diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..fec2f17861b52185c3f691052af0032c1c2fc161 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,8 @@ saved_model/**/* 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-364/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-378/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-392/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-402/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e37e64e5c128a03eb0e7997f58f0456368a93fbc --- /dev/null +++ b/README.md @@ -0,0 +1,145 @@ +--- +library_name: peft +license: gemma +base_model: google/gemma-2-9b-it +tags: +- generated_from_trainer +datasets: +- frjonah/training_data5 +model-index: +- name: outputs/test3 + results: [] +--- + + + +[Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl) +
See axolotl config + +axolotl version: `0.10.0.dev0` +```yaml +# axolotl preprocess config.yaml + +adapter: lora +base_model: google/gemma-2-9b-it +bf16: auto +dataset_processes: 32 +datasets: +- path: frjonah/training_data5 + type: + system_prompt: "" + field_system: system + field_instruction: prompt + field_output: completion + format: "[INST] {instruction} [/INST]" + no_input_format: "[INST] {instruction} [/INST]" + +resize_token_embeddings_to_32x: false +add_special_tokens: false +special_tokens: + pad_token: null + eos_token: null + bos_token: null + unk_token: null + +gradient_accumulation_steps: 1 +gradient_checkpointing: true +learning_rate: 0.00002 +lisa_layers_attribute: model.layers +load_best_model_at_end: false +load_in_4bit: false +load_in_8bit: true +lora_alpha: 256 +lora_dropout: 0.1 +lora_r: 128 +lora_target_modules: +- q_proj +- v_proj +- k_proj +- o_proj +- gate_proj +- down_proj +- up_proj +loraplus_lr_embedding: 1.0e-06 +lr_scheduler: cosine +max_prompt_len: 512 +mean_resizing_embeddings: false +micro_batch_size: 16 +num_epochs: 30.0 +optimizer: adamw_bnb_8bit +output_dir: ./outputs/test3 +pretrain_multipack_attn: true +pretrain_multipack_buffer_size: 10000 +qlora_sharded_model_loading: false +ray_num_workers: 1 +resources_per_worker: + GPU: 1 +sample_packing_bin_size: 200 +sample_packing_group_size: 100000 +save_only_model: false +save_safetensors: true +sequence_len: 2048 +shuffle_merged_datasets: true +skip_prepare_dataset: false +strict: false +train_on_inputs: false +trl: + log_completions: false + ref_model_mixup_alpha: 0.9 + ref_model_sync_steps: 64 + sync_ref_model: false + use_vllm: false + vllm_device: auto + vllm_dtype: auto + vllm_gpu_memory_utilization: 0.9 +use_ray: false +val_set_size: 0.0 +weight_decay: 0.01 + + +``` + +

+ +# outputs/test3 + +This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the frjonah/training_data5 dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 2e-05 +- train_batch_size: 16 +- eval_batch_size: 16 +- seed: 42 +- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 12 +- training_steps: 402 + +### Training results + + + +### Framework versions + +- PEFT 0.15.2 +- Transformers 4.52.3 +- Pytorch 2.6.0+cu124 +- Datasets 3.6.0 +- Tokenizers 0.21.1 \ No newline at end of file diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0903ea87f348df7f18650f0467f8051ebdd53938 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "corda_config": null, + "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": 256, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 128, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "up_proj", + "q_proj", + "o_proj", + "k_proj", + "down_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "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..b95539507d87439df973cf5055af06d60a06d40a --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ec6c916b9df77c8ab3fd504fae3a8cab10f1c25a8425cfc726a8fd5ebde9e1 +size 1728658208 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..923ec253c8dbefbb41cf084db7251df41d000f6d --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{{ 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 + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/checkpoint-364/README.md b/checkpoint-364/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ae0ed615fe362734126a5801320301bdfc158e46 --- /dev/null +++ b/checkpoint-364/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.15.2 \ No newline at end of file diff --git a/checkpoint-364/adapter_config.json b/checkpoint-364/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0903ea87f348df7f18650f0467f8051ebdd53938 --- /dev/null +++ b/checkpoint-364/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "corda_config": null, + "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": 256, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 128, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "up_proj", + "q_proj", + "o_proj", + "k_proj", + "down_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-364/adapter_model.safetensors b/checkpoint-364/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..948d17e2f3147c2d5acc2170436413a829165208 --- /dev/null +++ b/checkpoint-364/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5638f462c3637131475e2d28b21ff1bfede227d80cf1bd3243242c788fc39f84 +size 1728658208 diff --git a/checkpoint-364/chat_template.jinja b/checkpoint-364/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..923ec253c8dbefbb41cf084db7251df41d000f6d --- /dev/null +++ b/checkpoint-364/chat_template.jinja @@ -0,0 +1,4 @@ +{{ 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 + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/checkpoint-364/optimizer.pt b/checkpoint-364/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6db996c509de248450781e5bd2a3421cee6b9c08 --- /dev/null +++ b/checkpoint-364/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13823912688df31f1d91020dfc9906e582bbfe663fd07a9c653b78e72909eca4 +size 878485380 diff --git a/checkpoint-364/rng_state.pth b/checkpoint-364/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..0643d22a82f873ac737defc0051cfd1495a2b75b --- /dev/null +++ b/checkpoint-364/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d151d766c1e22a5f4d617eaa7fe207928f3a5abf646ecbc92d74dc94674e8f +size 14244 diff --git a/checkpoint-364/scheduler.pt b/checkpoint-364/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c077870c0fe1166314e693b57964d6ed144199e3 --- /dev/null +++ b/checkpoint-364/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcaf3bdb117793ebbb6a2f3141d28d45642ce8f4e3dfef03baa2b00144105ce +size 1064 diff --git a/checkpoint-364/special_tokens_map.json b/checkpoint-364/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-364/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-364/tokenizer.json b/checkpoint-364/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-364/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-364/tokenizer.model b/checkpoint-364/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-364/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-364/tokenizer_config.json b/checkpoint-364/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3ade6be57196932063a48c1329fbf9c2e7e154d1 --- /dev/null +++ b/checkpoint-364/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

