": 1.6666666666666667e-05, + "loss": 4.4355, + "step": 4 + }, + { + "epoch": 0.05, + "grad_norm": 5.495668411254883, + "learning_rate": 2.5e-05, + "loss": 4.0183, + "step": 6 + }, + { + "epoch": 0.06666666666666667, + "grad_norm": 5.333839416503906, + "learning_rate": 3.3333333333333335e-05, + "loss": 4.4543, + "step": 8 + }, + { + "epoch": 0.08333333333333333, + "grad_norm": 4.8141961097717285, + "learning_rate": 4.166666666666667e-05, + "loss": 4.0576, + "step": 10 + }, + { + "epoch": 0.1, + "grad_norm": 4.4542341232299805, + "learning_rate": 5e-05, + "loss": 3.3098, + "step": 12 + }, + { + "epoch": 0.11666666666666667, + "grad_norm": 4.608759880065918, + "learning_rate": 5.833333333333334e-05, + "loss": 3.3983, + "step": 14 + }, + { + "epoch": 0.13333333333333333, + "grad_norm": 3.7876033782958984, + "learning_rate": 6.666666666666667e-05, + "loss": 2.7265, + "step": 16 + }, + { + "epoch": 0.15, + "grad_norm": 4.206045627593994, + "learning_rate": 7.500000000000001e-05, + "loss": 2.4786, + "step": 18 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 4.687928676605225, + "learning_rate": 8.333333333333334e-05, + "loss": 2.2298, + "step": 20 + }, + { + "epoch": 0.18333333333333332, + "grad_norm": 4.639834880828857, + "learning_rate": 9.166666666666667e-05, + "loss": 2.5465, + "step": 22 + }, + { + "epoch": 0.2, + "grad_norm": 4.179326057434082, + "learning_rate": 0.0001, + "loss": 2.0804, + "step": 24 + }, + { + "epoch": 0.21666666666666667, + "grad_norm": 4.4850287437438965, + "learning_rate": 0.00010833333333333333, + "loss": 2.0512, + "step": 26 + }, + { + "epoch": 0.23333333333333334, + "grad_norm": 5.006600379943848, + "learning_rate": 0.00011666666666666668, + "loss": 2.1484, + "step": 28 + }, + { + "epoch": 0.25, + "grad_norm": 4.475966453552246, + "learning_rate": 0.000125, + "loss": 1.9871, + "step": 30 + }, + { + "epoch": 0.26666666666666666, + "grad_norm": 4.605421543121338, + "learning_rate": 0.00013333333333333334, + "loss": 2.1455, + "step": 32 + }, + { + "epoch": 0.2833333333333333, + "grad_norm": 4.921014785766602, + "learning_rate": 0.00014166666666666668, + "loss": 1.9162, + "step": 34 + }, + { + "epoch": 0.3, + "grad_norm": 4.6443634033203125, + "learning_rate": 0.00015000000000000001, + "loss": 2.0503, + "step": 36 + }, + { + "epoch": 0.31666666666666665, + "grad_norm": 4.234635353088379, + "learning_rate": 0.00015833333333333332, + "loss": 2.0901, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 4.628840446472168, + "learning_rate": 0.0001666666666666667, + "loss": 1.8014, + "step": 40 + }, + { + "epoch": 0.35, + "grad_norm": 3.8235278129577637, + "learning_rate": 0.000175, + "loss": 1.8156, + "step": 42 + }, + { + "epoch": 0.36666666666666664, + "grad_norm": 5.939589500427246, + "learning_rate": 0.00018333333333333334, + "loss": 1.7782, + "step": 44 + }, + { + "epoch": 0.38333333333333336, + "grad_norm": 4.921348571777344, + "learning_rate": 0.00019166666666666667, + "loss": 1.7167, + "step": 46 + }, + { + "epoch": 0.4, + "grad_norm": 4.549618244171143, + "learning_rate": 0.0002, + "loss": 2.2041, + "step": 48 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 4.085502624511719, + "learning_rate": 0.00019998942319271077, + "loss": 1.8483, + "step": 50 + }, + { + "epoch": 0.43333333333333335, + "grad_norm": 3.6243653297424316, + "learning_rate": 0.0001999576950082201, + "loss": 2.0321, + "step": 52 + }, + { + "epoch": 0.45, + "grad_norm": 3.530813455581665, + "learning_rate": 0.0001999048221581858, + "loss": 1.819, + "step": 54 + }, + { + "epoch": 0.4666666666666667, + "grad_norm": 3.175443649291992, + "learning_rate": 0.00019983081582712685, + "loss": 1.7011, + "step": 56 + }, + { + "epoch": 0.48333333333333334, + "grad_norm": 3.0620853900909424, + "learning_rate": 0.00019973569167005723, + "loss": 1.6158, + "step": 58 + }, + { + "epoch": 0.5, + "grad_norm": 3.984229564666748, + "learning_rate": 0.00019961946980917456, + "loss": 1.8606, + "step": 60 + }, + { + "epoch": 0.5166666666666667, + "grad_norm": 3.717822313308716, + "learning_rate": 0.0001994821748296033, + "loss": 1.7937, + "step": 62 + }, + { + "epoch": 0.5333333333333333, + "grad_norm": 4.549349308013916, + "learning_rate": 0.00019932383577419432, + "loss": 1.9389, + "step": 64 + }, + { + "epoch": 0.55, + "grad_norm": 4.229006767272949, + "learning_rate": 0.00019914448613738106, + "loss": 1.5434, + "step": 66 + }, + { + "epoch": 0.5666666666666667, + "grad_norm": 3.5755157470703125, + "learning_rate": 0.00019894416385809444, + "loss": 1.6555, + "step": 68 + }, + { + "epoch": 0.5833333333333334, + "grad_norm": 3.2299246788024902, + "learning_rate": 0.00019872291131173742, + "loss": 1.7088, + "step": 70 + }, + { + "epoch": 0.6, + "grad_norm": 3.777369260787964, + "learning_rate": 0.00019848077530122083, + "loss": 1.7569, + "step": 72 + }, + { + "epoch": 0.6166666666666667, + "grad_norm": 3.143406629562378, + "learning_rate": 0.00019821780704706307, + "loss": 1.7495, + "step": 74 + }, + { + "epoch": 0.6333333333333333, + "grad_norm": 3.655970811843872, + "learning_rate": 0.00019793406217655517, + "loss": 1.6553, + "step": 76 + }, + { + "epoch": 0.65, + "grad_norm": 3.4324283599853516, + "learning_rate": 0.00019762960071199333, + "loss": 1.5155, + "step": 78 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 3.7328310012817383, + "learning_rate": 0.00019730448705798239, + "loss": 1.8168, + "step": 80 + }, + { + "epoch": 0.6833333333333333, + "grad_norm": 3.8750150203704834, + "learning_rate": 0.0001969587899878116, + "loss": 1.705, + "step": 82 + }, + { + "epoch": 0.7, + "grad_norm": 4.362231254577637, + "learning_rate": 0.00019659258262890683, + "loss": 1.3282, + "step": 84 + }, + { + "epoch": 0.7166666666666667, + "grad_norm": 3.3029322624206543, + "learning_rate": 0.00019620594244736133, + "loss": 1.4785, + "step": 86 + }, + { + "epoch": 0.7333333333333333, + "grad_norm": 3.272670269012451, + "learning_rate": 0.0001957989512315489, + "loss": 1.7328, + "step": 88 + }, + { + "epoch": 0.75, + "grad_norm": 4.447598457336426, + "learning_rate": 0.0001953716950748227, + "loss": 1.8185, + "step": 90 + }, + { + "epoch": 0.7666666666666667, + "grad_norm": 2.942129373550415, + "learning_rate": 0.0001949242643573034, + "loss": 1.6651, + "step": 92 + }, + { + "epoch": 0.7833333333333333, + "grad_norm": 3.0011799335479736, + "learning_rate": 0.0001944567537267605, + "loss": 1.8555, + "step": 94 + }, + { + "epoch": 0.8, + "grad_norm": 3.2934067249298096, + "learning_rate": 0.00019396926207859084, + "loss": 1.5531, + "step": 96 + }, + { + "epoch": 0.8166666666666667, + "grad_norm": 3.1889824867248535, + "learning_rate": 0.00019346189253489885, + "loss": 1.8412, + "step": 98 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 2.921942949295044, + "learning_rate": 0.00019293475242268223, + "loss": 1.4985, + "step": 100 + }, + { + "epoch": 0.85, + "grad_norm": 3.1884875297546387, + "learning_rate": 0.0001923879532511287, + "loss": 1.5736, + "step": 102 + }, + { + "epoch": 0.8666666666666667, + "grad_norm": 3.4869801998138428, + "learning_rate": 0.00019182161068802741, + "loss": 1.4873, + "step": 104 + }, + { + "epoch": 0.8833333333333333, + "grad_norm": 2.8857343196868896, + "learning_rate": 0.00019123584453530144, + "loss": 1.4827, + "step": 106 + }, + { + "epoch": 0.9, + "grad_norm": 4.214871406555176, + "learning_rate": 0.000190630778703665, + "loss": 1.6214, + "step": 108 + }, + { + "epoch": 0.9166666666666666, + "grad_norm": 3.495774984359741, + "learning_rate": 0.00019000654118641211, + "loss": 1.6193, + "step": 110 + }, + { + "epoch": 0.9333333333333333, + "grad_norm": 3.5762667655944824, + "learning_rate": 0.00018936326403234125, + "loss": 1.5264, + "step": 112 + }, + { + "epoch": 0.95, + "grad_norm": 3.465022563934326, + "learning_rate": 0.00018870108331782217, + "loss": 1.6963, + "step": 114 + }, + { + "epoch": 0.9666666666666667, + "grad_norm": 3.743870973587036, + "learning_rate": 0.00018802013911801112, + "loss": 1.6291, + "step": 116 + }, + { + "epoch": 0.9833333333333333, + "grad_norm": 4.362145900726318, + "learning_rate": 0.0001873205754772196, + "loss": 1.3957, + "step": 118 + }, + { + "epoch": 1.0, + "grad_norm": 3.093210220336914, + "learning_rate": 0.00018660254037844388, + "loss": 1.5895, + "step": 120 + } + ], + "logging_steps": 2, + "max_steps": 480, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 120, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3015894871572480.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-120/training_args.bin b/checkpoint-120/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac8f391c607e66ead5154a805581d756800be5f3 --- /dev/null +++ b/checkpoint-120/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29a6aaefe60e2bc5b7a3cfaa3a6197fc31914ea7b1436562fae6685627aff67 +size 7032 diff --git a/checkpoint-240/README.md b/checkpoint-240/README.md new file mode 100644 index 0000000000000000000000000000000000000000..016ab2302388dbc76ea25a0c5b903b851ba5f7ef --- /dev/null +++ b/checkpoint-240/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-2b-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 0.14.0 \ No newline at end of file diff --git a/checkpoint-240/adapter_config.json b/checkpoint-240/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..16d13f2cf4bc5af463a7babc742a43dc76bd0ba6 --- /dev/null +++ b/checkpoint-240/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-2b-it", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "down_proj", + "gate_proj", + "up_proj", + "k_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-240/adapter_model.safetensors b/checkpoint-240/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe2a3be836b6d9b73001a0c57492f5fb3d0c1d3a --- /dev/null +++ b/checkpoint-240/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc7279af3684f2a758f364bbc2d1b9c9e218933fdec48d0e8e4f47408fcdc61 +size 83115256 diff --git a/checkpoint-240/optimizer.pt b/checkpoint-240/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..167c4f84cb87a9998db46091f14f3f6f150b0efa --- /dev/null +++ b/checkpoint-240/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af5bc438ce06ba555270b29e9000aa06cf4759de0ada46489672f340962bb13 +size 42608388 diff --git a/checkpoint-240/rng_state.pth b/checkpoint-240/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..282f68eff95caa258698628b187a7b07010a540d --- /dev/null +++ b/checkpoint-240/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534d0350cb4e7808f83e0f1746382bb154fa21b17e4dbcabbc3f64a780c9f4b0 +size 14244 diff --git a/checkpoint-240/scaler.pt b/checkpoint-240/scaler.pt new file mode 100644 index 0000000000000000000000000000000000000000..af83120af7c84e2b111e9132de27443e436cd851 --- /dev/null +++ b/checkpoint-240/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954e49954416f70ddf85b757c393ed97d0fad8ec66dadb5d462433cdf0a68a30 +size 988 diff --git a/checkpoint-240/scheduler.pt b/checkpoint-240/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..37cc0dedeab8887981dfa5f2ee1a05605e98054d --- /dev/null +++ b/checkpoint-240/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b449ae96f19e5bb5677233ab58e7d61d5163ff1e5093746d0028150f7a757e2 +size 1064 diff --git a/checkpoint-240/special_tokens_map.json b/checkpoint-240/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-240/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "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": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-240/tokenizer.json b/checkpoint-240/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-240/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-240/tokenizer.model b/checkpoint-240/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-240/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-240/tokenizer_config.json b/checkpoint-240/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f363b51b217d3edc09ff81b12d5eda8d4039d5b6 --- /dev/null +++ b/checkpoint-240/tokenizer_config.json @@ -0,0 +1,2014 @@ +{ + "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": "", + "extra_special_tokens": {}, + "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/checkpoint-240/trainer_state.json b/checkpoint-240/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b4afe54afcdec9f630340aee7a9073fad53d7c37 --- /dev/null +++ b/checkpoint-240/trainer_state.json @@ -0,0 +1,873 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 240, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.016666666666666666, + "grad_norm": 4.380008697509766, + "learning_rate": 8.333333333333334e-06, + "loss": 3.8472, + "step": 2 + }, + { + "epoch": 