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

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

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

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

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "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-364/trainer_state.json b/checkpoint-364/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..0b1ea8aa0889cff3c40bbf164551b2487eadde5e --- /dev/null +++ b/checkpoint-364/trainer_state.json @@ -0,0 +1,1308 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 26.0, + "eval_steps": 500, + "global_step": 364, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.14285714285714285, + "grad_norm": 49.90940856933594, + "learning_rate": 1.6666666666666667e-06, + "loss": 6.0076, + "step": 2 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 44.15715789794922, + "learning_rate": 5e-06, + "loss": 5.6559, + "step": 4 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 56.16670608520508, + "learning_rate": 8.333333333333334e-06, + "loss": 4.4368, + "step": 6 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 23.919437408447266, + "learning_rate": 1.1666666666666668e-05, + "loss": 2.7657, + "step": 8 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 20.757640838623047, + "learning_rate": 1.5000000000000002e-05, + "loss": 2.3404, + "step": 10 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 16.067575454711914, + "learning_rate": 1.8333333333333333e-05, + "loss": 2.038, + "step": 12 + }, + { + "epoch": 1.0, + "grad_norm": 23.458139419555664, + "learning_rate": 1.9999675557165282e-05, + "loss": 1.5809, + "step": 14 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 11.104408264160156, + "learning_rate": 1.9997080140801932e-05, + "loss": 1.1148, + "step": 16 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 11.328217506408691, + "learning_rate": 1.9991889981715696e-05, + "loss": 1.2528, + "step": 18 + }, + { + "epoch": 1.4285714285714286, + "grad_norm": 12.313949584960938, + "learning_rate": 1.9984106427012667e-05, + "loss": 1.2324, + "step": 20 + }, + { + "epoch": 1.5714285714285714, + "grad_norm": 10.425058364868164, + "learning_rate": 1.9973731496914914e-05, + "loss": 1.0203, + "step": 22 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 12.36324691772461, + "learning_rate": 1.9960767884236132e-05, + "loss": 1.0997, + "step": 24 + }, + { + "epoch": 1.8571428571428572, + "grad_norm": 14.280921936035156, + "learning_rate": 1.9945218953682736e-05, + "loss": 1.43, + "step": 26 + }, + { + "epoch": 2.0, + "grad_norm": 20.082475662231445, + "learning_rate": 1.992708874098054e-05, + "loss": 1.0748, + "step": 28 + }, + { + "epoch": 2.142857142857143, + "grad_norm": 5.667484283447266, + "learning_rate": 1.9906381951827295e-05, + "loss": 0.3794, + "step": 30 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 6.214536666870117, + "learning_rate": 1.9883103960671305e-05, + "loss": 0.2747, + "step": 32 + }, + { + "epoch": 2.4285714285714284, + "grad_norm": 6.836840629577637, + "learning_rate": 1.985726080931651e-05, + "loss": 0.2568, + "step": 34 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 13.044551849365234, + "learning_rate": 1.9828859205354326e-05, + "loss": 0.2937, + "step": 36 + }, + { + "epoch": 2.7142857142857144, + "grad_norm": 8.866482734680176, + "learning_rate": 1.979790652042268e-05, + "loss": 0.4252, + "step": 38 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 8.709479331970215, + "learning_rate": 1.9764410788292724e-05, + "loss": 0.3599, + "step": 40 + }, + { + "epoch": 3.0, + "grad_norm": 9.43436050415039, + "learning_rate": 1.9728380702783644e-05, + "loss": 0.3578, + "step": 42 + }, + { + "epoch": 3.142857142857143, + "grad_norm": 1.2470844984054565, + "learning_rate": 1.968982561550621e-05, + "loss": 0.1155, + "step": 44 + }, + { + "epoch": 3.2857142857142856, + "grad_norm": 5.716163635253906, + "learning_rate": 1.9648755533435517e-05, + "loss": 0.0708, + "step": 46 + }, + { + "epoch": 3.4285714285714284, + "grad_norm": 6.77197790145874, + "learning_rate": 1.9605181116313725e-05, + "loss": 0.081, + "step": 48 + }, + { + "epoch": 3.571428571428571, + "grad_norm": 5.336516380310059, + "learning_rate": 1.955911367388329e-05, + "loss": 0.112, + "step": 50 + }, + { + "epoch": 3.7142857142857144, + "grad_norm": 10.314866065979004, + "learning_rate": 1.9510565162951538e-05, + "loss": 0.0958, + "step": 52 + }, + { + "epoch": 3.857142857142857, + "grad_norm": 5.841635704040527, + "learning_rate": 1.9459548184287254e-05, + "loss": 0.0593, + "step": 54 + }, + { + "epoch": 4.0, + "grad_norm": 10.58973503112793, + "learning_rate": 1.9406075979350175e-05, + "loss": 0.2013, + "step": 56 + }, + { + "epoch": 4.142857142857143, + "grad_norm": 3.521483898162842, + "learning_rate": 1.9350162426854152e-05, + "loss": 0.0563, + "step": 58 + }, + { + "epoch": 4.285714285714286, + "grad_norm": 1.0017471313476562, + "learning_rate": 1.9291822039164934e-05, + "loss": 0.1029, + "step": 60 + }, + { + "epoch": 4.428571428571429, + "grad_norm": 0.33161500096321106, + "learning_rate": 1.923106995853349e-05, + "loss": 0.024, + "step": 62 + }, + { + "epoch": 4.571428571428571, + "grad_norm": 6.284483432769775, + "learning_rate": 1.9167921953165827e-05, + "loss": 0.1092, + "step": 64 + }, + { + "epoch": 4.714285714285714, + "grad_norm": 3.3121423721313477, + "learning_rate": 1.9102394413130348e-05, + "loss": 0.0401, + "step": 66 + }, + { + "epoch": 4.857142857142857, + "grad_norm": 8.295348167419434, + "learning_rate": 1.9034504346103825e-05, + "loss": 0.3237, + "step": 68 + }, + { + "epoch": 5.0, + "grad_norm": 2.1199071407318115, + "learning_rate": 1.896426937295704e-05, + "loss": 0.0375, + "step": 70 + }, + { + "epoch": 5.142857142857143, + "grad_norm": 0.45601171255111694, + "learning_rate": 1.8891707723181294e-05, + "loss": 0.0319, + "step": 72 + }, + { + "epoch": 5.285714285714286, + "grad_norm": 1.0054666996002197, + "learning_rate": 1.881683823015694e-05, + "loss": 0.0097, + "step": 74 + }, + { + "epoch": 5.428571428571429, + "grad_norm": 0.8899504542350769, + "learning_rate": 1.873968032626518e-05, + "loss": 0.0769, + "step": 76 + }, + { + "epoch": 5.571428571428571, + "grad_norm": 0.49617600440979004, + "learning_rate": 1.866025403784439e-05, + "loss": 0.0479, + "step": 78 + }, + { + "epoch": 5.714285714285714, + "grad_norm": 0.16562028229236603, + "learning_rate": 1.8578579979992266e-05, + "loss": 0.0051, + "step": 80 + }, + { + "epoch": 5.857142857142857, + "grad_norm": 11.048959732055664, + "learning_rate": 1.8494679351215212e-05, + "loss": 0.0984, + "step": 82 + }, + { + "epoch": 6.0, + "grad_norm": 7.846388816833496, + "learning_rate": 1.8408573927926225e-05, + "loss": 0.116, + "step": 84 + }, + { + "epoch": 6.142857142857143, + "grad_norm": 0.11113756895065308, + "learning_rate": 1.8320286058792845e-05, + "loss": 0.0027, + "step": 86 + }, + { + "epoch": 6.285714285714286, + "grad_norm": 3.4302117824554443, + "learning_rate": 1.8229838658936566e-05, + "loss": 0.0197, + "step": 88 + }, + { + "epoch": 6.428571428571429, + "grad_norm": 4.105597496032715, + "learning_rate": 1.81372552039852e-05, + "loss": 0.1183, + "step": 90 + }, + { + "epoch": 6.571428571428571, + "grad_norm": 3.2223429679870605, + "learning_rate": 1.804255972397977e-05, + "loss": 0.006, + "step": 92 + }, + { + "epoch": 6.714285714285714, + "grad_norm": 4.856196403503418, + "learning_rate": 1.7945776797137544e-05, + "loss": 0.0062, + "step": 94 + }, + { + "epoch": 6.857142857142857, + "grad_norm": 1.22345769405365, + "learning_rate": 1.7846931543472722e-05, + "loss": 0.0037, + "step": 96 + }, + { + "epoch": 7.0, + "grad_norm": 8.841476440429688, + "learning_rate": 1.7746049618276545e-05, + "loss": 0.0885, + "step": 98 + }, + { + "epoch": 7.142857142857143, + "grad_norm": 1.7171941995620728, + "learning_rate": 1.7643157205458483e-05, + "loss": 0.0732, + "step": 100 + }, + { + "epoch": 7.285714285714286, + "grad_norm": 0.2902078628540039, + "learning_rate": 1.753828101075017e-05, + "loss": 0.0019, + "step": 102 + }, + { + "epoch": 7.428571428571429, + "grad_norm": 6.003970623016357, + "learning_rate": 1.7431448254773943e-05, + "loss": 0.0219, + "step": 104 + }, + { + "epoch": 7.571428571428571, + "grad_norm": 0.211229145526886, + "learning_rate": 1.7322686665977738e-05, + "loss": 0.0014, + "step": 106 + }, + { + "epoch": 7.714285714285714, + "grad_norm": 14.436793327331543, + "learning_rate": 1.7212024473438145e-05, + "loss": 0.1415, + "step": 108 + }, + { + "epoch": 7.857142857142857, + "grad_norm": 0.05790628120303154, + "learning_rate": 1.7099490399533583e-05, + "loss": 0.0008, + "step": 110 + }, + { + "epoch": 8.0, + "grad_norm": 0.17556001245975494, + "learning_rate": 1.6985113652489374e-05, + "loss": 0.0044, + "step": 112 + }, + { + "epoch": 8.142857142857142, + "grad_norm": 0.38069918751716614, + "learning_rate": 1.6868923918796753e-05, + "loss": 0.001, + "step": 114 + }, + { + "epoch": 8.285714285714286, + "grad_norm": 0.093246690928936, + "learning_rate": 1.6750951355507763e-05, + "loss": 0.0321, + "step": 116 + }, + { + "epoch": 8.428571428571429, + "grad_norm": 0.15035825967788696, + "learning_rate": 1.6631226582407954e-05, + "loss": 0.0036, + "step": 118 + }, + { + "epoch": 8.571428571428571, + "grad_norm": 0.06252682954072952, + "learning_rate": 1.650978067406904e-05, + "loss": 0.0035, + "step": 120 + }, + { + "epoch": 8.714285714285714, + "grad_norm": 6.229085922241211, + "learning_rate": 1.638664515178348e-05, + "loss": 0.1034, + "step": 122 + }, + { + "epoch": 8.857142857142858, + "grad_norm": 2.403806686401367, + "learning_rate": 1.626185197538314e-05, + "loss": 0.036, + "step": 124 + }, + { + "epoch": 9.0, + "grad_norm": 0.07740367949008942, + "learning_rate": 1.613543353494409e-05, + "loss": 0.0006, + "step": 126 + }, + { + "epoch": 9.142857142857142, + "grad_norm": 0.322050541639328, + "learning_rate": 1.600742264237979e-05, + "loss": 0.0013, + "step": 128 + }, + { + "epoch": 9.285714285714286, + "grad_norm": 0.1652839183807373, + "learning_rate": 1.5877852522924733e-05, + "loss": 0.0008, + "step": 130 + }, + { + "epoch": 9.428571428571429, + "grad_norm": 0.048877034336328506, + "learning_rate": 1.574675680651084e-05, + "loss": 0.0008, + "step": 132 + }, + { + "epoch": 9.571428571428571, + "grad_norm": 0.06231057271361351, + "learning_rate": 1.561416951903881e-05, + "loss": 0.0022, + "step": 134 + }, + { + "epoch": 9.714285714285714, + "grad_norm": 0.03611210733652115, + "learning_rate": 1.5480125073546705e-05, + "loss": 0.0389, + "step": 136 + }, + { + "epoch": 9.857142857142858, + "grad_norm": 0.52008056640625, + "learning_rate": 1.5344658261278013e-05, + "loss": 0.0089, + "step": 138 + }, + { + "epoch": 10.0, + "grad_norm": 0.42384108901023865, + "learning_rate": 1.5207804242651625e-05, + "loss": 0.0015, + "step": 140 + }, + { + "epoch": 10.142857142857142, + "grad_norm": 0.055933400988578796, + "learning_rate": 1.5069598538135905e-05, + "loss": 0.0004, + "step": 142 + }, + { + "epoch": 10.285714285714286, + "grad_norm": 0.0212051160633564, + "learning_rate": 1.4930077019029376e-05, + "loss": 0.0072, + "step": 144 + }, + { + "epoch": 10.428571428571429, + "grad_norm": 0.03581853583455086, + "learning_rate": 1.4789275898150309e-05, + "loss": 0.0006, + "step": 146 + }, + { + "epoch": 10.571428571428571, + "grad_norm": 0.021400820463895798, + "learning_rate": 1.4647231720437687e-05, + "loss": 0.0005, + "step": 148 + }, + { + "epoch": 10.714285714285714, + "grad_norm": 1.3550739288330078, + "learning_rate": 1.450398135346597e-05, + "loss": 0.0332, + "step": 150 + }, + { + "epoch": 10.857142857142858, + "grad_norm": 0.014044591225683689, + "learning_rate": 1.4359561977876102e-05, + "loss": 0.0003, + "step": 152 + }, + { + "epoch": 11.0, + "grad_norm": 0.056435056030750275, + "learning_rate": 1.4214011077725293e-05, + "loss": 0.0004, + "step": 154 + }, + { + "epoch": 11.142857142857142, + "grad_norm": 0.012104465626180172, + "learning_rate": 1.4067366430758004e-05, + "loss": 0.0214, + "step": 156 + }, + { + "epoch": 11.285714285714286, + "grad_norm": 0.022569801658391953, + "learning_rate": 1.3919666098600753e-05, + "loss": 0.0003, + "step": 158 + }, + { + "epoch": 11.428571428571429, + "grad_norm": 0.019581535831093788, + "learning_rate": 1.3770948416883205e-05, + "loss": 0.0003, + "step": 160 + }, + { + "epoch": 11.571428571428571, + "grad_norm": 0.012900936417281628, + "learning_rate": 1.362125198528817e-05, + "loss": 0.0003, + "step": 162 + }, + { + "epoch": 11.714285714285714, + "grad_norm": 0.283460795879364, + "learning_rate": 1.347061565753303e-05, + "loss": 0.0151, + "step": 164 + }, + { + "epoch": 11.857142857142858, + "grad_norm": 0.02773939073085785, + "learning_rate": 1.3319078531285286e-05, + "loss": 0.0002, + "step": 166 + }, + { + "epoch": 12.0, + "grad_norm": 0.015381716191768646, + "learning_rate": 1.3166679938014728e-05, + "loss": 0.0002, + "step": 168 + }, + { + "epoch": 12.142857142857142, + "grad_norm": 0.013684879057109356, + "learning_rate": 1.301345943278496e-05, + "loss": 0.0002, + "step": 170 + }, + { + "epoch": 12.285714285714286, + "grad_norm": 0.011124438606202602, + "learning_rate": 1.2859456783986892e-05, + "loss": 0.0002, + "step": 172 + }, + { + "epoch": 12.428571428571429, + "grad_norm": 0.2694200873374939, + "learning_rate": 1.270471196301684e-05, + "loss": 0.0059, + "step": 174 + }, + { + "epoch": 12.571428571428571, + "grad_norm": 0.25839900970458984, + "learning_rate": 1.2549265133901934e-05, + "loss": 0.007, + "step": 176 + }, + { + "epoch": 12.714285714285714, + "grad_norm": 0.28028616309165955, + "learning_rate": 1.2393156642875579e-05, + "loss": 0.0081, + "step": 178 + }, + { + "epoch": 12.857142857142858, + "grad_norm": 0.007691177539527416, + "learning_rate": 1.2236427007905558e-05, + "loss": 0.0004, + "step": 180 + }, + { + "epoch": 13.0, + "grad_norm": 0.03421185538172722, + "learning_rate": 1.2079116908177592e-05, + "loss": 0.0002, + "step": 182 + }, + { + "epoch": 13.142857142857142, + "grad_norm": 0.21886347234249115, + "learning_rate": 1.1921267173537085e-05, + "loss": 0.0106, + "step": 184 + }, + { + "epoch": 13.285714285714286, + "grad_norm": 0.12066204100847244, + "learning_rate": 1.1762918773891691e-05, + "loss": 0.0039, + "step": 186 + }, + { + "epoch": 13.428571428571429, + "grad_norm": 0.009790458716452122, + "learning_rate": 1.1604112808577603e-05, + "loss": 0.0001, + "step": 188 + }, + { + "epoch": 13.571428571428571, + "grad_norm": 0.006134828552603722, + "learning_rate": 1.1444890495692214e-05, + "loss": 0.0001, + "step": 190 + }, + { + "epoch": 13.714285714285714, + "grad_norm": 0.007279029581695795, + "learning_rate": 1.1285293161395948e-05, + "loss": 0.0082, + "step": 192 + }, + { + "epoch": 13.857142857142858, + "grad_norm": 0.007834681309759617, + "learning_rate": 1.1125362229186056e-05, + "loss": 0.0001, + "step": 194 + }, + { + "epoch": 14.0, + "grad_norm": 0.011400113813579082, + "learning_rate": 1.0965139209145153e-05, + "loss": 0.0001, + "step": 196 + }, + { + "epoch": 14.142857142857142, + "grad_norm": 0.005645982455462217, + "learning_rate": 1.0804665687167262e-05, + "loss": 0.0001, + "step": 198 + }, + { + "epoch": 14.285714285714286, + "grad_norm": 0.007113787345588207, + "learning_rate": 1.0643983314164195e-05, + "loss": 0.0046, + "step": 200 + }, + { + "epoch": 14.428571428571429, + "grad_norm": 0.00671082129701972, + "learning_rate": 1.0483133795255072e-05, + "loss": 0.0001, + "step": 202 + }, + { + "epoch": 14.571428571428571, + "grad_norm": 0.10411105304956436, + "learning_rate": 1.0322158878941733e-05, + "loss": 0.0092, + "step": 204 + }, + { + "epoch": 14.714285714285714, + "grad_norm": 0.007047938648611307, + "learning_rate": 1.0161100346272913e-05, + "loss": 0.0046, + "step": 206 + }, + { + "epoch": 14.857142857142858, + "grad_norm": 0.006609996780753136, + "learning_rate": 1e-05, + "loss": 0.0001, + "step": 208 + }, + { + "epoch": 15.0, + "grad_norm": 0.00515047088265419, + "learning_rate": 9.838899653727088e-06, + "loss": 0.0001, + "step": 210 + }, + { + "epoch": 15.142857142857142, + "grad_norm": 0.005954743828624487, + "learning_rate": 9.677841121058274e-06, + "loss": 0.0001, + "step": 212 + }, + { + "epoch": 15.285714285714286, + "grad_norm": 0.19431306421756744, + "learning_rate": 9.516866204744932e-06, + "loss": 0.0046, + "step": 214 + }, + { + "epoch": 15.428571428571429, + "grad_norm": 0.007638772018253803, + "learning_rate": 9.356016685835807e-06, + "loss": 0.0045, + "step": 216 + }, + { + "epoch": 15.571428571428571, + "grad_norm": 0.10914219170808792, + "learning_rate": 9.195334312832742e-06, + "loss": 0.0092, + "step": 218 + }, + { + "epoch": 15.714285714285714, + "grad_norm": 0.005956027191132307, + "learning_rate": 9.034860790854848e-06, + "loss": 0.0001, + "step": 220 + }, + { + "epoch": 15.857142857142858, + "grad_norm": 0.006127700675278902, + "learning_rate": 8.874637770813947e-06, + "loss": 0.0001, + "step": 222 + }, + { + "epoch": 16.0, + "grad_norm": 0.006942708045244217, + "learning_rate": 8.714706838604056e-06, + "loss": 0.0001, + "step": 224 + }, + { + "epoch": 16.142857142857142, + "grad_norm": 0.17752425372600555, + "learning_rate": 8.55510950430779e-06, + "loss": 0.0098, + "step": 226 + }, + { + "epoch": 16.285714285714285, + "grad_norm": 0.004300012718886137, + "learning_rate": 8.395887191422397e-06, + "loss": 0.0001, + "step": 228 + }, + { + "epoch": 16.428571428571427, + "grad_norm": 0.0063268570229411125, + "learning_rate": 8.23708122610831e-06, + "loss": 0.0075, + "step": 230 + }, + { + "epoch": 16.571428571428573, + "grad_norm": 0.005733097437769175, + "learning_rate": 8.078732826462917e-06, + "loss": 0.0001, + "step": 232 + }, + { + "epoch": 16.714285714285715, + "grad_norm": 0.0077501749619841576, + "learning_rate": 7.92088309182241e-06, + "loss": 0.0001, + "step": 234 + }, + { + "epoch": 16.857142857142858, + "grad_norm": 0.005072280764579773, + "learning_rate": 7.763572992094448e-06, + "loss": 0.0001, + "step": 236 + }, + { + "epoch": 17.0, + "grad_norm": 0.007300873752683401, + "learning_rate": 7.606843357124426e-06, + "loss": 0.0001, + "step": 238 + }, + { + "epoch": 17.142857142857142, + "grad_norm": 0.10978183150291443, + "learning_rate": 7.450734866098066e-06, + "loss": 0.0036, + "step": 240 + }, + { + "epoch": 17.285714285714285, + "grad_norm": 0.005480973981320858, + "learning_rate": 7.2952880369831635e-06, + "loss": 0.0061, + "step": 242 + }, + { + "epoch": 17.428571428571427, + "grad_norm": 0.2027699053287506, + "learning_rate": 7.140543216013109e-06, + "loss": 0.0035, + "step": 244 + }, + { + "epoch": 17.571428571428573, + "grad_norm": 0.0048587811179459095, + "learning_rate": 6.986540567215043e-06, + "loss": 0.0001, + "step": 246 + }, + { + "epoch": 17.714285714285715, + "grad_norm": 0.005718125496059656, + "learning_rate": 6.833320061985278e-06, + "loss": 0.0001, + "step": 248 + }, + { + "epoch": 17.857142857142858, + "grad_norm": 0.0035847134422510862, + "learning_rate": 6.680921468714718e-06, + "loss": 0.0052, + "step": 250 + }, + { + "epoch": 18.0, + "grad_norm": 0.0035746165085583925, + "learning_rate": 6.529384342466971e-06, + "loss": 0.0001, + "step": 252 + }, + { + "epoch": 18.142857142857142, + "grad_norm": 0.00451216846704483, + "learning_rate": 6.378748014711834e-06, + "loss": 0.0001, + "step": 254 + }, + { + "epoch": 18.285714285714285, + "grad_norm": 0.004890494979918003, + "learning_rate": 6.229051583116796e-06, + "loss": 0.0001, + "step": 256 + }, + { + "epoch": 18.428571428571427, + "grad_norm": 0.004625991452485323, + "learning_rate": 6.080333901399252e-06, + "loss": 0.0058, + "step": 258 + }, + { + "epoch": 18.571428571428573, + "grad_norm": 0.005847033113241196, + "learning_rate": 5.932633569242e-06, + "loss": 0.0001, + "step": 260 + }, + { + "epoch": 18.714285714285715, + "grad_norm": 0.006245823111385107, + "learning_rate": 5.785988922274711e-06, + "loss": 0.0072, + "step": 262 + }, + { + "epoch": 18.857142857142858, + "grad_norm": 0.08823557943105698, + "learning_rate": 5.640438022123898e-06, + "loss": 0.0034, + "step": 264 + }, + { + "epoch": 19.0, + "grad_norm": 0.004038456827402115, + "learning_rate": 5.496018646534032e-06, + "loss": 0.0001, + "step": 266 + }, + { + "epoch": 19.142857142857142, + "grad_norm": 0.005825538653880358, + "learning_rate": 5.352768279562315e-06, + "loss": 0.0056, + "step": 268 + }, + { + "epoch": 19.285714285714285, + "grad_norm": 0.004666970111429691, + "learning_rate": 5.210724101849696e-06, + "loss": 0.0001, + "step": 270 + }, + { + "epoch": 19.428571428571427, + "grad_norm": 0.004332971293479204, + "learning_rate": 5.069922980970626e-06, + "loss": 0.0001, + "step": 272 + }, + { + "epoch": 19.571428571428573, + "grad_norm": 0.09540804475545883, + "learning_rate": 4.930401461864099e-06, + "loss": 0.0085, + "step": 274 + }, + { + "epoch": 19.714285714285715, + "grad_norm": 0.004319526720792055, + "learning_rate": 4.7921957573483756e-06, + "loss": 0.0001, + "step": 276 + }, + { + "epoch": 19.857142857142858, + "grad_norm": 0.00582715030759573, + "learning_rate": 4.655341738721989e-06, + "loss": 0.0001, + "step": 278 + }, + { + "epoch": 20.0, + "grad_norm": 0.005314113572239876, + "learning_rate": 4.519874926453303e-06, + "loss": 0.0001, + "step": 280 + }, + { + "epoch": 20.142857142857142, + "grad_norm": 0.006195093505084515, + "learning_rate": 4.385830480961192e-06, + "loss": 0.0001, + "step": 282 + }, + { + "epoch": 20.285714285714285, + "grad_norm": 0.004151402972638607, + "learning_rate": 4.2532431934891646e-06, + "loss": 0.0001, + "step": 284 + }, + { + "epoch": 20.428571428571427, + "grad_norm": 0.004392064176499844, + "learning_rate": 4.12214747707527e-06, + "loss": 0.0047, + "step": 286 + }, + { + "epoch": 20.571428571428573, + "grad_norm": 0.004756106063723564, + "learning_rate": 3.99257735762021e-06, + "loss": 0.0001, + "step": 288 + }, + { + "epoch": 20.714285714285715, + "grad_norm": 0.004611567594110966, + "learning_rate": 3.864566465055913e-06, + "loss": 0.0022, + "step": 290 + }, + { + "epoch": 20.857142857142858, + "grad_norm": 0.004500643815845251, + "learning_rate": 3.738148024616863e-06, + "loss": 0.0001, + "step": 292 + }, + { + "epoch": 21.0, + "grad_norm": 0.0058865793980658054, + "learning_rate": 3.6133548482165225e-06, + "loss": 0.0081, + "step": 294 + }, + { + "epoch": 21.142857142857142, + "grad_norm": 0.096845842897892, + "learning_rate": 3.4902193259309627e-06, + "loss": 0.0037, + "step": 296 + }, + { + "epoch": 21.285714285714285, + "grad_norm": 0.0038972089532762766, + "learning_rate": 3.3687734175920505e-06, + "loss": 0.0001, + "step": 298 + }, + { + "epoch": 21.428571428571427, + "grad_norm": 0.004685294348746538, + "learning_rate": 3.2490486444922396e-06, + "loss": 0.0001, + "step": 300 + }, + { + "epoch": 21.571428571428573, + "grad_norm": 0.20793084800243378, + "learning_rate": 3.131076081203247e-06, + "loss": 0.0019, + "step": 302 + }, + { + "epoch": 21.714285714285715, + "grad_norm": 0.0035532894544303417, + "learning_rate": 3.0148863475106315e-06, + "loss": 0.0058, + "step": 304 + }, + { + "epoch": 21.857142857142858, + "grad_norm": 0.2300863116979599, + "learning_rate": 2.900509600466418e-06, + "loss": 0.0025, + "step": 306 + }, + { + "epoch": 22.0, + "grad_norm": 0.007288255728781223, + "learning_rate": 2.7879755265618558e-06, + "loss": 0.0001, + "step": 308 + }, + { + "epoch": 22.142857142857142, + "grad_norm": 0.005309649743139744, + "learning_rate": 2.6773133340222677e-06, + "loss": 0.0016, + "step": 310 + }, + { + "epoch": 22.285714285714285, + "grad_norm": 0.003941751550883055, + "learning_rate": 2.5685517452260566e-06, + "loss": 0.0001, + "step": 312 + }, + { + "epoch": 22.428571428571427, + "grad_norm": 0.004016744904220104, + "learning_rate": 2.4617189892498326e-06, + "loss": 0.0001, + "step": 314 + }, + { + "epoch": 22.571428571428573, + "grad_norm": 0.13147950172424316, + "learning_rate": 2.3568427945415163e-06, + "loss": 0.0064, + "step": 316 + }, + { + "epoch": 22.714285714285715, + "grad_norm": 0.003918132279068232, + "learning_rate": 2.2539503817234553e-06, + "loss": 0.0001, + "step": 318 + }, + { + "epoch": 22.857142857142858, + "grad_norm": 0.004725574050098658, + "learning_rate": 2.153068456527283e-06, + "loss": 0.0001, + "step": 320 + }, + { + "epoch": 23.0, + "grad_norm": 0.3711271584033966, + "learning_rate": 2.0542232028624585e-06, + "loss": 0.0175, + "step": 322 + }, + { + "epoch": 23.142857142857142, + "grad_norm": 0.18150761723518372, + "learning_rate": 1.9574402760202315e-06, + "loss": 0.0023, + "step": 324 + }, + { + "epoch": 23.285714285714285, + "grad_norm": 0.13696324825286865, + "learning_rate": 1.8627447960148036e-06, + "loss": 0.0045, + "step": 326 + }, + { + "epoch": 23.428571428571427, + "grad_norm": 0.004304251167923212, + "learning_rate": 1.7701613410634367e-06, + "loss": 0.0001, + "step": 328 + }, + { + "epoch": 23.571428571428573, + "grad_norm": 0.005392234306782484, + "learning_rate": 1.6797139412071583e-06, + "loss": 0.0001, + "step": 330 + }, + { + "epoch": 23.714285714285715, + "grad_norm": 0.004501474089920521, + "learning_rate": 1.5914260720737796e-06, + "loss": 0.0001, + "step": 332 + }, + { + "epoch": 23.857142857142858, + "grad_norm": 0.0033914605155587196, + "learning_rate": 1.5053206487847916e-06, + "loss": 0.0047, + "step": 334 + }, + { + "epoch": 24.0, + "grad_norm": 0.005722349975258112, + "learning_rate": 1.4214200200077343e-06, + "loss": 0.0001, + "step": 336 + }, + { + "epoch": 24.142857142857142, + "grad_norm": 0.0028757653199136257, + "learning_rate": 1.339745962155613e-06, + "loss": 0.0001, + "step": 338 + }, + { + "epoch": 24.285714285714285, + "grad_norm": 0.004367240238934755, + "learning_rate": 1.2603196737348211e-06, + "loss": 0.0012, + "step": 340 + }, + { + "epoch": 24.428571428571427, + "grad_norm": 0.004103364888578653, + "learning_rate": 1.1831617698430609e-06, + "loss": 0.0001, + "step": 342 + }, + { + "epoch": 24.571428571428573, + "grad_norm": 0.12380176037549973, + "learning_rate": 1.1082922768187098e-06, + "loss": 0.0053, + "step": 344 + }, + { + "epoch": 24.714285714285715, + "grad_norm": 0.11978839337825775, + "learning_rate": 1.0357306270429623e-06, + "loss": 0.0045, + "step": 346 + }, + { + "epoch": 24.857142857142858, + "grad_norm": 0.15920782089233398, + "learning_rate": 9.65495653896179e-07, + "loss": 0.0008, + "step": 348 + }, + { + "epoch": 25.0, + "grad_norm": 0.005539704114198685, + "learning_rate": 8.976055868696543e-07, + "loss": 0.0001, + "step": 350 + }, + { + "epoch": 25.142857142857142, + "grad_norm": 0.004604020155966282, + "learning_rate": 8.320780468341761e-07, + "loss": 0.0001, + "step": 352 + }, + { + "epoch": 25.285714285714285, + "grad_norm": 0.19128715991973877, + "learning_rate": 7.689300414665124e-07, + "loss": 0.0012, + "step": 354 + }, + { + "epoch": 25.428571428571427, + "grad_norm": 0.0033012081403285265, + "learning_rate": 7.08177960835068e-07, + "loss": 0.0067, + "step": 356 + }, + { + "epoch": 25.571428571428573, + "grad_norm": 0.09938196837902069, + "learning_rate": 6.498375731458529e-07, + "loss": 0.0005, + "step": 358 + }, + { + "epoch": 25.714285714285715, + "grad_norm": 0.0049908701330423355, + "learning_rate": 5.939240206498287e-07, + "loss": 0.0001, + "step": 360 + }, + { + "epoch": 25.857142857142858, + "grad_norm": 0.0035182549618184566, + "learning_rate": 5.404518157127481e-07, + "loss": 0.0046, + "step": 362 + }, + { + "epoch": 26.0, + "grad_norm": 0.0068074483424425125, + "learning_rate": 4.894348370484648e-07, + "loss": 0.0001, + "step": 364 + } + ], + "logging_steps": 2, + "max_steps": 402, + "num_input_tokens_seen": 0, + "num_train_epochs": 29, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.870859949755597e+16, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-364/training_args.bin b/checkpoint-364/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5e40431601fe0fda63821c355ca2518b79c42df --- /dev/null +++ b/checkpoint-364/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25a0ccf5317ebd8f7cfcaefcfdfd3860c0c2887188910c19a4b9dde7e5910b1 +size 6520 diff --git a/checkpoint-378/README.md b/checkpoint-378/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ae0ed615fe362734126a5801320301bdfc158e46 --- /dev/null +++ b/checkpoint-378/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.15.2 \ No newline at end of file diff --git a/checkpoint-378/adapter_config.json b/checkpoint-378/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0903ea87f348df7f18650f0467f8051ebdd53938 --- /dev/null +++ b/checkpoint-378/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "corda_config": null, + "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": 256, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 128, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "up_proj", + "q_proj", + "o_proj", + "k_proj", + "down_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-378/adapter_model.safetensors b/checkpoint-378/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..708a29c3d58f87ea94e95797e6038cfdbd9dd42d --- /dev/null +++ b/checkpoint-378/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d57d7be7ecde770b3c8a1f0cb45ba73f78a00da3c7f43e0ead62d0c964be10 +size 1728658208 diff --git a/checkpoint-378/chat_template.jinja b/checkpoint-378/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..923ec253c8dbefbb41cf084db7251df41d000f6d --- /dev/null +++ b/checkpoint-378/chat_template.jinja @@ -0,0 +1,4 @@ +{{ 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 + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/checkpoint-378/optimizer.pt b/checkpoint-378/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0c6deb0d2c90b2466d411e4bf4f35fd1efa6a77 --- /dev/null +++ b/checkpoint-378/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ef831bc0ec7d83bdee9e282d47543219f27dac48d3b377fdaed58051b8efaf +size 878485380 diff --git a/checkpoint-378/rng_state.pth b/checkpoint-378/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9c4e563c7aeed424e7bdb9dc7484be8bcc835e5 --- /dev/null +++ b/checkpoint-378/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df028dd870144b3727e9334d05ace57fa20141f3e70469d247d178767f6726f +size 14244 diff --git a/checkpoint-378/scheduler.pt b/checkpoint-378/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6f03c1746bd2f38afb0b44677cf3cb3b3927ebe --- /dev/null +++ b/checkpoint-378/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9416c93f6e2bc9f6d69312a909602322d9508febb3c5db2ab9f2363e4c1f04e +size 1064 diff --git a/checkpoint-378/special_tokens_map.json b/checkpoint-378/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-378/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-378/tokenizer.json b/checkpoint-378/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-378/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-378/tokenizer.model b/checkpoint-378/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-378/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-378/tokenizer_config.json b/checkpoint-378/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3ade6be57196932063a48c1329fbf9c2e7e154d1 --- /dev/null +++ b/checkpoint-378/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