0.03333333333333333, + "grad_norm": 5.4320220947265625, + "learning_rate": 1.6666666666666667e-05, + "loss": 4.4355, + "step": 4 + }, + { + "epoch": 0.05, + "grad_norm": 5.495668411254883, + "learning_rate": 2.5e-05, + "loss": 4.0183, + "step": 6 + }, + { + "epoch": 0.06666666666666667, + "grad_norm": 5.333839416503906, + "learning_rate": 3.3333333333333335e-05, + "loss": 4.4543, + "step": 8 + }, + { + "epoch": 0.08333333333333333, + "grad_norm": 4.8141961097717285, + "learning_rate": 4.166666666666667e-05, + "loss": 4.0576, + "step": 10 + }, + { + "epoch": 0.1, + "grad_norm": 4.4542341232299805, + "learning_rate": 5e-05, + "loss": 3.3098, + "step": 12 + }, + { + "epoch": 0.11666666666666667, + "grad_norm": 4.608759880065918, + "learning_rate": 5.833333333333334e-05, + "loss": 3.3983, + "step": 14 + }, + { + "epoch": 0.13333333333333333, + "grad_norm": 3.7876033782958984, + "learning_rate": 6.666666666666667e-05, + "loss": 2.7265, + "step": 16 + }, + { + "epoch": 0.15, + "grad_norm": 4.206045627593994, + "learning_rate": 7.500000000000001e-05, + "loss": 2.4786, + "step": 18 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 4.687928676605225, + "learning_rate": 8.333333333333334e-05, + "loss": 2.2298, + "step": 20 + }, + { + "epoch": 0.18333333333333332, + "grad_norm": 4.639834880828857, + "learning_rate": 9.166666666666667e-05, + "loss": 2.5465, + "step": 22 + }, + { + "epoch": 0.2, + "grad_norm": 4.179326057434082, + "learning_rate": 0.0001, + "loss": 2.0804, + "step": 24 + }, + { + "epoch": 0.21666666666666667, + "grad_norm": 4.4850287437438965, + "learning_rate": 0.00010833333333333333, + "loss": 2.0512, + "step": 26 + }, + { + "epoch": 0.23333333333333334, + "grad_norm": 5.006600379943848, + "learning_rate": 0.00011666666666666668, + "loss": 2.1484, + "step": 28 + }, + { + "epoch": 0.25, + "grad_norm": 4.475966453552246, + "learning_rate": 0.000125, + "loss": 1.9871, + "step": 30 + }, + { + "epoch": 0.26666666666666666, + "grad_norm": 4.605421543121338, + "learning_rate": 0.00013333333333333334, + "loss": 2.1455, + "step": 32 + }, + { + "epoch": 0.2833333333333333, + "grad_norm": 4.921014785766602, + "learning_rate": 0.00014166666666666668, + "loss": 1.9162, + "step": 34 + }, + { + "epoch": 0.3, + "grad_norm": 4.6443634033203125, + "learning_rate": 0.00015000000000000001, + "loss": 2.0503, + "step": 36 + }, + { + "epoch": 0.31666666666666665, + "grad_norm": 4.234635353088379, + "learning_rate": 0.00015833333333333332, + "loss": 2.0901, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 4.628840446472168, + "learning_rate": 0.0001666666666666667, + "loss": 1.8014, + "step": 40 + }, + { + "epoch": 0.35, + "grad_norm": 3.8235278129577637, + "learning_rate": 0.000175, + "loss": 1.8156, + "step": 42 + }, + { + "epoch": 0.36666666666666664, + "grad_norm": 5.939589500427246, + "learning_rate": 0.00018333333333333334, + "loss": 1.7782, + "step": 44 + }, + { + "epoch": 0.38333333333333336, + "grad_norm": 4.921348571777344, + "learning_rate": 0.00019166666666666667, + "loss": 1.7167, + "step": 46 + }, + { + "epoch": 0.4, + "grad_norm": 4.549618244171143, + "learning_rate": 0.0002, + "loss": 2.2041, + "step": 48 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 4.085502624511719, + "learning_rate": 0.00019998942319271077, + "loss": 1.8483, + "step": 50 + }, + { + "epoch": 0.43333333333333335, + "grad_norm": 3.6243653297424316, + "learning_rate": 0.0001999576950082201, + "loss": 2.0321, + "step": 52 + }, + { + "epoch": 0.45, + "grad_norm": 3.530813455581665, + "learning_rate": 0.0001999048221581858, + "loss": 1.819, + "step": 54 + }, + { + "epoch": 0.4666666666666667, + "grad_norm": 3.175443649291992, + "learning_rate": 0.00019983081582712685, + "loss": 1.7011, + "step": 56 + }, + { + "epoch": 0.48333333333333334, + "grad_norm": 3.0620853900909424, + "learning_rate": 0.00019973569167005723, + "loss": 1.6158, + "step": 58 + }, + { + "epoch": 0.5, + "grad_norm": 3.984229564666748, + "learning_rate": 0.00019961946980917456, + "loss": 1.8606, + "step": 60 + }, + { + "epoch": 0.5166666666666667, + "grad_norm": 3.717822313308716, + "learning_rate": 0.0001994821748296033, + "loss": 1.7937, + "step": 62 + }, + { + "epoch": 0.5333333333333333, + "grad_norm": 4.549349308013916, + "learning_rate": 0.00019932383577419432, + "loss": 1.9389, + "step": 64 + }, + { + "epoch": 0.55, + "grad_norm": 4.229006767272949, + "learning_rate": 0.00019914448613738106, + "loss": 1.5434, + "step": 66 + }, + { + "epoch": 0.5666666666666667, + "grad_norm": 3.5755157470703125, + "learning_rate": 0.00019894416385809444, + "loss": 1.6555, + "step": 68 + }, + { + "epoch": 0.5833333333333334, + "grad_norm": 3.2299246788024902, + "learning_rate": 0.00019872291131173742, + "loss": 1.7088, + "step": 70 + }, + { + "epoch": 0.6, + "grad_norm": 3.777369260787964, + "learning_rate": 0.00019848077530122083, + "loss": 1.7569, + "step": 72 + }, + { + "epoch": 0.6166666666666667, + "grad_norm": 3.143406629562378, + "learning_rate": 0.00019821780704706307, + "loss": 1.7495, + "step": 74 + }, + { + "epoch": 0.6333333333333333, + "grad_norm": 3.655970811843872, + "learning_rate": 0.00019793406217655517, + "loss": 1.6553, + "step": 76 + }, + { + "epoch": 0.65, + "grad_norm": 3.4324283599853516, + "learning_rate": 0.00019762960071199333, + "loss": 1.5155, + "step": 78 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 3.7328310012817383, + "learning_rate": 0.00019730448705798239, + "loss": 1.8168, + "step": 80 + }, + { + "epoch": 0.6833333333333333, + "grad_norm": 3.8750150203704834, + "learning_rate": 0.0001969587899878116, + "loss": 1.705, + "step": 82 + }, + { + "epoch": 0.7, + "grad_norm": 4.362231254577637, + "learning_rate": 0.00019659258262890683, + "loss": 1.3282, + "step": 84 + }, + { + "epoch": 0.7166666666666667, + "grad_norm": 3.3029322624206543, + "learning_rate": 0.00019620594244736133, + "loss": 1.4785, + "step": 86 + }, + { + "epoch": 0.7333333333333333, + "grad_norm": 3.272670269012451, + "learning_rate": 0.0001957989512315489, + "loss": 1.7328, + "step": 88 + }, + { + "epoch": 0.75, + "grad_norm": 4.447598457336426, + "learning_rate": 0.0001953716950748227, + "loss": 1.8185, + "step": 90 + }, + { + "epoch": 0.7666666666666667, + "grad_norm": 2.942129373550415, + "learning_rate": 0.0001949242643573034, + "loss": 1.6651, + "step": 92 + }, + { + "epoch": 0.7833333333333333, + "grad_norm": 3.0011799335479736, + "learning_rate": 0.0001944567537267605, + "loss": 1.8555, + "step": 94 + }, + { + "epoch": 0.8, + "grad_norm": 3.2934067249298096, + "learning_rate": 0.00019396926207859084, + "loss": 1.5531, + "step": 96 + }, + { + "epoch": 0.8166666666666667, + "grad_norm": 3.1889824867248535, + "learning_rate": 0.00019346189253489885, + "loss": 1.8412, + "step": 98 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 2.921942949295044, + "learning_rate": 0.00019293475242268223, + "loss": 1.4985, + "step": 100 + }, + { + "epoch": 0.85, + "grad_norm": 3.1884875297546387, + "learning_rate": 0.0001923879532511287, + "loss": 1.5736, + "step": 102 + }, + { + "epoch": 0.8666666666666667, + "grad_norm": 3.4869801998138428, + "learning_rate": 0.00019182161068802741, + "loss": 1.4873, + "step": 104 + }, + { + "epoch": 0.8833333333333333, + "grad_norm": 2.8857343196868896, + "learning_rate": 0.00019123584453530144, + "loss": 1.4827, + "step": 106 + }, + { + "epoch": 0.9, + "grad_norm": 4.214871406555176, + "learning_rate": 0.000190630778703665, + "loss": 1.6214, + "step": 108 + }, + { + "epoch": 0.9166666666666666, + "grad_norm": 3.495774984359741, + "learning_rate": 0.00019000654118641211, + "loss": 1.6193, + "step": 110 + }, + { + "epoch": 0.9333333333333333, + "grad_norm": 3.5762667655944824, + "learning_rate": 0.00018936326403234125, + "loss": 1.5264, + "step": 112 + }, + { + "epoch": 0.95, + "grad_norm": 3.465022563934326, + "learning_rate": 0.00018870108331782217, + "loss": 1.6963, + "step": 114 + }, + { + "epoch": 0.9666666666666667, + "grad_norm": 3.743870973587036, + "learning_rate": 0.00018802013911801112, + "loss": 1.6291, + "step": 116 + }, + { + "epoch": 0.9833333333333333, + "grad_norm": 4.362145900726318, + "learning_rate": 0.0001873205754772196, + "loss": 1.3957, + "step": 118 + }, + { + "epoch": 1.0, + "grad_norm": 3.093210220336914, + "learning_rate": 0.00018660254037844388, + "loss": 1.5895, + "step": 120 + }, + { + "epoch": 1.0166666666666666, + "grad_norm": 3.2383241653442383, + "learning_rate": 0.00018586618571206134, + "loss": 1.1764, + "step": 122 + }, + { + "epoch": 1.0333333333333334, + "grad_norm": 3.522508144378662, + "learning_rate": 0.00018511166724369997, + "loss": 1.225, + "step": 124 + }, + { + "epoch": 1.05, + "grad_norm": 2.7789227962493896, + "learning_rate": 0.0001843391445812886, + "loss": 1.0999, + "step": 126 + }, + { + "epoch": 1.0666666666666667, + "grad_norm": 3.2942252159118652, + "learning_rate": 0.00018354878114129367, + "loss": 1.1459, + "step": 128 + }, + { + "epoch": 1.0833333333333333, + "grad_norm": 3.0693302154541016, + "learning_rate": 0.00018274074411415105, + "loss": 1.0881, + "step": 130 + }, + { + "epoch": 1.1, + "grad_norm": NaN, + "learning_rate": 0.00018233015127566807, + "loss": 1.2143, + "step": 132 + }, + { + "epoch": 1.1166666666666667, + "grad_norm": 3.5694239139556885, + "learning_rate": 0.0001814959255181988, + "loss": 0.9691, + "step": 134 + }, + { + "epoch": 1.1333333333333333, + "grad_norm": 3.9906177520751953, + "learning_rate": 0.00018064446042674828, + "loss": 1.1584, + "step": 136 + }, + { + "epoch": 1.15, + "grad_norm": 3.965775966644287, + "learning_rate": 0.00017977593611696015, + "loss": 0.985, + "step": 138 + }, + { + "epoch": 1.1666666666666667, + "grad_norm": 5.350390911102295, + "learning_rate": 0.00017889053631311947, + "loss": 1.3574, + "step": 140 + }, + { + "epoch": 1.1833333333333333, + "grad_norm": 3.8706905841827393, + "learning_rate": 0.00017798844830928817, + "loss": 1.159, + "step": 142 + }, + { + "epoch": 1.2, + "grad_norm": 3.463747024536133, + "learning_rate": 0.00017706986292968582, + "loss": 1.046, + "step": 144 + }, + { + "epoch": 1.2166666666666668, + "grad_norm": 3.620864152908325, + "learning_rate": 0.00017613497448832312, + "loss": 0.9971, + "step": 146 + }, + { + "epoch": 1.2333333333333334, + "grad_norm": 3.640916347503662, + "learning_rate": 0.00017518398074789775, + "loss": 0.8718, + "step": 148 + }, + { + "epoch": 1.25, + "grad_norm": 3.4872817993164062, + "learning_rate": 0.00017421708287796017, + "loss": 1.1691, + "step": 150 + }, + { + "epoch": 1.2666666666666666, + "grad_norm": 4.584655284881592, + "learning_rate": 0.00017323448541235924, + "loss": 1.1967, + "step": 152 + }, + { + "epoch": 1.2833333333333332, + "grad_norm": 3.5487728118896484, + "learning_rate": 0.00017223639620597556, + "loss": 1.0054, + "step": 154 + }, + { + "epoch": 1.3, + "grad_norm": 5.228781223297119, + "learning_rate": 0.0001712230263907531, + "loss": 1.4971, + "step": 156 + }, + { + "epoch": 1.3166666666666667, + "grad_norm": 3.641235828399658, + "learning_rate": 0.00017019459033103682, + "loss": 0.8541, + "step": 158 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 3.952843427658081, + "learning_rate": 0.00016915130557822695, + "loss": 0.9685, + "step": 160 + }, + { + "epoch": 1.35, + "grad_norm": 3.3446860313415527, + "learning_rate": 0.00016809339282475904, + "loss": 0.7522, + "step": 162 + }, + { + "epoch": 1.3666666666666667, + "grad_norm": 2.8159420490264893, + "learning_rate": 0.0001670210758574196, + "loss": 0.7398, + "step": 164 + }, + { + "epoch": 1.3833333333333333, + "grad_norm": 4.205153942108154, + "learning_rate": 0.00016593458151000688, + "loss": 1.1048, + "step": 166 + }, + { + "epoch": 1.4, + "grad_norm": 3.777249336242676, + "learning_rate": 0.00016483413961534762, + "loss": 1.0596, + "step": 168 + }, + { + "epoch": 1.4166666666666667, + "grad_norm": 4.2157440185546875, + "learning_rate": 0.00016371998295667886, + "loss": 0.8744, + "step": 170 + }, + { + "epoch": 1.4333333333333333, + "grad_norm": 5.198025703430176, + "learning_rate": 0.00016259234721840591, + "loss": 1.1068, + "step": 172 + }, + { + "epoch": 1.45, + "grad_norm": 4.17173957824707, + "learning_rate": 0.00016145147093624677, + "loss": 0.7444, + "step": 174 + }, + { + "epoch": 1.4666666666666668, + "grad_norm": 5.4046311378479, + "learning_rate": 0.00016029759544677297, + "loss": 1.0724, + "step": 176 + }, + { + "epoch": 1.4833333333333334, + "grad_norm": 3.2475147247314453, + "learning_rate": 0.00015913096483635824, + "loss": 0.9882, + "step": 178 + }, + { + "epoch": 1.5, + "grad_norm": 3.927030324935913, + "learning_rate": 0.0001579518258895455, + "loss": 0.7172, + "step": 180 + }, + { + "epoch": 1.5166666666666666, + "grad_norm": 3.783529758453369, + "learning_rate": 0.00015676042803684288, + "loss": 1.117, + "step": 182 + }, + { + "epoch": 1.5333333333333332, + "grad_norm": 4.151139736175537, + "learning_rate": 0.00015555702330196023, + "loss": 0.8876, + "step": 184 + }, + { + "epoch": 1.55, + "grad_norm": 4.858468055725098, + "learning_rate": 0.000154341866248497, + "loss": 0.818, + "step": 186 + }, + { + "epoch": 1.5666666666666667, + "grad_norm": 5.292931079864502, + "learning_rate": 0.00015311521392609282, + "loss": 1.1459, + "step": 188 + }, + { + "epoch": 1.5833333333333335, + "grad_norm": 5.330478668212891, + "learning_rate": 0.00015187732581605217, + "loss": 1.1276, + "step": 190 + }, + { + "epoch": 1.6, + "grad_norm": 4.155002117156982, + "learning_rate": 0.00015062846377645475, + "loss": 1.0617, + "step": 192 + }, + { + "epoch": 1.6166666666666667, + "grad_norm": 4.212536334991455, + "learning_rate": 0.00014936889198676303, + "loss": 0.7472, + "step": 194 + }, + { + "epoch": 1.6333333333333333, + "grad_norm": 3.7566754817962646, + "learning_rate": 0.00014809887689193877, + "loss": 1.1331, + "step": 196 + }, + { + "epoch": 1.65, + "grad_norm": 3.677277088165283, + "learning_rate": 0.0001468186871460802, + "loss": 0.7747, + "step": 198 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.946069717407227, + "learning_rate": 0.00014552859355559204, + "loss": 1.333, + "step": 200 + }, + { + "epoch": 1.6833333333333333, + "grad_norm": 4.023520469665527, + "learning_rate": 0.00014422886902190014, + "loss": 0.8673, + "step": 202 + }, + { + "epoch": 1.7, + "grad_norm": 3.5782713890075684, + "learning_rate": 0.00014291978848372293, + "loss": 0.8761, + "step": 204 + }, + { + "epoch": 1.7166666666666668, + "grad_norm": 2.9059038162231445, + "learning_rate": 0.00014160162885891193, + "loss": 0.7392, + "step": 206 + }, + { + "epoch": 1.7333333333333334, + "grad_norm": 4.512781143188477, + "learning_rate": 0.00014027466898587374, + "loss": 1.0393, + "step": 208 + }, + { + "epoch": 1.75, + "grad_norm": 4.064301013946533, + "learning_rate": 0.00013893918956458552, + "loss": 1.1425, + "step": 210 + }, + { + "epoch": 1.7666666666666666, + "grad_norm": 3.854093313217163, + "learning_rate": 0.0001375954730972168, + "loss": 0.8584, + "step": 212 + }, + { + "epoch": 1.7833333333333332, + "grad_norm": 4.655716896057129, + "learning_rate": 0.00013624380382837016, + "loss": 1.0068, + "step": 214 + }, + { + "epoch": 1.8, + "grad_norm": 4.099919319152832, + "learning_rate": 0.0001348844676849531, + "loss": 1.0037, + "step": 216 + }, + { + "epoch": 1.8166666666666667, + "grad_norm": 4.197730541229248, + "learning_rate": 0.00013351775221569415, + "loss": 0.9886, + "step": 218 + }, + { + "epoch": 1.8333333333333335, + "grad_norm": 4.721825122833252, + "learning_rate": 0.00013214394653031616, + "loss": 0.7593, + "step": 220 + }, + { + "epoch": 1.85, + "grad_norm": 3.716853618621826, + "learning_rate": 0.00013076334123837883, + "loss": 1.0082, + "step": 222 + }, + { + "epoch": 1.8666666666666667, + "grad_norm": 3.670105218887329, + "learning_rate": 0.00012937622838780444, + "loss": 1.0315, + "step": 224 + }, + { + "epoch": 1.8833333333333333, + "grad_norm": 4.269951343536377, + "learning_rate": 0.00012798290140309923, + "loss": 0.8955, + "step": 226 + }, + { + "epoch": 1.9, + "grad_norm": 3.60205078125, + "learning_rate": 0.0001265836550232833, + "loss": 1.1489, + "step": 228 + }, + { + "epoch": 1.9166666666666665, + "grad_norm": 3.538810968399048, + "learning_rate": 0.00012517878523954286, + "loss": 0.799, + "step": 230 + }, + { + "epoch": 1.9333333333333333, + "grad_norm": 4.749423980712891, + "learning_rate": 0.00012376858923261733, + "loss": 1.1039, + "step": 232 + }, + { + "epoch": 1.95, + "grad_norm": 4.193479537963867, + "learning_rate": 0.00012235336530993474, + "loss": 0.8296, + "step": 234 + }, + { + "epoch": 1.9666666666666668, + "grad_norm": 4.116739273071289, + "learning_rate": 0.0001209334128425092, + "loss": 1.0921, + "step": 236 + }, + { + "epoch": 1.9833333333333334, + "grad_norm": 4.641618728637695, + "learning_rate": 0.00011950903220161285, + "loss": 1.0626, + "step": 238 + }, + { + "epoch": 2.0, + "grad_norm": 3.8030502796173096, + "learning_rate": 0.00011808052469523654, + "loss": 0.8727, + "step": 240 + } + ], + "logging_steps": 2, + "max_steps": 480, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 120, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6031789743144960.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-240/training_args.bin b/checkpoint-240/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac8f391c607e66ead5154a805581d756800be5f3 --- /dev/null +++ b/checkpoint-240/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29a6aaefe60e2bc5b7a3cfaa3a6197fc31914ea7b1436562fae6685627aff67 +size 7032 diff --git a/checkpoint-360/README.md b/checkpoint-360/README.md new file mode 100644 index 0000000000000000000000000000000000000000..016ab2302388dbc76ea25a0c5b903b851ba5f7ef --- /dev/null +++ b/checkpoint-360/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-2b-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 0.14.0 \ No newline at end of file diff --git a/checkpoint-360/adapter_config.json b/checkpoint-360/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..16d13f2cf4bc5af463a7babc742a43dc76bd0ba6 --- /dev/null +++ b/checkpoint-360/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-2b-it", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "down_proj", + "gate_proj", + "up_proj", + "k_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-360/adapter_model.safetensors b/checkpoint-360/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fda9ffe172a9ce02b544fb5e4e70f154cd71f4be --- /dev/null +++ b/checkpoint-360/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fda4b1974a62d51f90ff23e88a3f662fcc6b7efea2704017cf5b212fafff8b6 +size 83115256 diff --git a/checkpoint-360/optimizer.pt b/checkpoint-360/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec91a67bfcd34e8f57b65815e64fb5b5448e1c80 --- /dev/null +++ b/checkpoint-360/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea537a557dc5c0ea3f9f3d645c5a51734d282a409fd073e785e247852facb4fb +size 42608772 diff --git a/checkpoint-360/rng_state.pth b/checkpoint-360/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce7436a7b6646c32030c7182fcac221ec095f1d2 --- /dev/null +++ b/checkpoint-360/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ff124fbe27ac8e3773837caf6998ba66f67e1ff82ff48c38047396e235a474 +size 14244 diff --git a/checkpoint-360/scaler.pt b/checkpoint-360/scaler.pt new file mode 100644 index 0000000000000000000000000000000000000000..58765636a9b64f4d4d4619cbf3e2ebd117bff014 --- /dev/null +++ b/checkpoint-360/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8afff1606f4bc266a86bc4b3050c567a951f228440e11a5af6c4ac950c742aa9 +size 988 diff --git a/checkpoint-360/scheduler.pt b/checkpoint-360/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..afa5b5e9f109bc3320f1527b1f841de11b46ade8 --- /dev/null +++ b/checkpoint-360/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de67fdd4979adc3fcf534fc76d1d61e7c8dce66e9f6aff6878be7cfae69aa1e +size 1064 diff --git a/checkpoint-360/special_tokens_map.json b/checkpoint-360/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-360/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "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": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-360/tokenizer.json b/checkpoint-360/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-360/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-360/tokenizer.model b/checkpoint-360/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-360/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-360/tokenizer_config.json b/checkpoint-360/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f363b51b217d3edc09ff81b12d5eda8d4039d5b6 --- /dev/null +++ b/checkpoint-360/tokenizer_config.json @@ -0,0 +1,2014 @@ +{ + "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": "", + "extra_special_tokens": {}, + "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/checkpoint-360/trainer_state.json b/checkpoint-360/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f238b74939074743aefd18ca2b855e8aae0979bf --- /dev/null +++ b/checkpoint-360/trainer_state.json @@ -0,0 +1,1293 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 360, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.016666666666666666, + "grad_norm": 4.380008697509766, + "learning_rate": 8.333333333333334e-06, + "loss": 3.8472, + "step": 2 + }, + { + "epoch": 0.03333333333333333, + "grad_norm": 5.4320220947265625, + "learning_rate": 1.6666666666666667e-05, + "loss": 4.4355, + "step": 4 + }, + { + "epoch": 0.05, + "grad_norm": 5.495668411254883, + "learning_rate": 2.5e-05, + "loss": 4.0183, + "step": 6 + }, + { + "epoch": 0.06666666666666667, + "grad_norm": 5.333839416503906, + "learning_rate": 3.3333333333333335e-05, + "loss": 4.4543, + "step": 8 + }, + { + "epoch": 0.08333333333333333, + "grad_norm": 4.8141961097717285, + "learning_rate": 4.166666666666667e-05, + "loss": 4.0576, + "step": 10 + }, + { + "epoch": 0.1, + "grad_norm": 4.4542341232299805, + "learning_rate": 5e-05, + "loss": 3.3098, + "step": 12 + }, + { + "epoch": 0.11666666666666667, + "grad_norm": 4.608759880065918, + "learning_rate": 5.833333333333334e-05, + "loss": 3.3983, + "step": 14 + }, + { + "epoch": 0.13333333333333333, + "grad_norm": 3.7876033782958984, + "learning_rate": 6.666666666666667e-05, + "loss": 2.7265, + "step": 16 + }, + { + "epoch": 0.15, + "grad_norm": 4.206045627593994, + "learning_rate": 7.500000000000001e-05, + "loss": 2.4786, + "step": 18 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 4.687928676605225, + "learning_rate": 8.333333333333334e-05, + "loss": 2.2298, + "step": 20 + }, + { + "epoch": 0.18333333333333332, + "grad_norm": 4.639834880828857, + "learning_rate": 9.166666666666667e-05, + "loss": 2.5465, + "step": 22 + }, + { + "epoch": 0.2, + "grad_norm": 4.179326057434082, + "learning_rate": 0.0001, + "loss": 2.0804, + "step": 24 + }, + { + "epoch": 0.21666666666666667, + "grad_norm": 4.4850287437438965, + "learning_rate": 0.00010833333333333333, + "loss": 2.0512, + "step": 26 + }, + { + "epoch": 0.23333333333333334, + "grad_norm": 5.006600379943848, + "learning_rate": 0.00011666666666666668, + "loss": 2.1484, + "step": 28 + }, + { + "epoch": 0.25, + "grad_norm": 4.475966453552246, + "learning_rate": 0.000125, + "loss": 1.9871, + "step": 30 + }, + { + "epoch": 0.26666666666666666, + "grad_norm": 4.605421543121338, + "learning_rate": 0.00013333333333333334, + "loss": 2.1455, + "step": 32 + }, + { + "epoch": 0.2833333333333333, + "grad_norm": 4.921014785766602, + "learning_rate": 0.00014166666666666668, + "loss": 1.9162, + "step": 34 + }, + { + "epoch": 0.3, + "grad_norm": 4.6443634033203125, + "learning_rate": 0.00015000000000000001, + "loss": 2.0503, + "step": 36 + }, + { + "epoch": 0.31666666666666665, + "grad_norm": 4.234635353088379, + "learning_rate": 0.00015833333333333332, + "loss": 2.0901, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 4.628840446472168, + "learning_rate": 0.0001666666666666667, + "loss": 1.8014, + "step": 40 + }, + { + "epoch": 0.35, + "grad_norm": 3.8235278129577637, + "learning_rate": 0.000175, + "loss": 1.8156, + "step": 42 + }, + { + "epoch": 0.36666666666666664, + "grad_norm": 5.939589500427246, + "learning_rate": 0.00018333333333333334, + "loss": 1.7782, + "step": 44 + }, + { + "epoch": 0.38333333333333336, + "grad_norm": 4.921348571777344, + "learning_rate": 0.00019166666666666667, + "loss": 1.7167, + "step": 46 + }, + { + "epoch": 0.4, + "grad_norm": 4.549618244171143, + "learning_rate": 0.0002, + "loss": 2.2041, + "step": 48 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 4.085502624511719, + "learning_rate": 0.00019998942319271077, + "loss": 1.8483, + "step": 50 + }, + { + "epoch": 0.43333333333333335, + "grad_norm": 3.6243653297424316, + "learning_rate": 0.0001999576950082201, + "loss": 2.0321, + "step": 52 + }, + { + "epoch": 0.45, + "grad_norm": 3.530813455581665, + "learning_rate": 0.0001999048221581858, + "loss": 1.819, + "step": 54 + }, + { + "epoch": 0.4666666666666667, + "grad_norm": 3.175443649291992, + "learning_rate": 0.00019983081582712685, + "loss": 1.7011, + "step": 56 + }, + { + "epoch": 0.48333333333333334, + "grad_norm": 3.0620853900909424, + "learning_rate": 0.00019973569167005723, + "loss": 1.6158, + "step": 