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

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

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

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

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "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-378/trainer_state.json b/checkpoint-378/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6b6fcd1dd1cd1acd41bab2072efb1b0e34d99101 --- /dev/null +++ b/checkpoint-378/trainer_state.json @@ -0,0 +1,1357 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 27.0, + "eval_steps": 500, + "global_step": 378, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.14285714285714285, + "grad_norm": 49.90940856933594, + "learning_rate": 1.6666666666666667e-06, + "loss": 6.0076, + "step": 2 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 44.15715789794922, + "learning_rate": 5e-06, + "loss": 5.6559, + "step": 4 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 56.16670608520508, + "learning_rate": 8.333333333333334e-06, + "loss": 4.4368, + "step": 6 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 23.919437408447266, + "learning_rate": 1.1666666666666668e-05, + "loss": 2.7657, + "step": 8 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 20.757640838623047, + "learning_rate": 1.5000000000000002e-05, + "loss": 2.3404, + "step": 10 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 16.067575454711914, + "learning_rate": 1.8333333333333333e-05, + "loss": 2.038, + "step": 12 + }, + { + "epoch": 1.0, + "grad_norm": 23.458139419555664, + "learning_rate": 1.9999675557165282e-05, + "loss": 1.5809, + "step": 14 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 11.104408264160156, + "learning_rate": 1.9997080140801932e-05, + "loss": 1.1148, + "step": 16 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 11.328217506408691, + "learning_rate": 1.9991889981715696e-05, + "loss": 1.2528, + "step": 18 + }, + { + "epoch": 1.4285714285714286, + "grad_norm": 12.313949584960938, + "learning_rate": 1.9984106427012667e-05, + "loss": 1.2324, + "step": 20 + }, + { + "epoch": 1.5714285714285714, + "grad_norm": 10.425058364868164, + "learning_rate": 1.9973731496914914e-05, + "loss": 1.0203, + "step": 22 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 12.36324691772461, + "learning_rate": 1.9960767884236132e-05, + "loss": 1.0997, + "step": 24 + }, + { + "epoch": 1.8571428571428572, + "grad_norm": 14.280921936035156, + "learning_rate": 1.9945218953682736e-05, + "loss": 1.43, + "step": 26 + }, + { + "epoch": 2.0, + "grad_norm": 20.082475662231445, + "learning_rate": 1.992708874098054e-05, + "loss": 1.0748, + "step": 28 + }, + { + "epoch": 2.142857142857143, + "grad_norm": 5.667484283447266, + "learning_rate": 1.9906381951827295e-05, + "loss": 0.3794, + "step": 30 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 6.214536666870117, + "learning_rate": 1.9883103960671305e-05, + "loss": 0.2747, + "step": 32 + }, + { + "epoch": 2.4285714285714284, + "grad_norm": 6.836840629577637, + "learning_rate": 1.985726080931651e-05, + "loss": 0.2568, + "step": 34 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 13.044551849365234, + "learning_rate": 1.9828859205354326e-05, + "loss": 0.2937, + "step": 36 + }, + { + "epoch": 2.7142857142857144, + "grad_norm": 8.866482734680176, + "learning_rate": 1.979790652042268e-05, + "loss": 0.4252, + "step": 38 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 8.709479331970215, + "learning_rate": 1.9764410788292724e-05, + "loss": 0.3599, + "step": 40 + }, + { + "epoch": 3.0, + "grad_norm": 9.43436050415039, + "learning_rate": 1.9728380702783644e-05, + "loss": 0.3578, + "step": 42 + }, + { + "epoch": 3.142857142857143, + "grad_norm": 1.2470844984054565, + "learning_rate": 1.968982561550621e-05, + "loss": 0.1155, + "step": 44 + }, + { + "epoch": 3.2857142857142856, + "grad_norm": 5.716163635253906, + "learning_rate": 1.9648755533435517e-05, + "loss": 0.0708, + "step": 46 + }, + { + "epoch": 3.4285714285714284, + "grad_norm": 6.77197790145874, + "learning_rate": 1.9605181116313725e-05, + "loss": 0.081, + "step": 48 + }, + { + "epoch": 3.571428571428571, + "grad_norm": 5.336516380310059, + "learning_rate": 1.955911367388329e-05, + "loss": 0.112, + "step": 50 + }, + { + "epoch": 3.7142857142857144, + "grad_norm": 10.314866065979004, + "learning_rate": 1.9510565162951538e-05, + "loss": 0.0958, + "step": 52 + }, + { + "epoch": 3.857142857142857, + "grad_norm": 5.841635704040527, + "learning_rate": 1.9459548184287254e-05, + "loss": 0.0593, + "step": 54 + }, + { + "epoch": 4.0, + "grad_norm": 10.58973503112793, + "learning_rate": 1.9406075979350175e-05, + "loss": 0.2013, + "step": 56 + }, + { + "epoch": 4.142857142857143, + "grad_norm": 3.521483898162842, + "learning_rate": 1.9350162426854152e-05, + "loss": 0.0563, + "step": 58 + }, + { + "epoch": 4.285714285714286, + "grad_norm": 1.0017471313476562, + "learning_rate": 1.9291822039164934e-05, + "loss": 0.1029, + "step": 60 + }, + { + "epoch": 4.428571428571429, + "grad_norm": 0.33161500096321106, + "learning_rate": 1.923106995853349e-05, + "loss": 0.024, + "step": 62 + }, + { + "epoch": 4.571428571428571, + "grad_norm": 6.284483432769775, + "learning_rate": 1.9167921953165827e-05, + "loss": 0.1092, + "step": 64 + }, + { + "epoch": 4.714285714285714, + "grad_norm": 3.3121423721313477, + "learning_rate": 1.9102394413130348e-05, + "loss": 0.0401, + "step": 66 + }, + { + "epoch": 4.857142857142857, + "grad_norm": 8.295348167419434, + "learning_rate": 1.9034504346103825e-05, + "loss": 0.3237, + "step": 68 + }, + { + "epoch": 5.0, + "grad_norm": 2.1199071407318115, + "learning_rate": 1.896426937295704e-05, + "loss": 0.0375, + "step": 70 + }, + { + "epoch": 5.142857142857143, + "grad_norm": 0.45601171255111694, + "learning_rate": 1.8891707723181294e-05, + "loss": 0.0319, + "step": 72 + }, + { + "epoch": 5.285714285714286, + "grad_norm": 1.0054666996002197, + "learning_rate": 1.881683823015694e-05, + "loss": 0.0097, + "step": 74 + }, + { + "epoch": 5.428571428571429, + "grad_norm": 0.8899504542350769, + "learning_rate": 1.873968032626518e-05, + "loss": 0.0769, + "step": 76 + }, + { + "epoch": 5.571428571428571, + "grad_norm": 0.49617600440979004, + "learning_rate": 1.866025403784439e-05, + "loss": 0.0479, + "step": 78 + }, + { + "epoch": 5.714285714285714, + "grad_norm": 0.16562028229236603, + "learning_rate": 1.8578579979992266e-05, + "loss": 0.0051, + "step": 80 + }, + { + "epoch": 5.857142857142857, + "grad_norm": 11.048959732055664, + "learning_rate": 1.8494679351215212e-05, + "loss": 0.0984, + "step": 82 + }, + { + "epoch": 6.0, + "grad_norm": 7.846388816833496, + "learning_rate": 1.8408573927926225e-05, + "loss": 0.116, + "step": 84 + }, + { + "epoch": 6.142857142857143, + "grad_norm": 0.11113756895065308, + "learning_rate": 1.8320286058792845e-05, + "loss": 0.0027, + "step": 86 + }, + { + "epoch": 6.285714285714286, + "grad_norm": 3.4302117824554443, + "learning_rate": 1.8229838658936566e-05, + "loss": 0.0197, + "step": 88 + }, + { + "epoch": 6.428571428571429, + "grad_norm": 4.105597496032715, + "learning_rate": 1.81372552039852e-05, + "loss": 0.1183, + "step": 90 + }, + { + "epoch": 6.571428571428571, + "grad_norm": 3.2223429679870605, + "learning_rate": 1.804255972397977e-05, + "loss": 0.006, + "step": 92 + }, + { + "epoch": 6.714285714285714, + "grad_norm": 4.856196403503418, + "learning_rate": 1.7945776797137544e-05, + "loss": 0.0062, + "step": 94 + }, + { + "epoch": 6.857142857142857, + "grad_norm": 1.22345769405365, + "learning_rate": 1.7846931543472722e-05, + "loss": 0.0037, + "step": 96 + }, + { + "epoch": 7.0, + "grad_norm": 8.841476440429688, + "learning_rate": 1.7746049618276545e-05, + "loss": 0.0885, + "step": 98 + }, + { + "epoch": 7.142857142857143, + "grad_norm": 1.7171941995620728, + "learning_rate": 1.7643157205458483e-05, + "loss": 0.0732, + "step": 100 + }, + { + "epoch": 7.285714285714286, + "grad_norm": 0.2902078628540039, + "learning_rate": 1.753828101075017e-05, + "loss": 0.0019, + "step": 102 + }, + { + "epoch": 7.428571428571429, + "grad_norm": 6.003970623016357, + "learning_rate": 1.7431448254773943e-05, + "loss": 0.0219, + "step": 104 + }, + { + "epoch": 7.571428571428571, + "grad_norm": 0.211229145526886, + "learning_rate": 1.7322686665977738e-05, + "loss": 0.0014, + "step": 106 + }, + { + "epoch": 7.714285714285714, + "grad_norm": 14.436793327331543, + "learning_rate": 1.7212024473438145e-05, + "loss": 0.1415, + "step": 108 + }, + { + "epoch": 7.857142857142857, + "grad_norm": 0.05790628120303154, + "learning_rate": 1.7099490399533583e-05, + "loss": 0.0008, + "step": 110 + }, + { + "epoch": 8.0, + "grad_norm": 0.17556001245975494, + "learning_rate": 1.6985113652489374e-05, + "loss": 0.0044, + "step": 112 + }, + { + "epoch": 8.142857142857142, + "grad_norm": 0.38069918751716614, + "learning_rate": 1.6868923918796753e-05, + "loss": 0.001, + "step": 114 + }, + { + "epoch": 8.285714285714286, + "grad_norm": 0.093246690928936, + "learning_rate": 1.6750951355507763e-05, + "loss": 0.0321, + "step": 116 + }, + { + "epoch": 8.428571428571429, + "grad_norm": 0.15035825967788696, + "learning_rate": 1.6631226582407954e-05, + "loss": 0.0036, + "step": 118 + }, + { + "epoch": 8.571428571428571, + "grad_norm": 0.06252682954072952, + "learning_rate": 1.650978067406904e-05, + "loss": 0.0035, + "step": 120 + }, + { + "epoch": 8.714285714285714, + "grad_norm": 6.229085922241211, + "learning_rate": 1.638664515178348e-05, + "loss": 0.1034, + "step": 122 + }, + { + "epoch": 8.857142857142858, + "grad_norm": 2.403806686401367, + "learning_rate": 1.626185197538314e-05, + "loss": 0.036, + "step": 124 + }, + { + "epoch": 9.0, + "grad_norm": 0.07740367949008942, + "learning_rate": 1.613543353494409e-05, + "loss": 0.0006, + "step": 126 + }, + { + "epoch": 9.142857142857142, + "grad_norm": 0.322050541639328, + "learning_rate": 1.600742264237979e-05, + "loss": 0.0013, + "step": 128 + }, + { + "epoch": 9.285714285714286, + "grad_norm": 0.1652839183807373, + "learning_rate": 1.5877852522924733e-05, + "loss": 0.0008, + "step": 130 + }, + { + "epoch": 9.428571428571429, + "grad_norm": 0.048877034336328506, + "learning_rate": 1.574675680651084e-05, + "loss": 0.0008, + "step": 132 + }, + { + "epoch": 9.571428571428571, + "grad_norm": 0.06231057271361351, + "learning_rate": 1.561416951903881e-05, + "loss": 0.0022, + "step": 134 + }, + { + "epoch": 9.714285714285714, + "grad_norm": 0.03611210733652115, + "learning_rate": 1.5480125073546705e-05, + "loss": 0.0389, + "step": 136 + }, + { + "epoch": 9.857142857142858, + "grad_norm": 0.52008056640625, + "learning_rate": 1.5344658261278013e-05, + "loss": 0.0089, + "step": 138 + }, + { + "epoch": 10.0, + "grad_norm": 0.42384108901023865, + "learning_rate": 1.5207804242651625e-05, + "loss": 0.0015, + "step": 140 + }, + { + "epoch": 10.142857142857142, + "grad_norm": 0.055933400988578796, + "learning_rate": 1.5069598538135905e-05, + "loss": 0.0004, + "step": 142 + }, + { + "epoch": 10.285714285714286, + "grad_norm": 0.0212051160633564, + "learning_rate": 1.4930077019029376e-05, + "loss": 0.0072, + "step": 144 + }, + { + "epoch": 10.428571428571429, + "grad_norm": 0.03581853583455086, + "learning_rate": 1.4789275898150309e-05, + "loss": 0.0006, + "step": 146 + }, + { + "epoch": 10.571428571428571, + "grad_norm": 0.021400820463895798, + "learning_rate": 1.4647231720437687e-05, + "loss": 0.0005, + "step": 148 + }, + { + "epoch": 10.714285714285714, + "grad_norm": 1.3550739288330078, + "learning_rate": 1.450398135346597e-05, + "loss": 0.0332, + "step": 150 + }, + { + "epoch": 10.857142857142858, + "grad_norm": 0.014044591225683689, + "learning_rate": 1.4359561977876102e-05, + "loss": 0.0003, + "step": 152 + }, + { + "epoch": 11.0, + "grad_norm": 0.056435056030750275, + "learning_rate": 1.4214011077725293e-05, + "loss": 0.0004, + "step": 154 + }, + { + "epoch": 11.142857142857142, + "grad_norm": 0.012104465626180172, + "learning_rate": 1.4067366430758004e-05, + "loss": 0.0214, + "step": 156 + }, + { + "epoch": 11.285714285714286, + "grad_norm": 0.022569801658391953, + "learning_rate": 1.3919666098600753e-05, + "loss": 0.0003, + "step": 158 + }, + { + "epoch": 11.428571428571429, + "grad_norm": 0.019581535831093788, + "learning_rate": 1.3770948416883205e-05, + "loss": 0.0003, + "step": 160 + }, + { + "epoch": 11.571428571428571, + "grad_norm": 0.012900936417281628, + "learning_rate": 1.362125198528817e-05, + "loss": 0.0003, + "step": 162 + }, + { + "epoch": 11.714285714285714, + "grad_norm": 0.283460795879364, + "learning_rate": 1.347061565753303e-05, + "loss": 0.0151, + "step": 164 + }, + { + "epoch": 11.857142857142858, + "grad_norm": 0.02773939073085785, + "learning_rate": 1.3319078531285286e-05, + "loss": 0.0002, + "step": 166 + }, + { + "epoch": 12.0, + "grad_norm": 0.015381716191768646, + "learning_rate": 1.3166679938014728e-05, + "loss": 0.0002, + "step": 168 + }, + { + "epoch": 12.142857142857142, + "grad_norm": 0.013684879057109356, + "learning_rate": 1.301345943278496e-05, + "loss": 0.0002, + "step": 170 + }, + { + "epoch": 12.285714285714286, + "grad_norm": 0.011124438606202602, + "learning_rate": 1.2859456783986892e-05, + "loss": 0.0002, + "step": 172 + }, + { + "epoch": 12.428571428571429, + "grad_norm": 0.2694200873374939, + "learning_rate": 1.270471196301684e-05, + "loss": 0.0059, + "step": 174 + }, + { + "epoch": 12.571428571428571, + "grad_norm": 0.25839900970458984, + "learning_rate": 1.2549265133901934e-05, + "loss": 0.007, + "step": 176 + }, + { + "epoch": 12.714285714285714, + "grad_norm": 0.28028616309165955, + "learning_rate": 1.2393156642875579e-05, + "loss": 0.0081, + "step": 178 + }, + { + "epoch": 12.857142857142858, + "grad_norm": 0.007691177539527416, + "learning_rate": 1.2236427007905558e-05, + "loss": 0.0004, + "step": 180 + }, + { + "epoch": 13.0, + "grad_norm": 0.03421185538172722, + "learning_rate": 1.2079116908177592e-05, + "loss": 0.0002, + "step": 182 + }, + { + "epoch": 13.142857142857142, + "grad_norm": 0.21886347234249115, + "learning_rate": 1.1921267173537085e-05, + "loss": 0.0106, + "step": 184 + }, + { + "epoch": 13.285714285714286, + "grad_norm": 0.12066204100847244, + "learning_rate": 1.1762918773891691e-05, + "loss": 0.0039, + "step": 186 + }, + { + "epoch": 13.428571428571429, + "grad_norm": 0.009790458716452122, + "learning_rate": 1.1604112808577603e-05, + "loss": 0.0001, + "step": 188 + }, + { + "epoch": 13.571428571428571, + "grad_norm": 0.006134828552603722, + "learning_rate": 1.1444890495692214e-05, + "loss": 0.0001, + "step": 190 + }, + { + "epoch": 13.714285714285714, + "grad_norm": 0.007279029581695795, + "learning_rate": 1.1285293161395948e-05, + "loss": 0.0082, + "step": 192 + }, + { + "epoch": 13.857142857142858, + "grad_norm": 0.007834681309759617, + "learning_rate": 1.1125362229186056e-05, + "loss": 0.0001, + "step": 194 + }, + { + "epoch": 14.0, + "grad_norm": 0.011400113813579082, + "learning_rate": 1.0965139209145153e-05, + "loss": 0.0001, + "step": 196 + }, + { + "epoch": 14.142857142857142, + "grad_norm": 0.005645982455462217, + "learning_rate": 1.0804665687167262e-05, + "loss": 0.0001, + "step": 198 + }, + { + "epoch": 14.285714285714286, + "grad_norm": 0.007113787345588207, + "learning_rate": 1.0643983314164195e-05, + "loss": 0.0046, + "step": 200 + }, + { + "epoch": 14.428571428571429, + "grad_norm": 0.00671082129701972, + "learning_rate": 1.0483133795255072e-05, + "loss": 0.0001, + "step": 202 + }, + { + "epoch": 14.571428571428571, + "grad_norm": 0.10411105304956436, + "learning_rate": 1.0322158878941733e-05, + "loss": 0.0092, + "step": 204 + }, + { + "epoch": 14.714285714285714, + "grad_norm": 0.007047938648611307, + "learning_rate": 1.0161100346272913e-05, + "loss": 0.0046, + "step": 206 + }, + { + "epoch": 14.857142857142858, + "grad_norm": 0.006609996780753136, + "learning_rate": 1e-05, + "loss": 0.0001, + "step": 208 + }, + { + "epoch": 15.0, + "grad_norm": 0.00515047088265419, + "learning_rate": 9.838899653727088e-06, + "loss": 0.0001, + "step": 210 + }, + { + "epoch": 15.142857142857142, + "grad_norm": 0.005954743828624487, + "learning_rate": 9.677841121058274e-06, + "loss": 0.0001, + "step": 212 + }, + { + "epoch": 15.285714285714286, + "grad_norm": 0.19431306421756744, + "learning_rate": 9.516866204744932e-06, + "loss": 0.0046, + "step": 214 + }, + { + "epoch": 15.428571428571429, + "grad_norm": 0.007638772018253803, + "learning_rate": 9.356016685835807e-06, + "loss": 0.0045, + "step": 216 + }, + { + "epoch": 15.571428571428571, + "grad_norm": 0.10914219170808792, + "learning_rate": 9.195334312832742e-06, + "loss": 0.0092, + "step": 218 + }, + { + "epoch": 15.714285714285714, + "grad_norm": 0.005956027191132307, + "learning_rate": 9.034860790854848e-06, + "loss": 0.0001, + "step": 220 + }, + { + "epoch": 15.857142857142858, + "grad_norm": 0.006127700675278902, + "learning_rate": 8.874637770813947e-06, + "loss": 0.0001, + "step": 222 + }, + { + "epoch": 16.0, + "grad_norm": 0.006942708045244217, + "learning_rate": 8.714706838604056e-06, + "loss": 0.0001, + "step": 224 + }, + { + "epoch": 16.142857142857142, + "grad_norm": 0.17752425372600555, + "learning_rate": 8.55510950430779e-06, + "loss": 0.0098, + "step": 226 + }, + { + "epoch": 16.285714285714285, + "grad_norm": 0.004300012718886137, + "learning_rate": 8.395887191422397e-06, + "loss": 0.0001, + "step": 228 + }, + { + "epoch": 16.428571428571427, + "grad_norm": 0.0063268570229411125, + "learning_rate": 8.23708122610831e-06, + "loss": 0.0075, + "step": 230 + }, + { + "epoch": 16.571428571428573, + "grad_norm": 0.005733097437769175, + "learning_rate": 8.078732826462917e-06, + "loss": 0.0001, + "step": 232 + }, + { + "epoch": 16.714285714285715, + "grad_norm": 0.0077501749619841576, + "learning_rate": 7.92088309182241e-06, + "loss": 0.0001, + "step": 234 + }, + { + "epoch": 16.857142857142858, + "grad_norm": 0.005072280764579773, + "learning_rate": 7.763572992094448e-06, + "loss": 0.0001, + "step": 236 + }, + { + "epoch": 17.0, + "grad_norm": 0.007300873752683401, + "learning_rate": 7.606843357124426e-06, + "loss": 0.0001, + "step": 238 + }, + { + "epoch": 17.142857142857142, + "grad_norm": 0.10978183150291443, + "learning_rate": 7.450734866098066e-06, + "loss": 0.0036, + "step": 240 + }, + { + "epoch": 17.285714285714285, + "grad_norm": 0.005480973981320858, + "learning_rate": 7.2952880369831635e-06, + "loss": 0.0061, + "step": 242 + }, + { + "epoch": 17.428571428571427, + "grad_norm": 0.2027699053287506, + "learning_rate": 7.140543216013109e-06, + "loss": 0.0035, + "step": 244 + }, + { + "epoch": 17.571428571428573, + "grad_norm": 0.0048587811179459095, + "learning_rate": 6.986540567215043e-06, + "loss": 0.0001, + "step": 246 + }, + { + "epoch": 17.714285714285715, + "grad_norm": 0.005718125496059656, + "learning_rate": 6.833320061985278e-06, + "loss": 0.0001, + "step": 248 + }, + { + "epoch": 17.857142857142858, + "grad_norm": 0.0035847134422510862, + "learning_rate": 6.680921468714718e-06, + "loss": 0.0052, + "step": 250 + }, + { + "epoch": 18.0, + "grad_norm": 0.0035746165085583925, + "learning_rate": 6.529384342466971e-06, + "loss": 0.0001, + "step": 252 + }, + { + "epoch": 18.142857142857142, + "grad_norm": 0.00451216846704483, + "learning_rate": 6.378748014711834e-06, + "loss": 0.0001, + "step": 254 + }, + { + "epoch": 18.285714285714285, + "grad_norm": 0.004890494979918003, + "learning_rate": 6.229051583116796e-06, + "loss": 0.0001, + "step": 256 + }, + { + "epoch": 18.428571428571427, + "grad_norm": 0.004625991452485323, + "learning_rate": 6.080333901399252e-06, + "loss": 0.0058, + "step": 258 + }, + { + "epoch": 18.571428571428573, + "grad_norm": 0.005847033113241196, + "learning_rate": 5.932633569242e-06, + "loss": 0.0001, + "step": 260 + }, + { + "epoch": 18.714285714285715, + "grad_norm": 0.006245823111385107, + "learning_rate": 5.785988922274711e-06, + "loss": 0.0072, + "step": 262 + }, + { + "epoch": 18.857142857142858, + "grad_norm": 0.08823557943105698, + "learning_rate": 5.640438022123898e-06, + "loss": 0.0034, + "step": 264 + }, + { + "epoch": 19.0, + "grad_norm": 0.004038456827402115, + "learning_rate": 5.496018646534032e-06, + "loss": 0.0001, + "step": 266 + }, + { + "epoch": 19.142857142857142, + "grad_norm": 0.005825538653880358, + "learning_rate": 5.352768279562315e-06, + "loss": 0.0056, + "step": 268 + }, + { + "epoch": 19.285714285714285, + "grad_norm": 0.004666970111429691, + "learning_rate": 5.210724101849696e-06, + "loss": 0.0001, + "step": 270 + }, + { + "epoch": 19.428571428571427, + "grad_norm": 0.004332971293479204, + "learning_rate": 5.069922980970626e-06, + "loss": 0.0001, + "step": 272 + }, + { + "epoch": 19.571428571428573, + "grad_norm": 0.09540804475545883, + "learning_rate": 4.930401461864099e-06, + "loss": 0.0085, + "step": 274 + }, + { + "epoch": 19.714285714285715, + "grad_norm": 0.004319526720792055, + "learning_rate": 4.7921957573483756e-06, + "loss": 0.0001, + "step": 276 + }, + { + "epoch": 19.857142857142858, + "grad_norm": 0.00582715030759573, + "learning_rate": 4.655341738721989e-06, + "loss": 0.0001, + "step": 278 + }, + { + "epoch": 20.0, + "grad_norm": 0.005314113572239876, + "learning_rate": 4.519874926453303e-06, + "loss": 0.0001, + "step": 280 + }, + { + "epoch": 20.142857142857142, + "grad_norm": 0.006195093505084515, + "learning_rate": 4.385830480961192e-06, + "loss": 0.0001, + "step": 282 + }, + { + "epoch": 20.285714285714285, + "grad_norm": 0.004151402972638607, + "learning_rate": 4.2532431934891646e-06, + "loss": 0.0001, + "step": 284 + }, + { + "epoch": 20.428571428571427, + "grad_norm": 0.004392064176499844, + "learning_rate": 4.12214747707527e-06, + "loss": 0.0047, + "step": 286 + }, + { + "epoch": 20.571428571428573, + "grad_norm": 0.004756106063723564, + "learning_rate": 3.99257735762021e-06, + "loss": 0.0001, + "step": 288 + }, + { + "epoch": 20.714285714285715, + "grad_norm": 0.004611567594110966, + "learning_rate": 3.864566465055913e-06, + "loss": 0.0022, + "step": 290 + }, + { + "epoch": 20.857142857142858, + "grad_norm": 0.004500643815845251, + "learning_rate": 3.738148024616863e-06, + "loss": 0.0001, + "step": 292 + }, + { + "epoch": 21.0, + "grad_norm": 0.0058865793980658054, + "learning_rate": 3.6133548482165225e-06, + "loss": 0.0081, + "step": 294 + }, + { + "epoch": 21.142857142857142, + "grad_norm": 0.096845842897892, + "learning_rate": 3.4902193259309627e-06, + "loss": 0.0037, + "step": 296 + }, + { + "epoch": 21.285714285714285, + "grad_norm": 0.0038972089532762766, + "learning_rate": 3.3687734175920505e-06, + "loss": 0.0001, + "step": 298 + }, + { + "epoch": 21.428571428571427, + "grad_norm": 0.004685294348746538, + "learning_rate": 3.2490486444922396e-06, + "loss": 0.0001, + "step": 300 + }, + { + "epoch": 21.571428571428573, + "grad_norm": 0.20793084800243378, + "learning_rate": 3.131076081203247e-06, + "loss": 0.0019, + "step": 302 + }, + { + "epoch": 21.714285714285715, + "grad_norm": 0.0035532894544303417, + "learning_rate": 3.0148863475106315e-06, + "loss": 0.0058, + "step": 304 + }, + { + "epoch": 21.857142857142858, + "grad_norm": 0.2300863116979599, + "learning_rate": 2.900509600466418e-06, + "loss": 0.0025, + "step": 306 + }, + { + "epoch": 22.0, + "grad_norm": 0.007288255728781223, + "learning_rate": 2.7879755265618558e-06, + "loss": 0.0001, + "step": 308 + }, + { + "epoch": 22.142857142857142, + "grad_norm": 0.005309649743139744, + "learning_rate": 2.6773133340222677e-06, + "loss": 0.0016, + "step": 310 + }, + { + "epoch": 22.285714285714285, + "grad_norm": 0.003941751550883055, + "learning_rate": 2.5685517452260566e-06, + "loss": 0.0001, + "step": 312 + }, + { + "epoch": 22.428571428571427, + "grad_norm": 0.004016744904220104, + "learning_rate": 2.4617189892498326e-06, + "loss": 0.0001, + "step": 314 + }, + { + "epoch": 22.571428571428573, + "grad_norm": 0.13147950172424316, + "learning_rate": 2.3568427945415163e-06, + "loss": 0.0064, + "step": 316 + }, + { + "epoch": 22.714285714285715, + "grad_norm": 0.003918132279068232, + "learning_rate": 2.2539503817234553e-06, + "loss": 0.0001, + "step": 318 + }, + { + "epoch": 22.857142857142858, + "grad_norm": 0.004725574050098658, + "learning_rate": 2.153068456527283e-06, + "loss": 0.0001, + "step": 320 + }, + { + "epoch": 23.0, + "grad_norm": 0.3711271584033966, + "learning_rate": 2.0542232028624585e-06, + "loss": 0.0175, + "step": 322 + }, + { + "epoch": 23.142857142857142, + "grad_norm": 0.18150761723518372, + "learning_rate": 1.9574402760202315e-06, + "loss": 0.0023, + "step": 324 + }, + { + "epoch": 23.285714285714285, + "grad_norm": 0.13696324825286865, + "learning_rate": 1.8627447960148036e-06, + "loss": 0.0045, + "step": 326 + }, + { + "epoch": 23.428571428571427, + "grad_norm": 0.004304251167923212, + "learning_rate": 1.7701613410634367e-06, + "loss": 0.0001, + "step": 328 + }, + { + "epoch": 23.571428571428573, + "grad_norm": 0.005392234306782484, + "learning_rate": 1.6797139412071583e-06, + "loss": 0.0001, + "step": 330 + }, + { + "epoch": 23.714285714285715, + "grad_norm": 0.004501474089920521, + "learning_rate": 1.5914260720737796e-06, + "loss": 0.0001, + "step": 332 + }, + { + "epoch": 23.857142857142858, + "grad_norm": 0.0033914605155587196, + "learning_rate": 1.5053206487847916e-06, + "loss": 0.0047, + "step": 334 + }, + { + "epoch": 24.0, + "grad_norm": 0.005722349975258112, + "learning_rate": 1.4214200200077343e-06, + "loss": 0.0001, + "step": 336 + }, + { + "epoch": 24.142857142857142, + "grad_norm": 0.0028757653199136257, + "learning_rate": 1.339745962155613e-06, + "loss": 0.0001, + "step": 338 + }, + { + "epoch": 24.285714285714285, + "grad_norm": 0.004367240238934755, + "learning_rate": 1.2603196737348211e-06, + "loss": 0.0012, + "step": 340 + }, + { + "epoch": 24.428571428571427, + "grad_norm": 0.004103364888578653, + "learning_rate": 1.1831617698430609e-06, + "loss": 0.0001, + "step": 342 + }, + { + "epoch": 24.571428571428573, + "grad_norm": 0.12380176037549973, + "learning_rate": 1.1082922768187098e-06, + "loss": 0.0053, + "step": 344 + }, + { + "epoch": 24.714285714285715, + "grad_norm": 0.11978839337825775, + "learning_rate": 1.0357306270429623e-06, + "loss": 0.0045, + "step": 346 + }, + { + "epoch": 24.857142857142858, + "grad_norm": 0.15920782089233398, + "learning_rate": 9.65495653896179e-07, + "loss": 0.0008, + "step": 348 + }, + { + "epoch": 25.0, + "grad_norm": 0.005539704114198685, + "learning_rate": 8.976055868696543e-07, + "loss": 0.0001, + "step": 350 + }, + { + "epoch": 25.142857142857142, + "grad_norm": 0.004604020155966282, + "learning_rate": 8.320780468341761e-07, + "loss": 0.0001, + "step": 352 + }, + { + "epoch": 25.285714285714285, + "grad_norm": 0.19128715991973877, + "learning_rate": 7.689300414665124e-07, + "loss": 0.0012, + "step": 354 + }, + { + "epoch": 25.428571428571427, + "grad_norm": 0.0033012081403285265, + "learning_rate": 7.08177960835068e-07, + "loss": 0.0067, + "step": 356 + }, + { + "epoch": 25.571428571428573, + "grad_norm": 0.09938196837902069, + "learning_rate": 6.498375731458529e-07, + "loss": 0.0005, + "step": 358 + }, + { + "epoch": 25.714285714285715, + "grad_norm": 0.0049908701330423355, + "learning_rate": 5.939240206498287e-07, + "loss": 0.0001, + "step": 360 + }, + { + "epoch": 25.857142857142858, + "grad_norm": 0.0035182549618184566, + "learning_rate": 5.404518157127481e-07, + "loss": 0.0046, + "step": 362 + }, + { + "epoch": 26.0, + "grad_norm": 0.0068074483424425125, + "learning_rate": 4.894348370484648e-07, + "loss": 0.0001, + "step": 364 + }, + { + "epoch": 26.142857142857142, + "grad_norm": 0.004269490484148264, + "learning_rate": 4.408863261167096e-07, + "loss": 0.0001, + "step": 366 + }, + { + "epoch": 26.285714285714285, + "grad_norm": 0.12823165953159332, + "learning_rate": 3.9481888368627764e-07, + "loss": 0.0042, + "step": 368 + }, + { + "epoch": 26.428571428571427, + "grad_norm": 0.0035812160931527615, + "learning_rate": 3.5124446656448654e-07, + "loss": 0.0001, + "step": 370 + }, + { + "epoch": 26.571428571428573, + "grad_norm": 0.00431048171594739, + "learning_rate": 3.101743844937943e-07, + "loss": 0.0059, + "step": 372 + }, + { + "epoch": 26.714285714285715, + "grad_norm": 0.004997176583856344, + "learning_rate": 2.716192972163556e-07, + "loss": 0.0001, + "step": 374 + }, + { + "epoch": 26.857142857142858, + "grad_norm": 0.004221776034682989, + "learning_rate": 2.355892117072789e-07, + "loss": 0.0001, + "step": 376 + }, + { + "epoch": 27.0, + "grad_norm": 0.007233808748424053, + "learning_rate": 2.0209347957732328e-07, + "loss": 0.0008, + "step": 378 + } + ], + "logging_steps": 2, + "max_steps": 402, + "num_input_tokens_seen": 0, + "num_train_epochs": 29, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.9428161016692736e+16, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-378/training_args.bin b/checkpoint-378/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5e40431601fe0fda63821c355ca2518b79c42df --- /dev/null +++ b/checkpoint-378/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25a0ccf5317ebd8f7cfcaefcfdfd3860c0c2887188910c19a4b9dde7e5910b1 +size 6520 diff --git a/checkpoint-392/README.md b/checkpoint-392/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ae0ed615fe362734126a5801320301bdfc158e46 --- /dev/null +++ b/checkpoint-392/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.15.2 \ No newline at end of file diff --git a/checkpoint-392/adapter_config.json b/checkpoint-392/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0903ea87f348df7f18650f0467f8051ebdd53938 --- /dev/null +++ b/checkpoint-392/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "corda_config": null, + "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": 256, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 128, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "up_proj", + "q_proj", + "o_proj", + "k_proj", + "down_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-392/adapter_model.safetensors b/checkpoint-392/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35338caff5c34dbef15da4ec3f859d07a46b2536 --- /dev/null +++ b/checkpoint-392/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f21d57be7274a103fb2a45feff582f6b03779323750d4179cf279d3f53d8b98 +size 1728658208 diff --git a/checkpoint-392/chat_template.jinja b/checkpoint-392/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..923ec253c8dbefbb41cf084db7251df41d000f6d --- /dev/null +++ b/checkpoint-392/chat_template.jinja @@ -0,0 +1,4 @@ +{{ 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 + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/checkpoint-392/optimizer.pt b/checkpoint-392/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc369f0139bef174ad058d7cc40ae13225680ac5 --- /dev/null +++ b/checkpoint-392/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd997c59daf13988f38f6e12b1824cd2952ca15b4ea589f6ac18cdf73aabb6b1 +size 878485380 diff --git a/checkpoint-392/rng_state.pth b/checkpoint-392/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..e86544981661129ecf97e540b33122be79358557 --- /dev/null +++ b/checkpoint-392/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7277bc934ade3a2b557c13775dde406cbfb4208cb972ee756636af0a0ee40151 +size 14244 diff --git a/checkpoint-392/scheduler.pt b/checkpoint-392/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..058e968ce1d1b36312f06303ad46f4313fb50782 --- /dev/null +++ b/checkpoint-392/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54499b6cf73ccbf794e5efaabfc3960607ec0529871ad57628602fcb39853369 +size 1064 diff --git a/checkpoint-392/special_tokens_map.json b/checkpoint-392/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-392/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-392/tokenizer.json b/checkpoint-392/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-392/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-392/tokenizer.model b/checkpoint-392/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-392/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-392/tokenizer_config.json b/checkpoint-392/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3ade6be57196932063a48c1329fbf9c2e7e154d1 --- /dev/null +++ b/checkpoint-392/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