58 + }, + { + "epoch": 0.5, + "grad_norm": 3.984229564666748, + "learning_rate": 0.00019961946980917456, + "loss": 1.8606, + "step": 60 + }, + { + "epoch": 0.5166666666666667, + "grad_norm": 3.717822313308716, + "learning_rate": 0.0001994821748296033, + "loss": 1.7937, + "step": 62 + }, + { + "epoch": 0.5333333333333333, + "grad_norm": 4.549349308013916, + "learning_rate": 0.00019932383577419432, + "loss": 1.9389, + "step": 64 + }, + { + "epoch": 0.55, + "grad_norm": 4.229006767272949, + "learning_rate": 0.00019914448613738106, + "loss": 1.5434, + "step": 66 + }, + { + "epoch": 0.5666666666666667, + "grad_norm": 3.5755157470703125, + "learning_rate": 0.00019894416385809444, + "loss": 1.6555, + "step": 68 + }, + { + "epoch": 0.5833333333333334, + "grad_norm": 3.2299246788024902, + "learning_rate": 0.00019872291131173742, + "loss": 1.7088, + "step": 70 + }, + { + "epoch": 0.6, + "grad_norm": 3.777369260787964, + "learning_rate": 0.00019848077530122083, + "loss": 1.7569, + "step": 72 + }, + { + "epoch": 0.6166666666666667, + "grad_norm": 3.143406629562378, + "learning_rate": 0.00019821780704706307, + "loss": 1.7495, + "step": 74 + }, + { + "epoch": 0.6333333333333333, + "grad_norm": 3.655970811843872, + "learning_rate": 0.00019793406217655517, + "loss": 1.6553, + "step": 76 + }, + { + "epoch": 0.65, + "grad_norm": 3.4324283599853516, + "learning_rate": 0.00019762960071199333, + "loss": 1.5155, + "step": 78 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 3.7328310012817383, + "learning_rate": 0.00019730448705798239, + "loss": 1.8168, + "step": 80 + }, + { + "epoch": 0.6833333333333333, + "grad_norm": 3.8750150203704834, + "learning_rate": 0.0001969587899878116, + "loss": 1.705, + "step": 82 + }, + { + "epoch": 0.7, + "grad_norm": 4.362231254577637, + "learning_rate": 0.00019659258262890683, + "loss": 1.3282, + "step": 84 + }, + { + "epoch": 0.7166666666666667, + "grad_norm": 3.3029322624206543, + "learning_rate": 0.00019620594244736133, + "loss": 1.4785, + "step": 86 + }, + { + "epoch": 0.7333333333333333, + "grad_norm": 3.272670269012451, + "learning_rate": 0.0001957989512315489, + "loss": 1.7328, + "step": 88 + }, + { + "epoch": 0.75, + "grad_norm": 4.447598457336426, + "learning_rate": 0.0001953716950748227, + "loss": 1.8185, + "step": 90 + }, + { + "epoch": 0.7666666666666667, + "grad_norm": 2.942129373550415, + "learning_rate": 0.0001949242643573034, + "loss": 1.6651, + "step": 92 + }, + { + "epoch": 0.7833333333333333, + "grad_norm": 3.0011799335479736, + "learning_rate": 0.0001944567537267605, + "loss": 1.8555, + "step": 94 + }, + { + "epoch": 0.8, + "grad_norm": 3.2934067249298096, + "learning_rate": 0.00019396926207859084, + "loss": 1.5531, + "step": 96 + }, + { + "epoch": 0.8166666666666667, + "grad_norm": 3.1889824867248535, + "learning_rate": 0.00019346189253489885, + "loss": 1.8412, + "step": 98 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 2.921942949295044, + "learning_rate": 0.00019293475242268223, + "loss": 1.4985, + "step": 100 + }, + { + "epoch": 0.85, + "grad_norm": 3.1884875297546387, + "learning_rate": 0.0001923879532511287, + "loss": 1.5736, + "step": 102 + }, + { + "epoch": 0.8666666666666667, + "grad_norm": 3.4869801998138428, + "learning_rate": 0.00019182161068802741, + "loss": 1.4873, + "step": 104 + }, + { + "epoch": 0.8833333333333333, + "grad_norm": 2.8857343196868896, + "learning_rate": 0.00019123584453530144, + "loss": 1.4827, + "step": 106 + }, + { + "epoch": 0.9, + "grad_norm": 4.214871406555176, + "learning_rate": 0.000190630778703665, + "loss": 1.6214, + "step": 108 + }, + { + "epoch": 0.9166666666666666, + "grad_norm": 3.495774984359741, + "learning_rate": 0.00019000654118641211, + "loss": 1.6193, + "step": 110 + }, + { + "epoch": 0.9333333333333333, + "grad_norm": 3.5762667655944824, + "learning_rate": 0.00018936326403234125, + "loss": 1.5264, + "step": 112 + }, + { + "epoch": 0.95, + "grad_norm": 3.465022563934326, + "learning_rate": 0.00018870108331782217, + "loss": 1.6963, + "step": 114 + }, + { + "epoch": 0.9666666666666667, + "grad_norm": 3.743870973587036, + "learning_rate": 0.00018802013911801112, + "loss": 1.6291, + "step": 116 + }, + { + "epoch": 0.9833333333333333, + "grad_norm": 4.362145900726318, + "learning_rate": 0.0001873205754772196, + "loss": 1.3957, + "step": 118 + }, + { + "epoch": 1.0, + "grad_norm": 3.093210220336914, + "learning_rate": 0.00018660254037844388, + "loss": 1.5895, + "step": 120 + }, + { + "epoch": 1.0166666666666666, + "grad_norm": 3.2383241653442383, + "learning_rate": 0.00018586618571206134, + "loss": 1.1764, + "step": 122 + }, + { + "epoch": 1.0333333333333334, + "grad_norm": 3.522508144378662, + "learning_rate": 0.00018511166724369997, + "loss": 1.225, + "step": 124 + }, + { + "epoch": 1.05, + "grad_norm": 2.7789227962493896, + "learning_rate": 0.0001843391445812886, + "loss": 1.0999, + "step": 126 + }, + { + "epoch": 1.0666666666666667, + "grad_norm": 3.2942252159118652, + "learning_rate": 0.00018354878114129367, + "loss": 1.1459, + "step": 128 + }, + { + "epoch": 1.0833333333333333, + "grad_norm": 3.0693302154541016, + "learning_rate": 0.00018274074411415105, + "loss": 1.0881, + "step": 130 + }, + { + "epoch": 1.1, + "grad_norm": NaN, + "learning_rate": 0.00018233015127566807, + "loss": 1.2143, + "step": 132 + }, + { + "epoch": 1.1166666666666667, + "grad_norm": 3.5694239139556885, + "learning_rate": 0.0001814959255181988, + "loss": 0.9691, + "step": 134 + }, + { + "epoch": 1.1333333333333333, + "grad_norm": 3.9906177520751953, + "learning_rate": 0.00018064446042674828, + "loss": 1.1584, + "step": 136 + }, + { + "epoch": 1.15, + "grad_norm": 3.965775966644287, + "learning_rate": 0.00017977593611696015, + "loss": 0.985, + "step": 138 + }, + { + "epoch": 1.1666666666666667, + "grad_norm": 5.350390911102295, + "learning_rate": 0.00017889053631311947, + "loss": 1.3574, + "step": 140 + }, + { + "epoch": 1.1833333333333333, + "grad_norm": 3.8706905841827393, + "learning_rate": 0.00017798844830928817, + "loss": 1.159, + "step": 142 + }, + { + "epoch": 1.2, + "grad_norm": 3.463747024536133, + "learning_rate": 0.00017706986292968582, + "loss": 1.046, + "step": 144 + }, + { + "epoch": 1.2166666666666668, + "grad_norm": 3.620864152908325, + "learning_rate": 0.00017613497448832312, + "loss": 0.9971, + "step": 146 + }, + { + "epoch": 1.2333333333333334, + "grad_norm": 3.640916347503662, + "learning_rate": 0.00017518398074789775, + "loss": 0.8718, + "step": 148 + }, + { + "epoch": 1.25, + "grad_norm": 3.4872817993164062, + "learning_rate": 0.00017421708287796017, + "loss": 1.1691, + "step": 150 + }, + { + "epoch": 1.2666666666666666, + "grad_norm": 4.584655284881592, + "learning_rate": 0.00017323448541235924, + "loss": 1.1967, + "step": 152 + }, + { + "epoch": 1.2833333333333332, + "grad_norm": 3.5487728118896484, + "learning_rate": 0.00017223639620597556, + "loss": 1.0054, + "step": 154 + }, + { + "epoch": 1.3, + "grad_norm": 5.228781223297119, + "learning_rate": 0.0001712230263907531, + "loss": 1.4971, + "step": 156 + }, + { + "epoch": 1.3166666666666667, + "grad_norm": 3.641235828399658, + "learning_rate": 0.00017019459033103682, + "loss": 0.8541, + "step": 158 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 3.952843427658081, + "learning_rate": 0.00016915130557822695, + "loss": 0.9685, + "step": 160 + }, + { + "epoch": 1.35, + "grad_norm": 3.3446860313415527, + "learning_rate": 0.00016809339282475904, + "loss": 0.7522, + "step": 162 + }, + { + "epoch": 1.3666666666666667, + "grad_norm": 2.8159420490264893, + "learning_rate": 0.0001670210758574196, + "loss": 0.7398, + "step": 164 + }, + { + "epoch": 1.3833333333333333, + "grad_norm": 4.205153942108154, + "learning_rate": 0.00016593458151000688, + "loss": 1.1048, + "step": 166 + }, + { + "epoch": 1.4, + "grad_norm": 3.777249336242676, + "learning_rate": 0.00016483413961534762, + "loss": 1.0596, + "step": 168 + }, + { + "epoch": 1.4166666666666667, + "grad_norm": 4.2157440185546875, + "learning_rate": 0.00016371998295667886, + "loss": 0.8744, + "step": 170 + }, + { + "epoch": 1.4333333333333333, + "grad_norm": 5.198025703430176, + "learning_rate": 0.00016259234721840591, + "loss": 1.1068, + "step": 172 + }, + { + "epoch": 1.45, + "grad_norm": 4.17173957824707, + "learning_rate": 0.00016145147093624677, + "loss": 0.7444, + "step": 174 + }, + { + "epoch": 1.4666666666666668, + "grad_norm": 5.4046311378479, + "learning_rate": 0.00016029759544677297, + "loss": 1.0724, + "step": 176 + }, + { + "epoch": 1.4833333333333334, + "grad_norm": 3.2475147247314453, + "learning_rate": 0.00015913096483635824, + "loss": 0.9882, + "step": 178 + }, + { + "epoch": 1.5, + "grad_norm": 3.927030324935913, + "learning_rate": 0.0001579518258895455, + "loss": 0.7172, + "step": 180 + }, + { + "epoch": 1.5166666666666666, + "grad_norm": 3.783529758453369, + "learning_rate": 0.00015676042803684288, + "loss": 1.117, + "step": 182 + }, + { + "epoch": 1.5333333333333332, + "grad_norm": 4.151139736175537, + "learning_rate": 0.00015555702330196023, + "loss": 0.8876, + "step": 184 + }, + { + "epoch": 1.55, + "grad_norm": 4.858468055725098, + "learning_rate": 0.000154341866248497, + "loss": 0.818, + "step": 186 + }, + { + "epoch": 1.5666666666666667, + "grad_norm": 5.292931079864502, + "learning_rate": 0.00015311521392609282, + "loss": 1.1459, + "step": 188 + }, + { + "epoch": 1.5833333333333335, + "grad_norm": 5.330478668212891, + "learning_rate": 0.00015187732581605217, + "loss": 1.1276, + "step": 190 + }, + { + "epoch": 1.6, + "grad_norm": 4.155002117156982, + "learning_rate": 0.00015062846377645475, + "loss": 1.0617, + "step": 192 + }, + { + "epoch": 1.6166666666666667, + "grad_norm": 4.212536334991455, + "learning_rate": 0.00014936889198676303, + "loss": 0.7472, + "step": 194 + }, + { + "epoch": 1.6333333333333333, + "grad_norm": 3.7566754817962646, + "learning_rate": 0.00014809887689193877, + "loss": 1.1331, + "step": 196 + }, + { + "epoch": 1.65, + "grad_norm": 3.677277088165283, + "learning_rate": 0.0001468186871460802, + "loss": 0.7747, + "step": 198 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.946069717407227, + "learning_rate": 0.00014552859355559204, + "loss": 1.333, + "step": 200 + }, + { + "epoch": 1.6833333333333333, + "grad_norm": 4.023520469665527, + "learning_rate": 0.00014422886902190014, + "loss": 0.8673, + "step": 202 + }, + { + "epoch": 1.7, + "grad_norm": 3.5782713890075684, + "learning_rate": 0.00014291978848372293, + "loss": 0.8761, + "step": 204 + }, + { + "epoch": 1.7166666666666668, + "grad_norm": 2.9059038162231445, + "learning_rate": 0.00014160162885891193, + "loss": 0.7392, + "step": 206 + }, + { + "epoch": 1.7333333333333334, + "grad_norm": 4.512781143188477, + "learning_rate": 0.00014027466898587374, + "loss": 1.0393, + "step": 208 + }, + { + "epoch": 1.75, + "grad_norm": 4.064301013946533, + "learning_rate": 0.00013893918956458552, + "loss": 1.1425, + "step": 210 + }, + { + "epoch": 1.7666666666666666, + "grad_norm": 3.854093313217163, + "learning_rate": 0.0001375954730972168, + "loss": 0.8584, + "step": 212 + }, + { + "epoch": 1.7833333333333332, + "grad_norm": 4.655716896057129, + "learning_rate": 0.00013624380382837016, + "loss": 1.0068, + "step": 214 + }, + { + "epoch": 1.8, + "grad_norm": 4.099919319152832, + "learning_rate": 0.0001348844676849531, + "loss": 1.0037, + "step": 216 + }, + { + "epoch": 1.8166666666666667, + "grad_norm": 4.197730541229248, + "learning_rate": 0.00013351775221569415, + "loss": 0.9886, + "step": 218 + }, + { + "epoch": 1.8333333333333335, + "grad_norm": 4.721825122833252, + "learning_rate": 0.00013214394653031616, + "loss": 0.7593, + "step": 220 + }, + { + "epoch": 1.85, + "grad_norm": 3.716853618621826, + "learning_rate": 0.00013076334123837883, + "loss": 1.0082, + "step": 222 + }, + { + "epoch": 1.8666666666666667, + "grad_norm": 3.670105218887329, + "learning_rate": 0.00012937622838780444, + "loss": 1.0315, + "step": 224 + }, + { + "epoch": 1.8833333333333333, + "grad_norm": 4.269951343536377, + "learning_rate": 0.00012798290140309923, + "loss": 0.8955, + "step": 226 + }, + { + "epoch": 1.9, + "grad_norm": 3.60205078125, + "learning_rate": 0.0001265836550232833, + "loss": 1.1489, + "step": 228 + }, + { + "epoch": 1.9166666666666665, + "grad_norm": 3.538810968399048, + "learning_rate": 0.00012517878523954286, + "loss": 0.799, + "step": 230 + }, + { + "epoch": 1.9333333333333333, + "grad_norm": 4.749423980712891, + "learning_rate": 0.00012376858923261733, + "loss": 1.1039, + "step": 232 + }, + { + "epoch": 1.95, + "grad_norm": 4.193479537963867, + "learning_rate": 0.00012235336530993474, + "loss": 0.8296, + "step": 234 + }, + { + "epoch": 1.9666666666666668, + "grad_norm": 4.116739273071289, + "learning_rate": 0.0001209334128425092, + "loss": 1.0921, + "step": 236 + }, + { + "epoch": 1.9833333333333334, + "grad_norm": 4.641618728637695, + "learning_rate": 0.00011950903220161285, + "loss": 1.0626, + "step": 238 + }, + { + "epoch": 2.0, + "grad_norm": 3.8030502796173096, + "learning_rate": 0.00011808052469523654, + "loss": 0.8727, + "step": 240 + }, + { + "epoch": 2.0166666666666666, + "grad_norm": 2.3342442512512207, + "learning_rate": 0.00011664819250435246, + "loss": 0.4454, + "step": 242 + }, + { + "epoch": 2.033333333333333, + "grad_norm": 2.8402302265167236, + "learning_rate": 0.00011521233861899167, + "loss": 0.5571, + "step": 244 + }, + { + "epoch": 2.05, + "grad_norm": 2.57841420173645, + "learning_rate": 0.00011377326677415108, + "loss": 0.4795, + "step": 246 + }, + { + "epoch": 2.066666666666667, + "grad_norm": 3.053065538406372, + "learning_rate": 0.0001123312813855422, + "loss": 0.3929, + "step": 248 + }, + { + "epoch": 2.0833333333333335, + "grad_norm": 2.139831781387329, + "learning_rate": 0.00011088668748519647, + "loss": 0.282, + "step": 250 + }, + { + "epoch": 2.1, + "grad_norm": 3.3757216930389404, + "learning_rate": 0.00010943979065693975, + "loss": 0.2708, + "step": 252 + }, + { + "epoch": 2.1166666666666667, + "grad_norm": 3.2355637550354004, + "learning_rate": 0.0001079908969717504, + "loss": 0.311, + "step": 254 + }, + { + "epoch": 2.1333333333333333, + "grad_norm": 4.268968105316162, + "learning_rate": 0.00010654031292301432, + "loss": 0.4677, + "step": 256 + }, + { + "epoch": 2.15, + "grad_norm": 4.090265274047852, + "learning_rate": 0.00010508834536169028, + "loss": 0.3596, + "step": 258 + }, + { + "epoch": 2.1666666666666665, + "grad_norm": 7.346329689025879, + "learning_rate": 0.00010363530143139999, + "loss": 0.4479, + "step": 260 + }, + { + "epoch": 2.183333333333333, + "grad_norm": 4.075113773345947, + "learning_rate": 0.00010218148850345613, + "loss": 0.2427, + "step": 262 + }, + { + "epoch": 2.2, + "grad_norm": 4.176583290100098, + "learning_rate": 0.00010072721411184219, + "loss": 0.3568, + "step": 264 + }, + { + "epoch": 2.216666666666667, + "grad_norm": 6.221187591552734, + "learning_rate": 9.927278588815786e-05, + "loss": 0.448, + "step": 266 + }, + { + "epoch": 2.2333333333333334, + "grad_norm": 3.9996376037597656, + "learning_rate": 9.78185114965439e-05, + "loss": 0.3333, + "step": 268 + }, + { + "epoch": 2.25, + "grad_norm": 4.559553623199463, + "learning_rate": 9.636469856860005e-05, + "loss": 0.4674, + "step": 270 + }, + { + "epoch": 2.2666666666666666, + "grad_norm": 6.141816139221191, + "learning_rate": 9.491165463830975e-05, + "loss": 0.389, + "step": 272 + }, + { + "epoch": 2.283333333333333, + "grad_norm": 2.6158952713012695, + "learning_rate": 9.345968707698569e-05, + "loss": 0.2645, + "step": 274 + }, + { + "epoch": 2.3, + "grad_norm": 3.282641887664795, + "learning_rate": 9.200910302824963e-05, + "loss": 0.2093, + "step": 276 + }, + { + "epoch": 2.3166666666666664, + "grad_norm": 5.1213531494140625, + "learning_rate": 9.056020934306032e-05, + "loss": 0.49, + "step": 278 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 3.797430992126465, + "learning_rate": 8.911331251480357e-05, + "loss": 0.3902, + "step": 280 + }, + { + "epoch": 2.35, + "grad_norm": 6.6035003662109375, + "learning_rate": 8.76687186144578e-05, + "loss": 0.7753, + "step": 282 + }, + { + "epoch": 2.3666666666666667, + "grad_norm": 3.5583887100219727, + "learning_rate": 8.622673322584893e-05, + "loss": 0.4025, + "step": 284 + }, + { + "epoch": 2.3833333333333333, + "grad_norm": 4.608684539794922, + "learning_rate": 8.478766138100834e-05, + "loss": 0.5063, + "step": 286 + }, + { + "epoch": 2.4, + "grad_norm": 2.7952687740325928, + "learning_rate": 8.33518074956476e-05, + "loss": 0.3076, + "step": 288 + }, + { + "epoch": 2.4166666666666665, + "grad_norm": 2.9769716262817383, + "learning_rate": 8.19194753047635e-05, + "loss": 0.3486, + "step": 290 + }, + { + "epoch": 2.4333333333333336, + "grad_norm": 3.5893726348876953, + "learning_rate": 8.049096779838719e-05, + "loss": 0.2811, + "step": 292 + }, + { + "epoch": 2.45, + "grad_norm": 3.148125410079956, + "learning_rate": 7.90665871574908e-05, + "loss": 0.3277, + "step": 294 + }, + { + "epoch": 2.466666666666667, + "grad_norm": 5.177605628967285, + "learning_rate": 7.764663469006526e-05, + "loss": 0.3731, + "step": 296 + }, + { + "epoch": 2.4833333333333334, + "grad_norm": 3.892669916152954, + "learning_rate": 7.623141076738271e-05, + "loss": 0.3198, + "step": 298 + }, + { + "epoch": 2.5, + "grad_norm": 3.6123385429382324, + "learning_rate": 7.482121476045716e-05, + "loss": 0.5192, + "step": 300 + }, + { + "epoch": 2.5166666666666666, + "grad_norm": 2.719717025756836, + "learning_rate": 7.341634497671672e-05, + "loss": 0.2535, + "step": 302 + }, + { + "epoch": 2.533333333333333, + "grad_norm": 4.977841854095459, + "learning_rate": 7.20170985969008e-05, + "loss": 0.4689, + "step": 304 + }, + { + "epoch": 2.55, + "grad_norm": 5.187366008758545, + "learning_rate": 7.062377161219556e-05, + "loss": 0.5351, + "step": 306 + }, + { + "epoch": 2.5666666666666664, + "grad_norm": 4.046250820159912, + "learning_rate": 6.923665876162118e-05, + "loss": 0.3217, + "step": 308 + }, + { + "epoch": 2.5833333333333335, + "grad_norm": 4.094428062438965, + "learning_rate": 6.785605346968386e-05, + "loss": 0.2732, + "step": 310 + }, + { + "epoch": 2.6, + "grad_norm": 3.866711378097534, + "learning_rate": 6.648224778430586e-05, + "loss": 0.3628, + "step": 312 + }, + { + "epoch": 2.6166666666666667, + "grad_norm": 4.404598712921143, + "learning_rate": 6.511553231504693e-05, + "loss": 0.3413, + "step": 314 + }, + { + "epoch": 2.6333333333333333, + "grad_norm": 2.5987486839294434, + "learning_rate": 6.375619617162985e-05, + "loss": 0.2774, + "step": 316 + }, + { + "epoch": 2.65, + "grad_norm": 3.71152400970459, + "learning_rate": 6.24045269027832e-05, + "loss": 0.2921, + "step": 318 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 3.979522466659546, + "learning_rate": 6.106081043541451e-05, + "loss": 0.4342, + "step": 320 + }, + { + "epoch": 2.6833333333333336, + "grad_norm": 3.911111831665039, + "learning_rate": 5.9725331014126294e-05, + "loss": 0.31, + "step": 322 + }, + { + "epoch": 2.7, + "grad_norm": 3.6240077018737793, + "learning_rate": 5.83983711410881e-05, + "loss": 0.327, + "step": 324 + }, + { + "epoch": 2.716666666666667, + "grad_norm": 5.9682464599609375, + "learning_rate": 5.708021151627712e-05, + "loss": 0.4872, + "step": 326 + }, + { + "epoch": 2.7333333333333334, + "grad_norm": 3.8597633838653564, + "learning_rate": 5.577113097809989e-05, + "loss": 0.4383, + "step": 328 + }, + { + "epoch": 2.75, + "grad_norm": 5.048224449157715, + "learning_rate": 5.447140644440798e-05, + "loss": 0.3032, + "step": 330 + }, + { + "epoch": 2.7666666666666666, + "grad_norm": 5.027097702026367, + "learning_rate": 5.3181312853919804e-05, + "loss": 0.3896, + "step": 332 + }, + { + "epoch": 2.783333333333333, + "grad_norm": 4.691665172576904, + "learning_rate": 5.190112310806126e-05, + "loss": 0.3472, + "step": 334 + }, + { + "epoch": 2.8, + "grad_norm": 3.9736762046813965, + "learning_rate": 5.063110801323697e-05, + "loss": 0.4055, + "step": 336 + }, + { + "epoch": 2.8166666666666664, + "grad_norm": 4.054826736450195, + "learning_rate": 4.937153622354529e-05, + "loss": 0.3726, + "step": 338 + }, + { + "epoch": 2.8333333333333335, + "grad_norm": 3.664060115814209, + "learning_rate": 4.8122674183947836e-05, + "loss": 0.3371, + "step": 340 + }, + { + "epoch": 2.85, + "grad_norm": 4.178070545196533, + "learning_rate": 4.688478607390723e-05, + "loss": 0.3097, + "step": 342 + }, + { + "epoch": 2.8666666666666667, + "grad_norm": 3.4262094497680664, + "learning_rate": 4.565813375150302e-05, + "loss": 0.3026, + "step": 344 + }, + { + "epoch": 2.8833333333333333, + "grad_norm": 3.2188515663146973, + "learning_rate": 4.444297669803981e-05, + "loss": 0.355, + "step": 346 + }, + { + "epoch": 2.9, + "grad_norm": 3.4030818939208984, + "learning_rate": 4.3239571963157145e-05, + "loss": 0.3154, + "step": 348 + }, + { + "epoch": 2.9166666666666665, + "grad_norm": 4.020461082458496, + "learning_rate": 4.2048174110454496e-05, + "loss": 0.3343, + "step": 350 + }, + { + "epoch": 2.9333333333333336, + "grad_norm": 4.760802745819092, + "learning_rate": 4.086903516364179e-05, + "loss": 0.3838, + "step": 352 + }, + { + "epoch": 2.95, + "grad_norm": 3.0673415660858154, + "learning_rate": 3.9702404553227046e-05, + "loss": 0.3273, + "step": 354 + }, + { + "epoch": 2.966666666666667, + "grad_norm": 4.536604404449463, + "learning_rate": 3.854852906375326e-05, + "loss": 0.4689, + "step": 356 + }, + { + "epoch": 2.9833333333333334, + "grad_norm": 4.535534381866455, + "learning_rate": 3.7407652781594095e-05, + "loss": 0.3247, + "step": 358 + }, + { + "epoch": 3.0, + "grad_norm": 3.0231096744537354, + "learning_rate": 3.628001704332118e-05, + "loss": 0.2235, + "step": 360 + } + ], + "logging_steps": 2, + "max_steps": 480, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 120, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9047684614717440.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-360/training_args.bin b/checkpoint-360/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac8f391c607e66ead5154a805581d756800be5f3 --- /dev/null +++ b/checkpoint-360/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29a6aaefe60e2bc5b7a3cfaa3a6197fc31914ea7b1436562fae6685627aff67 +size 7032 diff --git a/checkpoint-480/README.md b/checkpoint-480/README.md new file mode 100644 index 0000000000000000000000000000000000000000..016ab2302388dbc76ea25a0c5b903b851ba5f7ef --- /dev/null +++ b/checkpoint-480/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-2b-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 0.14.0 \ No newline at end of file diff --git a/checkpoint-480/adapter_config.json b/checkpoint-480/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..16d13f2cf4bc5af463a7babc742a43dc76bd0ba6 --- /dev/null +++ b/checkpoint-480/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-2b-it", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 16, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "down_proj", + "gate_proj", + "up_proj", + "k_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-480/adapter_model.safetensors b/checkpoint-480/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d1c8e92a32aa281d46e6e8725b2b5dd6604509e --- /dev/null +++ b/checkpoint-480/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a782f63cc9a1b25942cc1b6c6dfb940642b0e5112a44fd0717c078091839ab07 +size 83115256 diff --git a/checkpoint-480/optimizer.pt b/checkpoint-480/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..4bdf071b33307ea49aa54e95c3c87a9fa28bb1a5 --- /dev/null +++ b/checkpoint-480/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a23df90ad175558e6edf070250f2ece9f343fbc0a1f8a47f3600065989bf0a +size 42608772 diff --git a/checkpoint-480/rng_state.pth b/checkpoint-480/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..309eaea9285fd4daddc568f0dc32ec22de04fd6b --- /dev/null +++ b/checkpoint-480/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c648edf17b1926c7241e10b9a80892cfe06509d8da73ec69717149efac9ea7a7 +size 14244 diff --git a/checkpoint-480/scaler.pt b/checkpoint-480/scaler.pt new file mode 100644 index 0000000000000000000000000000000000000000..adbf8545bec44d61664d6f3315018330eca3ae42 --- /dev/null +++ b/checkpoint-480/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b24707f5b5a9002cdf32e3f79b5ef15433d33cee1afcb625a5548cc117189b5 +size 988 diff --git a/checkpoint-480/scheduler.pt b/checkpoint-480/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9134f36d78935376a98825753bd23e0a37ff6fa6 --- /dev/null +++ b/checkpoint-480/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5af75e797ed8c9ca22a1692491a7cb1cfbf79325e10f3d7689e22fe8f23bbfb +size 1064 diff --git a/checkpoint-480/special_tokens_map.json b/checkpoint-480/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-480/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "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": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-480/tokenizer.json b/checkpoint-480/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-480/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-480/tokenizer.model b/checkpoint-480/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-480/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-480/tokenizer_config.json