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

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

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

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

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "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-392/trainer_state.json b/checkpoint-392/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a4b5c6f50f286e9359ccc87b7a17286a34ffdf17 --- /dev/null +++ b/checkpoint-392/trainer_state.json @@ -0,0 +1,1406 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 28.0, + "eval_steps": 500, + "global_step": 392, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.14285714285714285, + "grad_norm": 49.90940856933594, + "learning_rate": 1.6666666666666667e-06, + "loss": 6.0076, + "step": 2 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 44.15715789794922, + "learning_rate": 5e-06, + "loss": 5.6559, + "step": 4 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 56.16670608520508, + "learning_rate": 8.333333333333334e-06, + "loss": 4.4368, + "step": 6 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 23.919437408447266, + "learning_rate": 1.1666666666666668e-05, + "loss": 2.7657, + "step": 8 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 20.757640838623047, + "learning_rate": 1.5000000000000002e-05, + "loss": 2.3404, + "step": 10 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 16.067575454711914, + "learning_rate": 1.8333333333333333e-05, + "loss": 2.038, + "step": 12 + }, + { + "epoch": 1.0, + "grad_norm": 23.458139419555664, + "learning_rate": 1.9999675557165282e-05, + "loss": 1.5809, + "step": 14 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 11.104408264160156, + "learning_rate": 1.9997080140801932e-05, + "loss": 1.1148, + "step": 16 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 11.328217506408691, + "learning_rate": 1.9991889981715696e-05, + "loss": 1.2528, + "step": 18 + }, + { + "epoch": 1.4285714285714286, + "grad_norm": 12.313949584960938, + "learning_rate": 1.9984106427012667e-05, + "loss": 1.2324, + "step": 20 + }, + { + "epoch": 1.5714285714285714, + "grad_norm": 10.425058364868164, + "learning_rate": 1.9973731496914914e-05, + "loss": 1.0203, + "step": 22 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 12.36324691772461, + "learning_rate": 1.9960767884236132e-05, + "loss": 1.0997, + "step": 24 + }, + { + "epoch": 1.8571428571428572, + "grad_norm": 14.280921936035156, + "learning_rate": 1.9945218953682736e-05, + "loss": 1.43, + "step": 26 + }, + { + "epoch": 2.0, + "grad_norm": 20.082475662231445, + "learning_rate": 1.992708874098054e-05, + "loss": 1.0748, + "step": 28 + }, + { + "epoch": 2.142857142857143, + "grad_norm": 5.667484283447266, + "learning_rate": 1.9906381951827295e-05, + "loss": 0.3794, + "step": 30 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 6.214536666870117, + "learning_rate": 1.9883103960671305e-05, + "loss": 0.2747, + "step": 32 + }, + { + "epoch": 2.4285714285714284, + "grad_norm": 6.836840629577637, + "learning_rate": 1.985726080931651e-05, + "loss": 0.2568, + "step": 34 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 13.044551849365234, + "learning_rate": 1.9828859205354326e-05, + "loss": 0.2937, + "step": 36 + }, + { + "epoch": 2.7142857142857144, + "grad_norm": 8.866482734680176, + "learning_rate": 1.979790652042268e-05, + "loss": 0.4252, + "step": 38 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 8.709479331970215, + "learning_rate": 1.9764410788292724e-05, + "loss": 0.3599, + "step": 40 + }, + { + "epoch": 3.0, + "grad_norm": 9.43436050415039, + "learning_rate": 1.9728380702783644e-05, + "loss": 0.3578, + "step": 42 + }, + { + "epoch": 3.142857142857143, + "grad_norm": 1.2470844984054565, + "learning_rate": 1.968982561550621e-05, + "loss": 0.1155, + "step": 44 + }, + { + "epoch": 3.2857142857142856, + "grad_norm": 5.716163635253906, + "learning_rate": 1.9648755533435517e-05, + "loss": 0.0708, + "step": 46 + }, + { + "epoch": 3.4285714285714284, + "grad_norm": 6.77197790145874, + "learning_rate": 1.9605181116313725e-05, + "loss": 0.081, + "step": 48 + }, + { + "epoch": 3.571428571428571, + "grad_norm": 5.336516380310059, + "learning_rate": 1.955911367388329e-05, + "loss": 0.112, + "step": 50 + }, + { + "epoch": 3.7142857142857144, + "grad_norm": 10.314866065979004, + "learning_rate": 1.9510565162951538e-05, + "loss": 0.0958, + "step": 52 + }, + { + "epoch": 3.857142857142857, + "grad_norm": 5.841635704040527, + "learning_rate": 1.9459548184287254e-05, + "loss": 0.0593, + "step": 54 + }, + { + "epoch": 4.0, + "grad_norm": 10.58973503112793, + "learning_rate": 1.9406075979350175e-05, + "loss": 0.2013, + "step": 56 + }, + { + "epoch": 4.142857142857143, + "grad_norm": 3.521483898162842, + "learning_rate": 1.9350162426854152e-05, + "loss": 0.0563, + "step": 58 + }, + { + "epoch": 4.285714285714286, + "grad_norm": 1.0017471313476562, + "learning_rate": 1.9291822039164934e-05, + "loss": 0.1029, + "step": 60 + }, + { + "epoch": 4.428571428571429, + "grad_norm": 0.33161500096321106, + "learning_rate": 1.923106995853349e-05, + "loss": 0.024, + "step": 62 + }, + { + "epoch": 4.571428571428571, + "grad_norm": 6.284483432769775, + "learning_rate": 1.9167921953165827e-05, + "loss": 0.1092, + "step": 64 + }, + { + "epoch": 4.714285714285714, + "grad_norm": 3.3121423721313477, + "learning_rate": 1.9102394413130348e-05, + "loss": 0.0401, + "step": 66 + }, + { + "epoch": 4.857142857142857, + "grad_norm": 8.295348167419434, + "learning_rate": 1.9034504346103825e-05, + "loss": 0.3237, + "step": 68 + }, + { + "epoch": 5.0, + "grad_norm": 2.1199071407318115, + "learning_rate": 1.896426937295704e-05, + "loss": 0.0375, + "step": 70 + }, + { + "epoch": 5.142857142857143, + "grad_norm": 0.45601171255111694, + "learning_rate": 1.8891707723181294e-05, + "loss": 0.0319, + "step": 72 + }, + { + "epoch": 5.285714285714286, + "grad_norm": 1.0054666996002197, + "learning_rate": 1.881683823015694e-05, + "loss": 0.0097, + "step": 74 + }, + { + "epoch": 5.428571428571429, + "grad_norm": 0.8899504542350769, + "learning_rate": 1.873968032626518e-05, + "loss": 0.0769, + "step": 76 + }, + { + "epoch": 5.571428571428571, + "grad_norm": 0.49617600440979004, + "learning_rate": 1.866025403784439e-05, + "loss": 0.0479, + "step": 78 + }, + { + "epoch": 5.714285714285714, + "grad_norm": 0.16562028229236603, + "learning_rate": 1.8578579979992266e-05, + "loss": 0.0051, + "step": 80 + }, + { + "epoch": 5.857142857142857, + "grad_norm": 11.048959732055664, + "learning_rate": 1.8494679351215212e-05, + "loss": 0.0984, + "step": 82 + }, + { + "epoch": 6.0, + "grad_norm": 7.846388816833496, + "learning_rate": 1.8408573927926225e-05, + "loss": 0.116, + "step": 84 + }, + { + "epoch": 6.142857142857143, + "grad_norm": 0.11113756895065308, + "learning_rate": 1.8320286058792845e-05, + "loss": 0.0027, + "step": 86 + }, + { + "epoch": 6.285714285714286, + "grad_norm": 3.4302117824554443, + "learning_rate": 1.8229838658936566e-05, + "loss": 0.0197, + "step": 88 + }, + { + "epoch": 6.428571428571429, + "grad_norm": 4.105597496032715, + "learning_rate": 1.81372552039852e-05, + "loss": 0.1183, + "step": 90 + }, + { + "epoch": 6.571428571428571, + "grad_norm": 3.2223429679870605, + "learning_rate": 1.804255972397977e-05, + "loss": 0.006, + "step": 92 + }, + { + "epoch": 6.714285714285714, + "grad_norm": 4.856196403503418, + "learning_rate": 1.7945776797137544e-05, + "loss": 0.0062, + "step": 94 + }, + { + "epoch": 6.857142857142857, + "grad_norm": 1.22345769405365, + "learning_rate": 1.7846931543472722e-05, + "loss": 0.0037, + "step": 96 + }, + { + "epoch": 7.0, + "grad_norm": 8.841476440429688, + "learning_rate": 1.7746049618276545e-05, + "loss": 0.0885, + "step": 98 + }, + { + "epoch": 7.142857142857143, + "grad_norm": 1.7171941995620728, + "learning_rate": 1.7643157205458483e-05, + "loss": 0.0732, + "step": 100 + }, + { + "epoch": 7.285714285714286, + "grad_norm": 0.2902078628540039, + "learning_rate": 1.753828101075017e-05, + "loss": 0.0019, + "step": 102 + }, + { + "epoch": 7.428571428571429, + "grad_norm": 6.003970623016357, + "learning_rate": 1.7431448254773943e-05, + "loss": 0.0219, + "step": 104 + }, + { + "epoch": 7.571428571428571, + "grad_norm": 0.211229145526886, + "learning_rate": 1.7322686665977738e-05, + "loss": 0.0014, + "step": 106 + }, + { + "epoch": 7.714285714285714, + "grad_norm": 14.436793327331543, + "learning_rate": 1.7212024473438145e-05, + "loss": 0.1415, + "step": 108 + }, + { + "epoch": 7.857142857142857, + "grad_norm": 0.05790628120303154, + "learning_rate": 1.7099490399533583e-05, + "loss": 0.0008, + "step": 110 + }, + { + "epoch": 8.0, + "grad_norm": 0.17556001245975494, + "learning_rate": 1.6985113652489374e-05, + "loss": 0.0044, + "step": 112 + }, + { + "epoch": 8.142857142857142, + "grad_norm": 0.38069918751716614, + "learning_rate": 1.6868923918796753e-05, + "loss": 0.001, + "step": 114 + }, + { + "epoch": 8.285714285714286, + "grad_norm": 0.093246690928936, + "learning_rate": 1.6750951355507763e-05, + "loss": 0.0321, + "step": 116 + }, + { + "epoch": 8.428571428571429, + "grad_norm": 0.15035825967788696, + "learning_rate": 1.6631226582407954e-05, + "loss": 0.0036, + "step": 118 + }, + { + "epoch": 8.571428571428571, + "grad_norm": 0.06252682954072952, + "learning_rate": 1.650978067406904e-05, + "loss": 0.0035, + "step": 120 + }, + { + "epoch": 8.714285714285714, + "grad_norm": 6.229085922241211, + "learning_rate": 1.638664515178348e-05, + "loss": 0.1034, + "step": 122 + }, + { + "epoch": 8.857142857142858, + "grad_norm": 2.403806686401367, + "learning_rate": 1.626185197538314e-05, + "loss": 0.036, + "step": 124 + }, + { + "epoch": 9.0, + "grad_norm": 0.07740367949008942, + "learning_rate": 1.613543353494409e-05, + "loss": 0.0006, + "step": 126 + }, + { + "epoch": 9.142857142857142, + "grad_norm": 0.322050541639328, + "learning_rate": 1.600742264237979e-05, + "loss": 0.0013, + "step": 128 + }, + { + "epoch": 9.285714285714286, + "grad_norm": 0.1652839183807373, + "learning_rate": 1.5877852522924733e-05, + "loss": 0.0008, + "step": 130 + }, + { + "epoch": 9.428571428571429, + "grad_norm": 0.048877034336328506, + "learning_rate": 1.574675680651084e-05, + "loss": 0.0008, + "step": 132 + }, + { + "epoch": 9.571428571428571, + "grad_norm": 0.06231057271361351, + "learning_rate": 1.561416951903881e-05, + "loss": 0.0022, + "step": 134 + }, + { + "epoch": 9.714285714285714, + "grad_norm": 0.03611210733652115, + "learning_rate": 1.5480125073546705e-05, + "loss": 0.0389, + "step": 136 + }, + { + "epoch": 9.857142857142858, + "grad_norm": 0.52008056640625, + "learning_rate": 1.5344658261278013e-05, + "loss": 0.0089, + "step": 138 + }, + { + "epoch": 10.0, + "grad_norm": 0.42384108901023865, + "learning_rate": 1.5207804242651625e-05, + "loss": 0.0015, + "step": 140 + }, + { + "epoch": 10.142857142857142, + "grad_norm": 0.055933400988578796, + "learning_rate": 1.5069598538135905e-05, + "loss": 0.0004, + "step": 142 + }, + { + "epoch": 10.285714285714286, + "grad_norm": 0.0212051160633564, + "learning_rate": 1.4930077019029376e-05, + "loss": 0.0072, + "step": 144 + }, + { + "epoch": 10.428571428571429, + "grad_norm": 0.03581853583455086, + "learning_rate": 1.4789275898150309e-05, + "loss": 0.0006, + "step": 146 + }, + { + "epoch": 10.571428571428571, + "grad_norm": 0.021400820463895798, + "learning_rate": 1.4647231720437687e-05, + "loss": 0.0005, + "step": 148 + }, + { + "epoch": 10.714285714285714, + "grad_norm": 1.3550739288330078, + "learning_rate": 1.450398135346597e-05, + "loss": 0.0332, + "step": 150 + }, + { + "epoch": 10.857142857142858, + "grad_norm": 0.014044591225683689, + "learning_rate": 1.4359561977876102e-05, + "loss": 0.0003, + "step": 152 + }, + { + "epoch": 11.0, + "grad_norm": 0.056435056030750275, + "learning_rate": 1.4214011077725293e-05, + "loss": 0.0004, + "step": 154 + }, + { + "epoch": 11.142857142857142, + "grad_norm": 0.012104465626180172, + "learning_rate": 1.4067366430758004e-05, + "loss": 0.0214, + "step": 156 + }, + { + "epoch": 11.285714285714286, + "grad_norm": 0.022569801658391953, + "learning_rate": 1.3919666098600753e-05, + "loss": 0.0003, + "step": 158 + }, + { + "epoch": 11.428571428571429, + "grad_norm": 0.019581535831093788, + "learning_rate": 1.3770948416883205e-05, + "loss": 0.0003, + "step": 160 + }, + { + "epoch": 11.571428571428571, + "grad_norm": 0.012900936417281628, + "learning_rate": 1.362125198528817e-05, + "loss": 0.0003, + "step": 162 + }, + { + "epoch": 11.714285714285714, + "grad_norm": 0.283460795879364, + "learning_rate": 1.347061565753303e-05, + "loss": 0.0151, + "step": 164 + }, + { + "epoch": 11.857142857142858, + "grad_norm": 0.02773939073085785, + "learning_rate": 1.3319078531285286e-05, + "loss": 0.0002, + "step": 166 + }, + { + "epoch": 12.0, + "grad_norm": 0.015381716191768646, + "learning_rate": 1.3166679938014728e-05, + "loss": 0.0002, + "step": 168 + }, + { + "epoch": 12.142857142857142, + "grad_norm": 0.013684879057109356, + "learning_rate": 1.301345943278496e-05, + "loss": 0.0002, + "step": 170 + }, + { + "epoch": 12.285714285714286, + "grad_norm": 0.011124438606202602, + "learning_rate": 1.2859456783986892e-05, + "loss": 0.0002, + "step": 172 + }, + { + "epoch": 12.428571428571429, + "grad_norm": 0.2694200873374939, + "learning_rate": 1.270471196301684e-05, + "loss": 0.0059, + "step": 174 + }, + { + "epoch": 12.571428571428571, + "grad_norm": 0.25839900970458984, + "learning_rate": 1.2549265133901934e-05, + "loss": 0.007, + "step": 176 + }, + { + "epoch": 12.714285714285714, + "grad_norm": 0.28028616309165955, + "learning_rate": 1.2393156642875579e-05, + "loss": 0.0081, + "step": 178 + }, + { + "epoch": 12.857142857142858, + "grad_norm": 0.007691177539527416, + "learning_rate": 1.2236427007905558e-05, + "loss": 0.0004, + "step": 180 + }, + { + "epoch": 13.0, + "grad_norm": 0.03421185538172722, + "learning_rate": 1.2079116908177592e-05, + "loss": 0.0002, + "step": 182 + }, + { + "epoch": 13.142857142857142, + "grad_norm": 0.21886347234249115, + "learning_rate": 1.1921267173537085e-05, + "loss": 0.0106, + "step": 184 + }, + { + "epoch": 13.285714285714286, + "grad_norm": 0.12066204100847244, + "learning_rate": 1.1762918773891691e-05, + "loss": 0.0039, + "step": 186 + }, + { + "epoch": 13.428571428571429, + "grad_norm": 0.009790458716452122, + "learning_rate": 1.1604112808577603e-05, + "loss": 0.0001, + "step": 188 + }, + { + "epoch": 13.571428571428571, + "grad_norm": 0.006134828552603722, + "learning_rate": 1.1444890495692214e-05, + "loss": 0.0001, + "step": 190 + }, + { + "epoch": 13.714285714285714, + "grad_norm": 0.007279029581695795, + "learning_rate": 1.1285293161395948e-05, + "loss": 0.0082, + "step": 192 + }, + { + "epoch": 13.857142857142858, + "grad_norm": 0.007834681309759617, + "learning_rate": 1.1125362229186056e-05, + "loss": 0.0001, + "step": 194 + }, + { + "epoch": 14.0, + "grad_norm": 0.011400113813579082, + "learning_rate": 1.0965139209145153e-05, + "loss": 0.0001, + "step": 196 + }, + { + "epoch": 14.142857142857142, + "grad_norm": 0.005645982455462217, + "learning_rate": 1.0804665687167262e-05, + "loss": 0.0001, + "step": 198 + }, + { + "epoch": 14.285714285714286, + "grad_norm": 0.007113787345588207, + "learning_rate": 1.0643983314164195e-05, + "loss": 0.0046, + "step": 200 + }, + { + "epoch": 14.428571428571429, + "grad_norm": 0.00671082129701972, + "learning_rate": 1.0483133795255072e-05, + "loss": 0.0001, + "step": 202 + }, + { + "epoch": 14.571428571428571, + "grad_norm": 0.10411105304956436, + "learning_rate": 1.0322158878941733e-05, + "loss": 0.0092, + "step": 204 + }, + { + "epoch": 14.714285714285714, + "grad_norm": 0.007047938648611307, + "learning_rate": 1.0161100346272913e-05, + "loss": 0.0046, + "step": 206 + }, + { + "epoch": 14.857142857142858, + "grad_norm": 0.006609996780753136, + "learning_rate": 1e-05, + "loss": 0.0001, + "step": 208 + }, + { + "epoch": 15.0, + "grad_norm": 0.00515047088265419, + "learning_rate": 9.838899653727088e-06, + "loss": 0.0001, + "step": 210 + }, + { + "epoch": 15.142857142857142, + "grad_norm": 0.005954743828624487, + "learning_rate": 9.677841121058274e-06, + "loss": 0.0001, + "step": 212 + }, + { + "epoch": 15.285714285714286, + "grad_norm": 0.19431306421756744, + "learning_rate": 9.516866204744932e-06, + "loss": 0.0046, + "step": 214 + }, + { + "epoch": 15.428571428571429, + "grad_norm": 0.007638772018253803, + "learning_rate": 9.356016685835807e-06, + "loss": 0.0045, + "step": 216 + }, + { + "epoch": 15.571428571428571, + "grad_norm": 0.10914219170808792, + "learning_rate": 9.195334312832742e-06, + "loss": 0.0092, + "step": 218 + }, + { + "epoch": 15.714285714285714, + "grad_norm": 0.005956027191132307, + "learning_rate": 9.034860790854848e-06, + "loss": 0.0001, + "step": 220 + }, + { + "epoch": 15.857142857142858, + "grad_norm": 0.006127700675278902, + "learning_rate": 8.874637770813947e-06, + "loss": 0.0001, + "step": 222 + }, + { + "epoch": 16.0, + "grad_norm": 0.006942708045244217, + "learning_rate": 8.714706838604056e-06, + "loss": 0.0001, + "step": 224 + }, + { + "epoch": 16.142857142857142, + "grad_norm": 0.17752425372600555, + "learning_rate": 8.55510950430779e-06, + "loss": 0.0098, + "step": 226 + }, + { + "epoch": 16.285714285714285, + "grad_norm": 0.004300012718886137, + "learning_rate": 8.395887191422397e-06, + "loss": 0.0001, + "step": 228 + }, + { + "epoch": 16.428571428571427, + "grad_norm": 0.0063268570229411125, + "learning_rate": 8.23708122610831e-06, + "loss": 0.0075, + "step": 230 + }, + { + "epoch": 16.571428571428573, + "grad_norm": 0.005733097437769175, + "learning_rate": 8.078732826462917e-06, + "loss": 0.0001, + "step": 232 + }, + { + "epoch": 16.714285714285715, + "grad_norm": 0.0077501749619841576, + "learning_rate": 7.92088309182241e-06, + "loss": 0.0001, + "step": 234 + }, + { + "epoch": 16.857142857142858, + "grad_norm": 0.005072280764579773, + "learning_rate": 7.763572992094448e-06, + "loss": 0.0001, + "step": 236 + }, + { + "epoch": 17.0, + "grad_norm": 0.007300873752683401, + "learning_rate": 7.606843357124426e-06, + "loss": 0.0001, + "step": 238 + }, + { + "epoch": 17.142857142857142, + "grad_norm": 0.10978183150291443, + "learning_rate": 7.450734866098066e-06, + "loss": 0.0036, + "step": 240 + }, + { + "epoch": 17.285714285714285, + "grad_norm": 0.005480973981320858, + "learning_rate": 7.2952880369831635e-06, + "loss": 0.0061, + "step": 242 + }, + { + "epoch": 17.428571428571427, + "grad_norm": 0.2027699053287506, + "learning_rate": 7.140543216013109e-06, + "loss": 0.0035, + "step": 244 + }, + { + "epoch": 17.571428571428573, + "grad_norm": 0.0048587811179459095, + "learning_rate": 6.986540567215043e-06, + "loss": 0.0001, + "step": 246 + }, + { + "epoch": 17.714285714285715, + "grad_norm": 0.005718125496059656, + "learning_rate": 6.833320061985278e-06, + "loss": 0.0001, + "step": 248 + }, + { + "epoch": 17.857142857142858, + "grad_norm": 0.0035847134422510862, + "learning_rate": 6.680921468714718e-06, + "loss": 0.0052, + "step": 250 + }, + { + "epoch": 18.0, + "grad_norm": 0.0035746165085583925, + "learning_rate": 6.529384342466971e-06, + "loss": 0.0001, + "step": 252 + }, + { + "epoch": 18.142857142857142, + "grad_norm": 0.00451216846704483, + "learning_rate": 6.378748014711834e-06, + "loss": 0.0001, + "step": 254 + }, + { + "epoch": 18.285714285714285, + "grad_norm": 0.004890494979918003, + "learning_rate": 6.229051583116796e-06, + "loss": 0.0001, + "step": 256 + }, + { + "epoch": 18.428571428571427, + "grad_norm": 0.004625991452485323, + "learning_rate": 6.080333901399252e-06, + "loss": 0.0058, + "step": 258 + }, + { + "epoch": 18.571428571428573, + "grad_norm": 0.005847033113241196, + "learning_rate": 5.932633569242e-06, + "loss": 0.0001, + "step": 260 + }, + { + "epoch": 18.714285714285715, + "grad_norm": 0.006245823111385107, + "learning_rate": 5.785988922274711e-06, + "loss": 0.0072, + "step": 262 + }, + { + "epoch": 18.857142857142858, + "grad_norm": 0.08823557943105698, + "learning_rate": 5.640438022123898e-06, + "loss": 0.0034, + "step": 264 + }, + { + "epoch": 19.0, + "grad_norm": 0.004038456827402115, + "learning_rate": 5.496018646534032e-06, + "loss": 0.0001, + "step": 266 + }, + { + "epoch": 19.142857142857142, + "grad_norm": 0.005825538653880358, + "learning_rate": 5.352768279562315e-06, + "loss": 0.0056, + "step": 268 + }, + { + "epoch": 19.285714285714285, + "grad_norm": 0.004666970111429691, + "learning_rate": 5.210724101849696e-06, + "loss": 0.0001, + "step": 270 + }, + { + "epoch": 19.428571428571427, + "grad_norm": 0.004332971293479204, + "learning_rate": 5.069922980970626e-06, + "loss": 0.0001, + "step": 272 + }, + { + "epoch": 19.571428571428573, + "grad_norm": 0.09540804475545883, + "learning_rate": 4.930401461864099e-06, + "loss": 0.0085, + "step": 274 + }, + { + "epoch": 19.714285714285715, + "grad_norm": 0.004319526720792055, + "learning_rate": 4.7921957573483756e-06, + "loss": 0.0001, + "step": 276 + }, + { + "epoch": 19.857142857142858, + "grad_norm": 0.00582715030759573, + "learning_rate": 4.655341738721989e-06, + "loss": 0.0001, + "step": 278 + }, + { + "epoch": 20.0, + "grad_norm": 0.005314113572239876, + "learning_rate": 4.519874926453303e-06, + "loss": 0.0001, + "step": 280 + }, + { + "epoch": 20.142857142857142, + "grad_norm": 0.006195093505084515, + "learning_rate": 4.385830480961192e-06, + "loss": 0.0001, + "step": 282 + }, + { + "epoch": 20.285714285714285, + "grad_norm": 0.004151402972638607, + "learning_rate": 4.2532431934891646e-06, + "loss": 0.0001, + "step": 284 + }, + { + "epoch": 20.428571428571427, + "grad_norm": 0.004392064176499844, + "learning_rate": 4.12214747707527e-06, + "loss": 0.0047, + "step": 286 + }, + { + "epoch": 20.571428571428573, + "grad_norm": 0.004756106063723564, + "learning_rate": 3.99257735762021e-06, + "loss": 0.0001, + "step": 288 + }, + { + "epoch": 20.714285714285715, + "grad_norm": 0.004611567594110966, + "learning_rate": 3.864566465055913e-06, + "loss": 0.0022, + "step": 290 + }, + { + "epoch": 20.857142857142858, + "grad_norm": 0.004500643815845251, + "learning_rate": 3.738148024616863e-06, + "loss": 0.0001, + "step": 292 + }, + { + "epoch": 21.0, + "grad_norm": 0.0058865793980658054, + "learning_rate": 3.6133548482165225e-06, + "loss": 0.0081, + "step": 294 + }, + { + "epoch": 21.142857142857142, + "grad_norm": 0.096845842897892, + "learning_rate": 3.4902193259309627e-06, + "loss": 0.0037, + "step": 296 + }, + { + "epoch": 21.285714285714285, + "grad_norm": 0.0038972089532762766, + "learning_rate": 3.3687734175920505e-06, + "loss": 0.0001, + "step": 298 + }, + { + "epoch": 21.428571428571427, + "grad_norm": 0.004685294348746538, + "learning_rate": 3.2490486444922396e-06, + "loss": 0.0001, + "step": 300 + }, + { + "epoch": 21.571428571428573, + "grad_norm": 0.20793084800243378, + "learning_rate": 3.131076081203247e-06, + "loss": 0.0019, + "step": 302 + }, + { + "epoch": 21.714285714285715, + "grad_norm": 0.0035532894544303417, + "learning_rate": 3.0148863475106315e-06, + "loss": 0.0058, + "step": 304 + }, + { + "epoch": 21.857142857142858, + "grad_norm": 0.2300863116979599, + "learning_rate": 2.900509600466418e-06, + "loss": 0.0025, + "step": 306 + }, + { + "epoch": 22.0, + "grad_norm": 0.007288255728781223, + "learning_rate": 2.7879755265618558e-06, + "loss": 0.0001, + "step": 308 + }, + { + "epoch": 22.142857142857142, + "grad_norm": 0.005309649743139744, + "learning_rate": 2.6773133340222677e-06, + "loss": 0.0016, + "step": 310 + }, + { + "epoch": 22.285714285714285, + "grad_norm": 0.003941751550883055, + "learning_rate": 2.5685517452260566e-06, + "loss": 0.0001, + "step": 312 + }, + { + "epoch": 22.428571428571427, + "grad_norm": 0.004016744904220104, + "learning_rate": 2.4617189892498326e-06, + "loss": 0.0001, + "step": 314 + }, + { + "epoch": 22.571428571428573, + "grad_norm": 0.13147950172424316, + "learning_rate": 2.3568427945415163e-06, + "loss": 0.0064, + "step": 316 + }, + { + "epoch": 22.714285714285715, + "grad_norm": 0.003918132279068232, + "learning_rate": 2.2539503817234553e-06, + "loss": 0.0001, + "step": 318 + }, + { + "epoch": 22.857142857142858, + "grad_norm": 0.004725574050098658, + "learning_rate": 2.153068456527283e-06, + "loss": 0.0001, + "step": 320 + }, + { + "epoch": 23.0, + "grad_norm": 0.3711271584033966, + "learning_rate": 2.0542232028624585e-06, + "loss": 0.0175, + "step": 322 + }, + { + "epoch": 23.142857142857142, + "grad_norm": 0.18150761723518372, + "learning_rate": 1.9574402760202315e-06, + "loss": 0.0023, + "step": 324 + }, + { + "epoch": 23.285714285714285, + "grad_norm": 0.13696324825286865, + "learning_rate": 1.8627447960148036e-06, + "loss": 0.0045, + "step": 326 + }, + { + "epoch": 23.428571428571427, + "grad_norm": 0.004304251167923212, + "learning_rate": 1.7701613410634367e-06, + "loss": 0.0001, + "step": 328 + }, + { + "epoch": 23.571428571428573, + "grad_norm": 0.005392234306782484, + "learning_rate": 1.6797139412071583e-06, + "loss": 0.0001, + "step": 330 + }, + { + "epoch": 23.714285714285715, + "grad_norm": 0.004501474089920521, + "learning_rate": 1.5914260720737796e-06, + "loss": 0.0001, + "step": 332 + }, + { + "epoch": 23.857142857142858, + "grad_norm": 0.0033914605155587196, + "learning_rate": 1.5053206487847916e-06, + "loss": 0.0047, + "step": 334 + }, + { + "epoch": 24.0, + "grad_norm": 0.005722349975258112, + "learning_rate": 1.4214200200077343e-06, + "loss": 0.0001, + "step": 336 + }, + { + "epoch": 24.142857142857142, + "grad_norm": 0.0028757653199136257, + "learning_rate": 1.339745962155613e-06, + "loss": 0.0001, + "step": 338 + }, + { + "epoch": 24.285714285714285, + "grad_norm": 0.004367240238934755, + "learning_rate": 1.2603196737348211e-06, + "loss": 0.0012, + "step": 340 + }, + { + "epoch": 24.428571428571427, + "grad_norm": 0.004103364888578653, + "learning_rate": 1.1831617698430609e-06, + "loss": 0.0001, + "step": 342 + }, + { + "epoch": 24.571428571428573, + "grad_norm": 0.12380176037549973, + "learning_rate": 1.1082922768187098e-06, + "loss": 0.0053, + "step": 344 + }, + { + "epoch": 24.714285714285715, + "grad_norm": 0.11978839337825775, + "learning_rate": 1.0357306270429623e-06, + "loss": 0.0045, + "step": 346 + }, + { + "epoch": 24.857142857142858, + "grad_norm": 0.15920782089233398, + "learning_rate": 9.65495653896179e-07, + "loss": 0.0008, + "step": 348 + }, + { + "epoch": 25.0, + "grad_norm": 0.005539704114198685, + "learning_rate": 8.976055868696543e-07, + "loss": 0.0001, + "step": 350 + }, + { + "epoch": 25.142857142857142, + "grad_norm": 0.004604020155966282, + "learning_rate": 8.320780468341761e-07, + "loss": 0.0001, + "step": 352 + }, + { + "epoch": 25.285714285714285, + "grad_norm": 0.19128715991973877, + "learning_rate": 7.689300414665124e-07, + "loss": 0.0012, + "step": 354 + }, + { + "epoch": 25.428571428571427, + "grad_norm": 0.0033012081403285265, + "learning_rate": 7.08177960835068e-07, + "loss": 0.0067, + "step": 356 + }, + { + "epoch": 25.571428571428573, + "grad_norm": 0.09938196837902069, + "learning_rate": 6.498375731458529e-07, + "loss": 0.0005, + "step": 358 + }, + { + "epoch": 25.714285714285715, + "grad_norm": 0.0049908701330423355, + "learning_rate": 5.939240206498287e-07, + "loss": 0.0001, + "step": 360 + }, + { + "epoch": 25.857142857142858, + "grad_norm": 0.0035182549618184566, + "learning_rate": 5.404518157127481e-07, + "loss": 0.0046, + "step": 362 + }, + { + "epoch": 26.0, + "grad_norm": 0.0068074483424425125, + "learning_rate": 4.894348370484648e-07, + "loss": 0.0001, + "step": 364 + }, + { + "epoch": 26.142857142857142, + "grad_norm": 0.004269490484148264, + "learning_rate": 4.408863261167096e-07, + "loss": 0.0001, + "step": 366 + }, + { + "epoch": 26.285714285714285, + "grad_norm": 0.12823165953159332, + "learning_rate": 3.9481888368627764e-07, + "loss": 0.0042, + "step": 368 + }, + { + "epoch": 26.428571428571427, + "grad_norm": 0.0035812160931527615, + "learning_rate": 3.5124446656448654e-07, + "loss": 0.0001, + "step": 370 + }, + { + "epoch": 26.571428571428573, + "grad_norm": 0.00431048171594739, + "learning_rate": 3.101743844937943e-07, + "loss": 0.0059, + "step": 372 + }, + { + "epoch": 26.714285714285715, + "grad_norm": 0.004997176583856344, + "learning_rate": 2.716192972163556e-07, + "loss": 0.0001, + "step": 374 + }, + { + "epoch": 26.857142857142858, + "grad_norm": 0.004221776034682989, + "learning_rate": 2.355892117072789e-07, + "loss": 0.0001, + "step": 376 + }, + { + "epoch": 27.0, + "grad_norm": 0.007233808748424053, + "learning_rate": 2.0209347957732328e-07, + "loss": 0.0008, + "step": 378 + }, + { + "epoch": 27.142857142857142, + "grad_norm": 0.0030983760952949524, + "learning_rate": 1.711407946456789e-07, + "loss": 0.0001, + "step": 380 + }, + { + "epoch": 27.285714285714285, + "grad_norm": 0.13253678381443024, + "learning_rate": 1.4273919068349184e-07, + "loss": 0.0014, + "step": 382 + }, + { + "epoch": 27.428571428571427, + "grad_norm": 0.003873329609632492, + "learning_rate": 1.1689603932869664e-07, + "loss": 0.0001, + "step": 384 + }, + { + "epoch": 27.571428571428573, + "grad_norm": 0.005466313101351261, + "learning_rate": 9.36180481727067e-08, + "loss": 0.0046, + "step": 386 + }, + { + "epoch": 27.714285714285715, + "grad_norm": 0.004763293080031872, + "learning_rate": 7.291125901946027e-08, + "loss": 0.0001, + "step": 388 + }, + { + "epoch": 27.857142857142858, + "grad_norm": 0.11048487573862076, + "learning_rate": 5.4781046317267103e-08, + "loss": 0.0048, + "step": 390 + }, + { + "epoch": 28.0, + "grad_norm": 0.007729329634457827, + "learning_rate": 3.923211576387087e-08, + "loss": 0.0001, + "step": 392 + } + ], + "logging_steps": 2, + "max_steps": 402, + "num_input_tokens_seen": 0, + "num_train_epochs": 29, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.0147722535829504e+16, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-392/training_args.bin b/checkpoint-392/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5e40431601fe0fda63821c355ca2518b79c42df --- /dev/null +++ b/checkpoint-392/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25a0ccf5317ebd8f7cfcaefcfdfd3860c0c2887188910c19a4b9dde7e5910b1 +size 6520 diff --git a/checkpoint-402/README.md b/checkpoint-402/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ae0ed615fe362734126a5801320301bdfc158e46 --- /dev/null +++ b/checkpoint-402/README.md @@ -0,0 +1,202 @@ +--- +base_model: google/gemma-2-9b-it +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.15.2 \ No newline at end of file diff --git a/checkpoint-402/adapter_config.json b/checkpoint-402/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0903ea87f348df7f18650f0467f8051ebdd53938 --- /dev/null +++ b/checkpoint-402/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "google/gemma-2-9b-it", + "bias": "none", + "corda_config": null, + "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": 256, + "lora_bias": false, + "lora_dropout": 0.1, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 128, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "up_proj", + "q_proj", + "o_proj", + "k_proj", + "down_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-402/adapter_model.safetensors b/checkpoint-402/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b95539507d87439df973cf5055af06d60a06d40a --- /dev/null +++ b/checkpoint-402/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ec6c916b9df77c8ab3fd504fae3a8cab10f1c25a8425cfc726a8fd5ebde9e1 +size 1728658208 diff --git a/checkpoint-402/chat_template.jinja b/checkpoint-402/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..923ec253c8dbefbb41cf084db7251df41d000f6d --- /dev/null +++ b/checkpoint-402/chat_template.jinja @@ -0,0 +1,4 @@ +{{ 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 + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/checkpoint-402/optimizer.pt b/checkpoint-402/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2994fe6d0f54bdd21777193e58bf0e3d3f44730f --- /dev/null +++ b/checkpoint-402/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360a6529372ce9a224d7e0692371c67432d52b44f2253c7e84ce7b741ef31f82 +size 878485380 diff --git a/checkpoint-402/rng_state.pth b/checkpoint-402/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac7795c3812244a55cbdaafb9f31d560679e9d88 --- /dev/null +++ b/checkpoint-402/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d942d61d6d5f446e91151e28eeb4ceb11ebac34b50daecf2960117a00cf8233 +size 14244 diff --git a/checkpoint-402/scheduler.pt b/checkpoint-402/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b048bd2add95fd9da76a36d039e885695cf6081 --- /dev/null +++ b/checkpoint-402/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5b7f865fff447a834d063766ffbff2b06cf8776b1ce383609115b7efb4a180 +size 1064 diff --git a/checkpoint-402/special_tokens_map.json b/checkpoint-402/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..8d6368f7e735fbe4781bf6e956b7c6ad0586df80 --- /dev/null +++ b/checkpoint-402/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-402/tokenizer.json b/checkpoint-402/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a4a305d1de4d8f47c0252b4d7fe65a10dd8e2c22 --- /dev/null +++ b/checkpoint-402/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060 +size 34362873 diff --git a/checkpoint-402/tokenizer.model b/checkpoint-402/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/checkpoint-402/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/checkpoint-402/tokenizer_config.json b/checkpoint-402/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3ade6be57196932063a48c1329fbf9c2e7e154d1 --- /dev/null +++ b/checkpoint-402/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