b/checkpoint-480/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f363b51b217d3edc09ff81b12d5eda8d4039d5b6 --- /dev/null +++ b/checkpoint-480/tokenizer_config.json @@ -0,0 +1,2014 @@ +{ + "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": "", + "extra_special_tokens": {}, + "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/checkpoint-480/trainer_state.json b/checkpoint-480/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9d378dcac7af55d45822438f7c3a12399fad66cf --- /dev/null +++ b/checkpoint-480/trainer_state.json @@ -0,0 +1,1713 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.0, + "eval_steps": 500, + "global_step": 480, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.016666666666666666, + "grad_norm": 4.380008697509766, + "learning_rate": 8.333333333333334e-06, + "loss": 3.8472, + "step": 2 + }, + { + "epoch": 0.03333333333333333, + "grad_norm": 5.4320220947265625, + "learning_rate": 1.6666666666666667e-05, + "loss": 4.4355, + "step": 4 + }, + { + "epoch": 0.05, + "grad_norm": 5.495668411254883, + "learning_rate": 2.5e-05, + "loss": 4.0183, + "step": 6 + }, + { + "epoch": 0.06666666666666667, + "grad_norm": 5.333839416503906, + "learning_rate": 3.3333333333333335e-05, + "loss": 4.4543, + "step": 8 + }, + { + "epoch": 0.08333333333333333, + "grad_norm": 4.8141961097717285, + "learning_rate": 4.166666666666667e-05, + "loss": 4.0576, + "step": 10 + }, + { + "epoch": 0.1, + "grad_norm": 4.4542341232299805, + "learning_rate": 5e-05, + "loss": 3.3098, + "step": 12 + }, + { + "epoch": 0.11666666666666667, + "grad_norm": 4.608759880065918, + "learning_rate": 5.833333333333334e-05, + "loss": 3.3983, + "step": 14 + }, + { + "epoch": 0.13333333333333333, + "grad_norm": 3.7876033782958984, + "learning_rate": 6.666666666666667e-05, + "loss": 2.7265, + "step": 16 + }, + { + "epoch": 0.15, + "grad_norm": 4.206045627593994, + "learning_rate": 7.500000000000001e-05, + "loss": 2.4786, + "step": 18 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 4.687928676605225, + "learning_rate": 8.333333333333334e-05, + "loss": 2.2298, + "step": 20 + }, + { + "epoch": 0.18333333333333332, + "grad_norm": 4.639834880828857, + "learning_rate": 9.166666666666667e-05, + "loss": 2.5465, + "step": 22 + }, + { + "epoch": 0.2, + "grad_norm": 4.179326057434082, + "learning_rate": 0.0001, + "loss": 2.0804, + "step": 24 + }, + { + "epoch": 0.21666666666666667, + "grad_norm": 4.4850287437438965, + "learning_rate": 0.00010833333333333333, + "loss": 2.0512, + "step": 26 + }, + { + "epoch": 0.23333333333333334, + "grad_norm": 5.006600379943848, + "learning_rate": 0.00011666666666666668, + "loss": 2.1484, + "step": 28 + }, + { + "epoch": 0.25, + "grad_norm": 4.475966453552246, + "learning_rate": 0.000125, + "loss": 1.9871, + "step": 30 + }, + { + "epoch": 0.26666666666666666, + "grad_norm": 4.605421543121338, + "learning_rate": 0.00013333333333333334, + "loss": 2.1455, + "step": 32 + }, + { + "epoch": 0.2833333333333333, + "grad_norm": 4.921014785766602, + "learning_rate": 0.00014166666666666668, + "loss": 1.9162, + "step": 34 + }, + { + "epoch": 0.3, + "grad_norm": 4.6443634033203125, + "learning_rate": 0.00015000000000000001, + "loss": 2.0503, + "step": 36 + }, + { + "epoch": 0.31666666666666665, + "grad_norm": 4.234635353088379, + "learning_rate": 0.00015833333333333332, + "loss": 2.0901, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 4.628840446472168, + "learning_rate": 0.0001666666666666667, + "loss": 1.8014, + "step": 40 + }, + { + "epoch": 0.35, + "grad_norm": 3.8235278129577637, + "learning_rate": 0.000175, + "loss": 1.8156, + "step": 42 + }, + { + "epoch": 0.36666666666666664, + "grad_norm": 5.939589500427246, + "learning_rate": 0.00018333333333333334, + "loss": 1.7782, + "step": 44 + }, + { + "epoch": 0.38333333333333336, + "grad_norm": 4.921348571777344, + "learning_rate": 0.00019166666666666667, + "loss": 1.7167, + "step": 46 + }, + { + "epoch": 0.4, + "grad_norm": 4.549618244171143, + "learning_rate": 0.0002, + "loss": 2.2041, + "step": 48 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 4.085502624511719, + "learning_rate": 0.00019998942319271077, + "loss": 1.8483, + "step": 50 + }, + { + "epoch": 0.43333333333333335, + "grad_norm": 3.6243653297424316, + "learning_rate": 0.0001999576950082201, + "loss": 2.0321, + "step": 52 + }, + { + "epoch": 0.45, + "grad_norm": 3.530813455581665, + "learning_rate": 0.0001999048221581858, + "loss": 1.819, + "step": 54 + }, + { + "epoch": 0.4666666666666667, + "grad_norm": 3.175443649291992, + "learning_rate": 0.00019983081582712685, + "loss": 1.7011, + "step": 56 + }, + { + "epoch": 0.48333333333333334, + "grad_norm": 3.0620853900909424, + "learning_rate": 0.00019973569167005723, + "loss": 1.6158, + "step": 58 + }, + { + "epoch": 0.5, + "grad_norm": 3.984229564666748, + "learning_rate": 0.00019961946980917456, + "loss": 1.8606, + "step": 60 + }, + { + "epoch": 0.5166666666666667, + "grad_norm": 3.717822313308716, + "learning_rate": 0.0001994821748296033, + "loss": 1.7937, + "step": 62 + }, + { + "epoch": 0.5333333333333333, + "grad_norm": 4.549349308013916, + "learning_rate": 0.00019932383577419432, + "loss": 1.9389, + "step": 64 + }, + { + "epoch": 0.55, + "grad_norm": 4.229006767272949, + "learning_rate": 0.00019914448613738106, + "loss": 1.5434, + "step": 66 + }, + { + "epoch": 0.5666666666666667, + "grad_norm": 3.5755157470703125, + "learning_rate": 0.00019894416385809444, + "loss": 1.6555, + "step": 68 + }, + { + "epoch": 0.5833333333333334, + "grad_norm": 3.2299246788024902, + "learning_rate": 0.00019872291131173742, + "loss": 1.7088, + "step": 70 + }, + { + "epoch": 0.6, + "grad_norm": 3.777369260787964, + "learning_rate": 0.00019848077530122083, + "loss": 1.7569, + "step": 72 + }, + { + "epoch": 0.6166666666666667, + "grad_norm": 3.143406629562378, + "learning_rate": 0.00019821780704706307, + "loss": 1.7495, + "step": 74 + }, + { + "epoch": 0.6333333333333333, + "grad_norm": 3.655970811843872, + "learning_rate": 0.00019793406217655517, + "loss": 1.6553, + "step": 76 + }, + { + "epoch": 0.65, + "grad_norm": 3.4324283599853516, + "learning_rate": 0.00019762960071199333, + "loss": 1.5155, + "step": 78 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 3.7328310012817383, + "learning_rate": 0.00019730448705798239, + "loss": 1.8168, + "step": 80 + }, + { + "epoch": 0.6833333333333333, + "grad_norm": 3.8750150203704834, + "learning_rate": 0.0001969587899878116, + "loss": 1.705, + "step": 82 + }, + { + "epoch": 0.7, + "grad_norm": 4.362231254577637, + "learning_rate": 0.00019659258262890683, + "loss": 1.3282, + "step": 84 + }, + { + "epoch": 0.7166666666666667, + "grad_norm": 3.3029322624206543, + "learning_rate": 0.00019620594244736133, + "loss": 1.4785, + "step": 86 + }, + { + "epoch": 0.7333333333333333, + "grad_norm": 3.272670269012451, + "learning_rate": 0.0001957989512315489, + "loss": 1.7328, + "step": 88 + }, + { + "epoch": 0.75, + "grad_norm": 4.447598457336426, + "learning_rate": 0.0001953716950748227, + "loss": 1.8185, + "step": 90 + }, + { + "epoch": 0.7666666666666667, + "grad_norm": 2.942129373550415, + "learning_rate": 0.0001949242643573034, + "loss": 1.6651, + "step": 92 + }, + { + "epoch": 0.7833333333333333, + "grad_norm": 3.0011799335479736, + "learning_rate": 0.0001944567537267605, + "loss": 1.8555, + "step": 94 + }, + { + "epoch": 0.8, + "grad_norm": 3.2934067249298096, + "learning_rate": 0.00019396926207859084, + "loss": 1.5531, + "step": 96 + }, + { + "epoch": 0.8166666666666667, + "grad_norm": 3.1889824867248535, + "learning_rate": 0.00019346189253489885, + "loss": 1.8412, + "step": 98 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 2.921942949295044, + "learning_rate": 0.00019293475242268223, + "loss": 1.4985, + "step": 100 + }, + { + "epoch": 0.85, + "grad_norm": 3.1884875297546387, + "learning_rate": 0.0001923879532511287, + "loss": 1.5736, + "step": 102 + }, + { + "epoch": 0.8666666666666667, + "grad_norm": 3.4869801998138428, + "learning_rate": 0.00019182161068802741, + "loss": 1.4873, + "step": 104 + }, + { + "epoch": 0.8833333333333333, + "grad_norm": 2.8857343196868896, + "learning_rate": 0.00019123584453530144, + "loss": 1.4827, + "step": 106 + }, + { + "epoch": 0.9, + "grad_norm": 4.214871406555176, + "learning_rate": 0.000190630778703665, + "loss": 1.6214, + "step": 108 + }, + { + "epoch": 0.9166666666666666, + "grad_norm": 3.495774984359741, + "learning_rate": 0.00019000654118641211, + "loss": 1.6193, + "step": 110 + }, + { + "epoch": 0.9333333333333333, + "grad_norm": 3.5762667655944824, + "learning_rate": 0.00018936326403234125, + "loss": 1.5264, + "step": 112 + }, + { + "epoch": 0.95, + "grad_norm": 3.465022563934326, + "learning_rate": 0.00018870108331782217, + "loss": 1.6963, + "step": 114 + }, + { + "epoch": 0.9666666666666667, + "grad_norm": 3.743870973587036, + "learning_rate": 0.00018802013911801112, + "loss": 1.6291, + "step": 116 + }, + { + "epoch": 0.9833333333333333, + "grad_norm": 4.362145900726318, + "learning_rate": 0.0001873205754772196, + "loss": 1.3957, + "step": 118 + }, + { + "epoch": 1.0, + "grad_norm": 3.093210220336914, + "learning_rate": 0.00018660254037844388, + "loss": 1.5895, + "step": 120 + }, + { + "epoch": 1.0166666666666666, + "grad_norm": 3.2383241653442383, + "learning_rate": 0.00018586618571206134, + "loss": 1.1764, + "step": 122 + }, + { + "epoch": 1.0333333333333334, + "grad_norm": 3.522508144378662, + "learning_rate": 0.00018511166724369997, + "loss": 1.225, + "step": 124 + }, + { + "epoch": 1.05, + "grad_norm": 2.7789227962493896, + "learning_rate": 0.0001843391445812886, + "loss": 1.0999, + "step": 126 + }, + { + "epoch": 1.0666666666666667, + "grad_norm": 3.2942252159118652, + "learning_rate": 0.00018354878114129367, + "loss": 1.1459, + "step": 128 + }, + { + "epoch": 1.0833333333333333, + "grad_norm": 3.0693302154541016, + "learning_rate": 0.00018274074411415105, + "loss": 1.0881, + "step": 130 + }, + { + "epoch": 1.1, + "grad_norm": NaN, + "learning_rate": 0.00018233015127566807, + "loss": 1.2143, + "step": 132 + }, + { + "epoch": 1.1166666666666667, + "grad_norm": 3.5694239139556885, + "learning_rate": 0.0001814959255181988, + "loss": 0.9691, + "step": 134 + }, + { + "epoch": 1.1333333333333333, + "grad_norm": 3.9906177520751953, + "learning_rate": 0.00018064446042674828, + "loss": 1.1584, + "step": 136 + }, + { + "epoch": 1.15, + "grad_norm": 3.965775966644287, + "learning_rate": 0.00017977593611696015, + "loss": 0.985, + "step": 138 + }, + { + "epoch": 1.1666666666666667, + "grad_norm": 5.350390911102295, + "learning_rate": 0.00017889053631311947, + "loss": 1.3574, + "step": 140 + }, + { + "epoch": 1.1833333333333333, + "grad_norm": 3.8706905841827393, + "learning_rate": 0.00017798844830928817, + "loss": 1.159, + "step": 142 + }, + { + "epoch": 1.2, + "grad_norm": 3.463747024536133, + "learning_rate": 0.00017706986292968582, + "loss": 1.046, + "step": 144 + }, + { + "epoch": 1.2166666666666668, + "grad_norm": 3.620864152908325, + "learning_rate": 0.00017613497448832312, + "loss": 0.9971, + "step": 146 + }, + { + "epoch": 1.2333333333333334, + "grad_norm": 3.640916347503662, + "learning_rate": 0.00017518398074789775, + "loss": 0.8718, + "step": 148 + }, + { + "epoch": 1.25, + "grad_norm": 3.4872817993164062, + "learning_rate": 0.00017421708287796017, + "loss": 1.1691, + "step": 150 + }, + { + "epoch": 1.2666666666666666, + "grad_norm": 4.584655284881592, + "learning_rate": 0.00017323448541235924, + "loss": 1.1967, + "step": 152 + }, + { + "epoch": 1.2833333333333332, + "grad_norm": 3.5487728118896484, + "learning_rate": 0.00017223639620597556, + "loss": 1.0054, + "step": 154 + }, + { + "epoch": 1.3, + "grad_norm": 5.228781223297119, + "learning_rate": 0.0001712230263907531, + "loss": 1.4971, + "step": 156 + }, + { + "epoch": 1.3166666666666667, + "grad_norm": 3.641235828399658, + "learning_rate": 0.00017019459033103682, + "loss": 0.8541, + "step": 158 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 3.952843427658081, + "learning_rate": 0.00016915130557822695, + "loss": 0.9685, + "step": 160 + }, + { + "epoch": 1.35, + "grad_norm": 3.3446860313415527, + "learning_rate": 0.00016809339282475904, + "loss": 0.7522, + "step": 162 + }, + { + "epoch": 1.3666666666666667, + "grad_norm": 2.8159420490264893, + "learning_rate": 0.0001670210758574196, + "loss": 0.7398, + "step": 164 + }, + { + "epoch": 1.3833333333333333, + "grad_norm": 4.205153942108154, + "learning_rate": 0.00016593458151000688, + "loss": 1.1048, + "step": 166 + }, + { + "epoch": 1.4, + "grad_norm": 3.777249336242676, + "learning_rate": 0.00016483413961534762, + "loss": 1.0596, + "step": 168 + }, + { + "epoch": 1.4166666666666667, + "grad_norm": 4.2157440185546875, + "learning_rate": 0.00016371998295667886, + "loss": 0.8744, + "step": 170 + }, + { + "epoch": 1.4333333333333333, + "grad_norm": 5.198025703430176, + "learning_rate": 0.00016259234721840591, + "loss": 1.1068, + "step": 172 + }, + { + "epoch": 1.45, + "grad_norm": 4.17173957824707, + "learning_rate": 0.00016145147093624677, + "loss": 0.7444, + "step": 174 + }, + { + "epoch": 1.4666666666666668, + "grad_norm": 5.4046311378479, + "learning_rate": 0.00016029759544677297, + "loss": 1.0724, + "step": 176 + }, + { + "epoch": 1.4833333333333334, + "grad_norm": 3.2475147247314453, + "learning_rate": 0.00015913096483635824, + "loss": 0.9882, + "step": 178 + }, + { + "epoch": 1.5, + "grad_norm": 3.927030324935913, + "learning_rate": 0.0001579518258895455, + "loss": 0.7172, + "step": 180 + }, + { + "epoch": 1.5166666666666666, + "grad_norm": 3.783529758453369, + "learning_rate": 0.00015676042803684288, + "loss": 1.117, + "step": 182 + }, + { + "epoch": 1.5333333333333332, + "grad_norm": 4.151139736175537, + "learning_rate": 0.00015555702330196023, + "loss": 0.8876, + "step": 184 + }, + { + "epoch": 1.55, + "grad_norm": 4.858468055725098, + "learning_rate": 0.000154341866248497, + "loss": 0.818, + "step": 186 + }, + { + "epoch": 1.5666666666666667, + "grad_norm": 5.292931079864502, + "learning_rate": 0.00015311521392609282, + "loss": 1.1459, + "step": 188 + }, + { + "epoch": 1.5833333333333335, + "grad_norm": 5.330478668212891, + "learning_rate": 0.00015187732581605217, + "loss": 1.1276, + "step": 190 + }, + { + "epoch": 1.6, + "grad_norm": 4.155002117156982, + "learning_rate": 0.00015062846377645475, + "loss": 1.0617, + "step": 192 + }, + { + "epoch": 1.6166666666666667, + "grad_norm": 4.212536334991455, + "learning_rate": 0.00014936889198676303, + "loss": 0.7472, + "step": 194 + }, + { + "epoch": 1.6333333333333333, + "grad_norm": 3.7566754817962646, + "learning_rate": 0.00014809887689193877, + "loss": 1.1331, + "step": 196 + }, + { + "epoch": 1.65, + "grad_norm": 3.677277088165283, + "learning_rate": 0.0001468186871460802, + "loss": 0.7747, + "step": 198 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.946069717407227, + "learning_rate": 0.00014552859355559204, + "loss": 1.333, + "step": 200 + }, + { + "epoch": 1.6833333333333333, + "grad_norm": 4.023520469665527, + "learning_rate": 0.00014422886902190014, + "loss": 0.8673, + "step": 202 + }, + { + "epoch": 1.7, + "grad_norm": 3.5782713890075684, + "learning_rate": 0.00014291978848372293, + "loss": 0.8761, + "step": 204 + }, + { + "epoch": 1.7166666666666668, + "grad_norm": 2.9059038162231445, + "learning_rate": 0.00014160162885891193, + "loss": 0.7392, + "step": 206 + }, + { + "epoch": 1.7333333333333334, + "grad_norm": 4.512781143188477, + "learning_rate": 0.00014027466898587374, + "loss": 1.0393, + "step": 208 + }, + { + "epoch": 1.75, + "grad_norm": 4.064301013946533, + "learning_rate": 0.00013893918956458552, + "loss": 1.1425, + "step": 210 + }, + { + "epoch": 1.7666666666666666, + "grad_norm": 3.854093313217163, + "learning_rate": 0.0001375954730972168, + "loss": 0.8584, + "step": 212 + }, + { + "epoch": 1.7833333333333332, + "grad_norm": 4.655716896057129, + "learning_rate": 0.00013624380382837016, + "loss": 1.0068, + "step": 214 + }, + { + "epoch": 1.8, + "grad_norm": 4.099919319152832, + "learning_rate": 0.0001348844676849531, + "loss": 1.0037, + "step": 216 + }, + { + "epoch": 1.8166666666666667, + "grad_norm": 4.197730541229248, + "learning_rate": 0.00013351775221569415, + "loss": 0.9886, + "step": 218 + }, + { + "epoch": 1.8333333333333335, + "grad_norm": 4.721825122833252, + "learning_rate": 0.00013214394653031616, + "loss": 0.7593, + "step": 220 + }, + { + "epoch": 1.85, + "grad_norm": 3.716853618621826, + "learning_rate": 0.00013076334123837883, + "loss": 1.0082, + "step": 222 + }, + { + "epoch": 1.8666666666666667, + "grad_norm": 3.670105218887329, + "learning_rate": 0.00012937622838780444, + "loss": 1.0315, + "step": 224 + }, + { + "epoch": 1.8833333333333333, + "grad_norm": 4.269951343536377, + "learning_rate": 0.00012798290140309923, + "loss": 0.8955, + "step": 226 + }, + { + "epoch": 1.9, + "grad_norm": 3.60205078125, + "learning_rate": 0.0001265836550232833, + "loss": 1.1489, + "step": 228 + }, + { + "epoch": 1.9166666666666665, + "grad_norm": 3.538810968399048, + "learning_rate": 0.00012517878523954286, + "loss": 0.799, + "step": 230 + }, + { + "epoch": 1.9333333333333333, + "grad_norm": 4.749423980712891, + "learning_rate": 0.00012376858923261733, + "loss": 1.1039, + "step": 232 + }, + { + "epoch": 1.95, + "grad_norm": 4.193479537963867, + "learning_rate": 0.00012235336530993474, + "loss": 0.8296, + "step": 234 + }, + { + "epoch": 1.9666666666666668, + "grad_norm": 4.116739273071289, + "learning_rate": 0.0001209334128425092, + "loss": 1.0921, + "step": 236 + }, + { + "epoch": 1.9833333333333334, + "grad_norm": 4.641618728637695, + "learning_rate": 0.00011950903220161285, + "loss": 1.0626, + "step": 238 + }, + { + "epoch": 2.0, + "grad_norm": 3.8030502796173096, + "learning_rate": 0.00011808052469523654, + "loss": 0.8727, + "step": 240 + }, + { + "epoch": 2.0166666666666666, + "grad_norm": 2.3342442512512207, + "learning_rate": 0.00011664819250435246, + "loss": 0.4454, + "step": 242 + }, + { + "epoch": 2.033333333333333, + "grad_norm": 2.8402302265167236, + "learning_rate": 0.00011521233861899167, + "loss": 0.5571, + "step": 244 + }, + { + "epoch": 2.05, + "grad_norm": 2.57841420173645, + "learning_rate": 0.00011377326677415108, + "loss": 0.4795, + "step": 246 + }, + { + "epoch": 2.066666666666667, + "grad_norm": 3.053065538406372, + "learning_rate": 0.0001123312813855422, + "loss": 0.3929, + "step": 248 + }, + { + "epoch": 2.0833333333333335, + "grad_norm": 2.139831781387329, + "learning_rate": 0.00011088668748519647, + "loss": 0.282, + "step": 250 + }, + { + "epoch": 2.1, + "grad_norm": 3.3757216930389404, + "learning_rate": 0.00010943979065693975, + "loss": 0.2708, + "step": 252 + }, + { + "epoch": 2.1166666666666667, + "grad_norm": 3.2355637550354004, + "learning_rate": 0.0001079908969717504, + "loss": 0.311, + "step": 254 + }, + { + "epoch": 2.1333333333333333, + "grad_norm": 4.268968105316162, + "learning_rate": 0.00010654031292301432, + "loss": 0.4677, + "step": 256 + }, + { + "epoch": 2.15, + "grad_norm": 4.090265274047852, + "learning_rate": 0.00010508834536169028, + "loss": 0.3596, + "step": 258 + }, + { + "epoch": 2.1666666666666665, + "grad_norm": 7.346329689025879, + "learning_rate": 0.00010363530143139999, + "loss": 0.4479, + "step": 260 + }, + { + "epoch": 2.183333333333333, + "grad_norm": 4.075113773345947, + "learning_rate": 0.00010218148850345613, + "loss": 0.2427, + "step": 262 + }, + { + "epoch": 2.2, + "grad_norm": 4.176583290100098, + "learning_rate": 0.00010072721411184219, + "loss": 0.3568, + "step": 264 + }, + { + "epoch": 2.216666666666667, + "grad_norm": 6.221187591552734, + "learning_rate": 9.927278588815786e-05, + "loss": 0.448, + "step": 266 + }, + { + "epoch": 2.2333333333333334, + "grad_norm": 3.9996376037597656, + "learning_rate": 9.78185114965439e-05, + "loss": 0.3333, + "step": 268 + }, + { + "epoch": 2.25, + "grad_norm": 4.559553623199463, + "learning_rate": 9.636469856860005e-05, + "loss": 0.4674, + "step": 270 + }, + { + "epoch": 2.2666666666666666, + "grad_norm": 6.141816139221191, + "learning_rate": 9.491165463830975e-05, + "loss": 0.389, + "step": 272 + }, + { + "epoch": 2.283333333333333, + "grad_norm": 2.6158952713012695, + "learning_rate": 9.345968707698569e-05, + "loss": 0.2645, + "step": 274 + }, + { + "epoch": 2.3, + "grad_norm": 3.282641887664795, + "learning_rate": 9.200910302824963e-05, + "loss": 0.2093, + "step": 276 + }, + { + "epoch": 2.3166666666666664, + "grad_norm": 5.1213531494140625, + "learning_rate": 9.056020934306032e-05, + "loss": 0.49, + "step": 278 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 3.797430992126465, + "learning_rate": 8.911331251480357e-05, + "loss": 0.3902, + "step": 280 + }, + { + "epoch": 2.35, + "grad_norm": 6.6035003662109375, + "learning_rate": 8.76687186144578e-05, + "loss": 0.7753, + "step": 282 + }, + { + "epoch": 2.3666666666666667, + "grad_norm": 3.5583887100219727, + "learning_rate": 8.622673322584893e-05, + "loss": 0.4025, + "step": 284 + }, + { + "epoch": 2.3833333333333333, + "grad_norm": 4.608684539794922, + "learning_rate": 8.478766138100834e-05, + "loss": 0.5063, + "step": 286 + }, + { + "epoch": 2.4, + "grad_norm": 2.7952687740325928, + "learning_rate": 8.33518074956476e-05, + "loss": 0.3076, + "step": 288 + }, + { + "epoch": 2.4166666666666665, + "grad_norm": 2.9769716262817383, + "learning_rate": 8.19194753047635e-05, + "loss": 0.3486, + "step": 290 + }, + { + "epoch": 2.4333333333333336, + "grad_norm": 3.5893726348876953, + "learning_rate": 8.049096779838719e-05, + "loss": 0.2811, + "step": 292 + }, + { + "epoch": 2.45, + "grad_norm": 3.148125410079956, + "learning_rate": 7.90665871574908e-05, + "loss": 0.3277, + "step": 294 + }, + { + "epoch": 2.466666666666667, + "grad_norm": 5.177605628967285, + "learning_rate": 7.764663469006526e-05, + "loss": 0.3731, + "step": 296 + }, + { + "epoch": 2.4833333333333334, + "grad_norm": 3.892669916152954, + "learning_rate": 7.623141076738271e-05, + "loss": 0.3198, + "step": 298 + }, + { + "epoch": 2.5, + "grad_norm": 3.6123385429382324, + "learning_rate": 7.482121476045716e-05, + "loss": 0.5192, + "step": 300 + }, + { + "epoch": 2.5166666666666666, + "grad_norm": 2.719717025756836, + "learning_rate": 7.341634497671672e-05, + "loss": 0.2535, + "step": 302 + }, + { + "epoch": 2.533333333333333, + "grad_norm": 4.977841854095459, + "learning_rate": 7.20170985969008e-05, + "loss": 0.4689, + "step": 304 + }, + { + "epoch": 2.55, + "grad_norm": 5.187366008758545, + "learning_rate": 7.062377161219556e-05, + "loss": 0.5351, + "step": 306 + }, + { + "epoch": 2.5666666666666664, + "grad_norm": 4.046250820159912, + "learning_rate": 6.923665876162118e-05, + "loss": 0.3217, + "step": 308 + }, + { + "epoch": 2.5833333333333335, + "grad_norm": 4.094428062438965, + "learning_rate": 6.785605346968386e-05, + "loss": 0.2732, + "step": 310 + }, + { + "epoch": 2.6, + "grad_norm": 3.866711378097534, + "learning_rate": 6.648224778430586e-05, + "loss": 0.3628, + "step": 312 + }, + { + "epoch": 2.6166666666666667, + "grad_norm": 4.404598712921143, + "learning_rate": 6.511553231504693e-05, + "loss": 0.3413, + "step": 314 + }, + { + "epoch": 2.6333333333333333, + "grad_norm": 2.5987486839294434, + "learning_rate": 6.375619617162985e-05, + "loss": 0.2774, + "step": 316 + }, + { + "epoch": 2.65, + "grad_norm": 3.71152400970459, + "learning_rate": 6.24045269027832e-05, + "loss": 0.2921, + "step": 318 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 3.979522466659546, + "learning_rate": 6.106081043541451e-05, + "loss": 0.4342, + "step": 320 + }, + { + "epoch": 2.6833333333333336, + "grad_norm": 3.911111831665039, + "learning_rate": 5.9725331014126294e-05, + "loss": 0.31, + "step": 322 + }, + { + "epoch": 2.7, + "grad_norm": 3.6240077018737793, + "learning_rate": 5.83983711410881e-05, + "loss": 0.327, + "step": 324 + }, + { + "epoch": 2.716666666666667, + "grad_norm": 5.9682464599609375, + "learning_rate": 5.708021151627712e-05, + "loss": 0.4872, + "step": 326 + }, + { + "epoch": 2.7333333333333334, + "grad_norm": 3.8597633838653564, + "learning_rate": 5.577113097809989e-05, + "loss": 0.4383, + "step": 328 + }, + { + "epoch": 2.75, + "grad_norm": 5.048224449157715, + "learning_rate": 5.447140644440798e-05, + "loss": 0.3032, + "step": 330 + }, + { + "epoch": 2.7666666666666666, + "grad_norm": 5.027097702026367, + "learning_rate": 5.3181312853919804e-05, + "loss": 0.3896, + "step": 332 + }, + { + "epoch": 2.783333333333333, + "grad_norm": 4.691665172576904, + "learning_rate": 5.190112310806126e-05, + "loss": 0.3472, + "step": 334 + }, + { + "epoch": 2.8, + "grad_norm": 3.9736762046813965, + "learning_rate": 5.063110801323697e-05, + "loss": 0.4055, + "step": 336 + }, + { + "epoch": 2.8166666666666664, + "grad_norm": 4.054826736450195, + "learning_rate": 4.937153622354529e-05, + "loss": 0.3726, + "step": 338 + }, + { + "epoch": 2.8333333333333335, + "grad_norm": 3.664060115814209, + "learning_rate": 4.8122674183947836e-05, + "loss": 0.3371, + "step": 340 + }, + { + "epoch": 2.85, + "grad_norm": 4.178070545196533, + "learning_rate": 4.688478607390723e-05, + "loss": 0.3097, + "step": 342 + }, + { + "epoch": 2.8666666666666667, + "grad_norm": 3.4262094497680664, + "learning_rate": 4.565813375150302e-05, + "loss": 0.3026, + "step": 344 + }, + { + "epoch": 2.8833333333333333, + "grad_norm": 3.2188515663146973, + "learning_rate": 4.444297669803981e-05, + "loss": 0.355, + "step": 346 + }, + { + "epoch": 2.9, + "grad_norm": 3.4030818939208984, + "learning_rate": 4.3239571963157145e-05, + "loss": 0.3154, + "step": 348 + }, + { + "epoch": 2.9166666666666665, + "grad_norm": 4.020461082458496, + "learning_rate": 4.2048174110454496e-05, + "loss": 0.3343, + "step": 350 + }, + { + "epoch": 2.9333333333333336, + "grad_norm": 4.760802745819092, + "learning_rate": 4.086903516364179e-05, + "loss": 0.3838, + "step": 352 + }, + { + "epoch": 2.95, + "grad_norm": 3.0673415660858154, + "learning_rate": 3.9702404553227046e-05, + "loss": 0.3273, + "step": 354 + }, + { + "epoch": 2.966666666666667, + "grad_norm": 4.536604404449463, + "learning_rate": 3.854852906375326e-05, + "loss": 0.4689, + "step": 356 + }, + { + "epoch": 2.9833333333333334, + "grad_norm": 4.535534381866455, + "learning_rate": 3.7407652781594095e-05, + "loss": 0.3247, + "step": 358 + }, + { + "epoch": 3.0, + "grad_norm": 3.0231096744537354, + "learning_rate": 3.628001704332118e-05, + "loss": 0.2235, + "step": 360 + }, + { + "epoch": 3.0166666666666666, + "grad_norm": 1.689902901649475, + "learning_rate": 3.516586038465237e-05, + "loss": 0.1205, + "step": 362 + }, + { + "epoch": 3.033333333333333, + "grad_norm": 1.721530556678772, + "learning_rate": 3.406541848999312e-05, + "loss": 0.1297, + "step": 364 + }, + { + "epoch": 3.05, + "grad_norm": 2.444359302520752, + "learning_rate": 3.297892414258043e-05, + "loss": 0.133, + "step": 366 + }, + { + "epoch": 3.066666666666667, + "grad_norm": 2.129033327102661, + "learning_rate": 3.190660717524094e-05, + "loss": 0.1298, + "step": 368 + }, + { + "epoch": 3.0833333333333335, + "grad_norm": 1.7371456623077393, + "learning_rate": 3.0848694421773075e-05, + "loss": 0.1073, + "step": 370 + }, + { + "epoch": 3.1, + "grad_norm": 2.1412439346313477, + "learning_rate": 2.9805409668963168e-05, + "loss": 0.112, + "step": 372 + }, + { + "epoch": 3.1166666666666667, + "grad_norm": 1.1807520389556885, + "learning_rate": 2.8776973609246928e-05, + "loss": 0.1483, + "step": 374 + }, + { + "epoch": 3.1333333333333333, + "grad_norm": 1.5736063718795776, + "learning_rate": 2.776360379402445e-05, + "loss": 0.0716, + "step": 376 + }, + { + "epoch": 3.15, + "grad_norm": 2.7788288593292236, + "learning_rate": 2.6765514587640818e-05, + "loss": 0.1604, + "step": 378 + }, + { + "epoch": 3.1666666666666665, + "grad_norm": 1.5403401851654053, + "learning_rate": 2.578291712203983e-05, + "loss": 0.0799, + "step": 380 + }, + { + "epoch": 3.183333333333333, + "grad_norm": 1.7081397771835327, + "learning_rate": 2.4816019252102273e-05, + "loss": 0.1356, + "step": 382 + }, + { + "epoch": 3.2, + "grad_norm": 2.0004351139068604, + "learning_rate": 2.3865025511676897e-05, + "loss": 0.0915, + "step": 384 + }, + { + "epoch": 3.216666666666667, + "grad_norm": 2.7725274562835693, + "learning_rate": 2.2930137070314194e-05, + "loss": 0.0938, + "step": 386 + }, + { + "epoch": 3.2333333333333334, + "grad_norm": 1.8679347038269043, + "learning_rate": 2.201155169071184e-05, + "loss": 0.1975, + "step": 388 + }, + { + "epoch": 3.25, + "grad_norm": 4.1274824142456055, + "learning_rate": 2.110946368688055e-05, + "loss": 0.1267, + "step": 390 + }, + { + "epoch": 3.2666666666666666, + "grad_norm": 3.6267476081848145, + "learning_rate": 2.0224063883039868e-05, + "loss": 0.2046, + "step": 392 + }, + { + "epoch": 3.283333333333333, + "grad_norm": 1.8665709495544434, + "learning_rate": 1.9355539573251734e-05, + "loss": 0.0665, + "step": 394 + }, + { + "epoch": 3.3, + "grad_norm": 2.0604355335235596, + "learning_rate": 1.8504074481801238e-05, + "loss": 0.103, + "step": 396 + }, + { + "epoch": 3.3166666666666664, + "grad_norm": 3.836789131164551, + "learning_rate": 1.7669848724331984e-05, + "loss": 0.1435, + "step": 398 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 3.58620023727417, + "learning_rate": 1.6853038769745467e-05, + "loss": 0.1061, + "step": 400 + }, + { + "epoch": 3.35, + "grad_norm": 1.400498867034912, + "learning_rate": 1.6053817402871362e-05, + "loss": 0.0552, + "step": 402 + }, + { + "epoch": 3.3666666666666667, + "grad_norm": 2.337233066558838, + "learning_rate": 1.5272353687917196e-05, + "loss": 0.0931, + "step": 404 + }, + { + "epoch": 3.3833333333333333, + "grad_norm": 3.3815033435821533, + "learning_rate": 1.4508812932705363e-05, + "loss": 0.1705, + "step": 406 + }, + { + "epoch": 3.4, + "grad_norm": 2.2683122158050537, + "learning_rate": 1.3763356653704273e-05, + "loss": 0.0818, + "step": 408 + }, + { + "epoch": 3.4166666666666665, + "grad_norm": 4.132976055145264, + "learning_rate": 1.3036142541862118e-05, + "loss": 0.1501, + "step": 410 + }, + { + "epoch": 3.4333333333333336, + "grad_norm": 3.563286066055298, + "learning_rate": 1.2327324429249232e-05, + "loss": 0.145, + "step": 412 + }, + { + "epoch": 3.45, + "grad_norm": 3.074484348297119, + "learning_rate": 1.1637052256517244e-05, + "loss": 0.0896, + "step": 414 + }, + { + "epoch": 3.466666666666667, + "grad_norm": 2.444720983505249, + "learning_rate": 1.0965472041181102e-05, + "loss": 0.0791, + "step": 416 + }, + { + "epoch": 3.4833333333333334, + "grad_norm": 2.0574851036071777, + "learning_rate": 1.0312725846731175e-05, + "loss": 0.0553, + "step": 418 + }, + { + "epoch": 3.5, + "grad_norm": 4.138534069061279, + "learning_rate": 9.678951752581578e-06, + "loss": 0.0957, + "step": 420 + }, + { + "epoch": 3.5166666666666666, + "grad_norm": 2.8466336727142334, + "learning_rate": 9.064283824861486e-06, + "loss": 0.1626, + "step": 422 + }, + { + "epoch": 3.533333333333333, + "grad_norm": 2.2056469917297363, + "learning_rate": 8.46885208805529e-06, + "loss": 0.0769, + "step": 424 + }, + { + "epoch": 3.55, + "grad_norm": 2.024271249771118, + "learning_rate": 7.892782497497642e-06, + "loss": 0.1066, + "step": 426 + }, + { + "epoch": 3.5666666666666664, + "grad_norm": 3.893606662750244, + "learning_rate": 7.336196912729487e-06, + "loss": 0.1668, + "step": 428 + }, + { + "epoch": 3.5833333333333335, + "grad_norm": 3.0661404132843018, + "learning_rate": 6.7992130717201564e-06, + "loss": 0.1013, + "step": 430 + }, + { + "epoch": 3.6, + "grad_norm": 2.5830650329589844, + "learning_rate": 6.281944565961773e-06, + "loss": 0.0729, + "step": 432 + }, + { + "epoch": 3.6166666666666667, + "grad_norm": 3.114644765853882, + "learning_rate": 5.784500816440353e-06, + "loss": 0.1487, + "step": 434 + }, + { + "epoch": 3.6333333333333333, + "grad_norm": 2.4080984592437744, + "learning_rate": 5.306987050489442e-06, + "loss": 0.0833, + "step": 436 + }, + { + "epoch": 3.65, + "grad_norm": 4.849672794342041, + "learning_rate": 4.849504279530636e-06, + "loss": 0.1579, + "step": 438 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 1.7241791486740112, + "learning_rate": 4.412149277706046e-06, + "loss": 0.0739, + "step": 440 + }, + { + "epoch": 3.6833333333333336, + "grad_norm": 2.7701609134674072, + "learning_rate": 3.99501456140714e-06, + "loss": 0.0847, + "step": 442 + }, + { + "epoch": 3.7, + "grad_norm": 4.385118007659912, + "learning_rate": 3.598188369704036e-06, + "loss": 0.1509, + "step": 444 + }, + { + "epoch": 3.716666666666667, + "grad_norm": 3.6291391849517822, + "learning_rate": 3.2217546456799086e-06, + "loss": 0.0501, + "step": 446 + }, + { + "epoch": 3.7333333333333334, + "grad_norm": 2.650822162628174, + "learning_rate": 2.8657930186738567e-06, + "loss": 0.0783, + "step": 448 + }, + { + "epoch": 3.75, + "grad_norm": 0.8119848966598511, + "learning_rate": 2.530378787436527e-06, + "loss": 0.0614, + "step": 450 + }, + { + "epoch": 3.7666666666666666, + "grad_norm": 3.6683127880096436, + "learning_rate": 2.2155829042015962e-06, + "loss": 0.1109, + "step": 452 + }, + { + "epoch": 3.783333333333333, + "grad_norm": 2.81748628616333, + "learning_rate": 1.921471959676957e-06, + "loss": 0.1025, + "step": 454 + }, + { + "epoch": 3.8, + "grad_norm": 2.986403226852417, + "learning_rate": 1.648108168958229e-06, + "loss": 0.1222, + "step": 456 + }, + { + "epoch": 3.8166666666666664, + "grad_norm": 1.9328974485397339, + "learning_rate": 1.3955493583680868e-06, + "loss": 0.0682, + "step": 458 + }, + { + "epoch": 3.8333333333333335, + "grad_norm": 3.5435028076171875, + "learning_rate": 1.163848953223934e-06, + "loss": 0.0856, + "step": 460 + }, + { + "epoch": 3.85, + "grad_norm": 1.682571291923523, + "learning_rate": 9.530559665364202e-07, + "loss": 0.041, + "step": 462 + }, + { + "epoch": 3.8666666666666667, + "grad_norm": 2.2922608852386475, + "learning_rate": 7.632149886415363e-07, + "loss": 0.0743, + "step": 464 + }, + { + "epoch": 3.8833333333333333, + "grad_norm": 2.9161651134490967, + "learning_rate": 5.943661777680354e-07, + "loss": 0.1473, + "step": 466 + }, + { + "epoch": 3.9, + "grad_norm": 1.085811972618103, + "learning_rate": 4.465452515426072e-07, + "loss": 0.0395, + "step": 468 + }, + { + "epoch": 3.9166666666666665, + "grad_norm": 2.490661382675171, + "learning_rate": 3.197834794342436e-07, + "loss": 0.0874, + "step": 470 + }, + { + "epoch": 3.9333333333333336, + "grad_norm": 3.0676560401916504, + "learning_rate": 2.141076761396521e-07, + "loss": 0.1349, + "step": 472 + }, + { + "epoch": 3.95, + "grad_norm": 4.0954155921936035, + "learning_rate": 1.295401959109599e-07, + "loss": 0.1107, + "step": 474 + }, + { + "epoch": 3.966666666666667, + "grad_norm": 2.8223700523376465, + "learning_rate": 6.609892782699633e-08, + "loss": 0.0866, + "step": 476 + }, + { + "epoch": 3.9833333333333334, + "grad_norm": 1.3925378322601318, + "learning_rate": 2.379729200908676e-08, + "loss": 0.043, + "step": 478 + }, + { + "epoch": 4.0, + "grad_norm": 2.000886917114258, + "learning_rate": 2.6442367822565596e-09, + "loss": 0.0751, + "step": 480 + } + ], + "logging_steps": 2, + "max_steps": 480, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 120, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.206357948628992e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-480/training_args.bin b/checkpoint-480/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac8f391c607e66ead5154a805581d756800be5f3 --- /dev/null +++ b/checkpoint-480/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29a6aaefe60e2bc5b7a3cfaa3a6197fc31914ea7b1436562fae6685627aff67 +size 7032 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..782d5aec3a518140123ec128cf3f1103d1d079ac --- /dev/null +++ b/config.json @@ -0,0 +1,49 @@ +{ + "_attn_implementation_autoset": true, + "_name_or_path": "google/gemma-2-2b-it", + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2304, + "initializer_range": 0.02, + "intermediate_size": 9216, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 8, + "num_hidden_layers": 26, + "num_key_value_heads": 4, + "pad_token_id": 0, + "quantization_config": { + "_load_in_4bit": true, + "_load_in_8bit": false, + "bnb_4bit_compute_dtype": "float16", + "bnb_4bit_quant_storage": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "llm_int8_enable_fp32_cpu_offload": false, + "llm_int8_has_fp16_weight": false, + "llm_int8_skip_modules": null, + "llm_int8_threshold": 6.0, + "load_in_4bit": true, + "load_in_8bit": false, + "quant_method": "bitsandbytes" + }, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.49.0", + "use_cache": false, + "vocab_size": 256000 +} diff --git a/gemma-2-2B-it-F16-LoRA.gguf b/gemma-2-2B-it-F16-LoRA.gguf new file mode 100644 index 0000000000000000000000000000000000000000..9304df319fe2e1db8c96ed343e42f35b8a9114c9 --- /dev/null +++ b/gemma-2-2B-it-F16-LoRA.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370a21145cd4baf35b260a4d8e6381e9ae387441fa01e80cad67dfdec90ba5b1 +size 83092032 diff --git a/gemma-2-2b-it-Q8_0.gguf b/gemma-2-2b-it-Q8_0.gguf new file mode 100644 index 0000000000000000000000000000000000000000..51021ca1ab093a457d8371ef7b2b09a395f8ffc6 --- /dev/null +++ b/gemma-2-2b-it-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3bb1da03457fb2d53a14935f6666f46aea9c976d48a79347912005375057dab +size 2784495456 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "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": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f363b51b217d3edc09ff81b12d5eda8d4039d5b6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2014 @@ +{ + "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": "", + "extra_special_tokens": {}, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}