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

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

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

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

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "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-402/trainer_state.json b/checkpoint-402/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..cdb3f3c91d52459780f1fad73d9fc52ab017a02f --- /dev/null +++ b/checkpoint-402/trainer_state.json @@ -0,0 +1,1441 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 28.714285714285715, + "eval_steps": 500, + "global_step": 402, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.14285714285714285, + "grad_norm": 49.90940856933594, + "learning_rate": 1.6666666666666667e-06, + "loss": 6.0076, + "step": 2 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 44.15715789794922, + "learning_rate": 5e-06, + "loss": 5.6559, + "step": 4 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 56.16670608520508, + "learning_rate": 8.333333333333334e-06, + "loss": 4.4368, + "step": 6 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 23.919437408447266, + "learning_rate": 1.1666666666666668e-05, + "loss": 2.7657, + "step": 8 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 20.757640838623047, + "learning_rate": 1.5000000000000002e-05, + "loss": 2.3404, + "step": 10 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 16.067575454711914, + "learning_rate": 1.8333333333333333e-05, + "loss": 2.038, + "step": 12 + }, + { + "epoch": 1.0, + "grad_norm": 23.458139419555664, + "learning_rate": 1.9999675557165282e-05, + "loss": 1.5809, + "step": 14 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 11.104408264160156, + "learning_rate": 1.9997080140801932e-05, + "loss": 1.1148, + "step": 16 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 11.328217506408691, + "learning_rate": 1.9991889981715696e-05, + "loss": 1.2528, + "step": 18 + }, + { + "epoch": 1.4285714285714286, + "grad_norm": 12.313949584960938, + "learning_rate": 1.9984106427012667e-05, + "loss": 1.2324, + "step": 20 + }, + { + "epoch": 1.5714285714285714, + "grad_norm": 10.425058364868164, + "learning_rate": 1.9973731496914914e-05, + "loss": 1.0203, + "step": 22 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 12.36324691772461, + "learning_rate": 1.9960767884236132e-05, + "loss": 1.0997, + "step": 24 + }, + { + "epoch": 1.8571428571428572, + "grad_norm": 14.280921936035156, + "learning_rate": 1.9945218953682736e-05, + "loss": 1.43, + "step": 26 + }, + { + "epoch": 2.0, + "grad_norm": 20.082475662231445, + "learning_rate": 1.992708874098054e-05, + "loss": 1.0748, + "step": 28 + }, + { + "epoch": 2.142857142857143, + "grad_norm": 5.667484283447266, + "learning_rate": 1.9906381951827295e-05, + "loss": 0.3794, + "step": 30 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 6.214536666870117, + "learning_rate": 1.9883103960671305e-05, + "loss": 0.2747, + "step": 32 + }, + { + "epoch": 2.4285714285714284, + "grad_norm": 6.836840629577637, + "learning_rate": 1.985726080931651e-05, + "loss": 0.2568, + "step": 34 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 13.044551849365234, + "learning_rate": 1.9828859205354326e-05, + "loss": 0.2937, + "step": 36 + }, + { + "epoch": 2.7142857142857144, + "grad_norm": 8.866482734680176, + "learning_rate": 1.979790652042268e-05, + "loss": 0.4252, + "step": 38 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 8.709479331970215, + "learning_rate": 1.9764410788292724e-05, + "loss": 0.3599, + "step": 40 + }, + { + "epoch": 3.0, + "grad_norm": 9.43436050415039, + "learning_rate": 1.9728380702783644e-05, + "loss": 0.3578, + "step": 42 + }, + { + "epoch": 3.142857142857143, + "grad_norm": 1.2470844984054565, + "learning_rate": 1.968982561550621e-05, + "loss": 0.1155, + "step": 44 + }, + { + "epoch": 3.2857142857142856, + "grad_norm": 5.716163635253906, + "learning_rate": 1.9648755533435517e-05, + "loss": 0.0708, + "step": 46 + }, + { + "epoch": 3.4285714285714284, + "grad_norm": 6.77197790145874, + "learning_rate": 1.9605181116313725e-05, + "loss": 0.081, + "step": 48 + }, + { + "epoch": 3.571428571428571, + "grad_norm": 5.336516380310059, + "learning_rate": 1.955911367388329e-05, + "loss": 0.112, + "step": 50 + }, + { + "epoch": 3.7142857142857144, + "grad_norm": 10.314866065979004, + "learning_rate": 1.9510565162951538e-05, + "loss": 0.0958, + "step": 52 + }, + { + "epoch": 3.857142857142857, + "grad_norm": 5.841635704040527, + "learning_rate": 1.9459548184287254e-05, + "loss": 0.0593, + "step": 54 + }, + { + "epoch": 4.0, + "grad_norm": 10.58973503112793, + "learning_rate": 1.9406075979350175e-05, + "loss": 0.2013, + "step": 56 + }, + { + "epoch": 4.142857142857143, + "grad_norm": 3.521483898162842, + "learning_rate": 1.9350162426854152e-05, + "loss": 0.0563, + "step": 58 + }, + { + "epoch": 4.285714285714286, + "grad_norm": 1.0017471313476562, + "learning_rate": 1.9291822039164934e-05, + "loss": 0.1029, + "step": 60 + }, + { + "epoch": 4.428571428571429, + "grad_norm": 0.33161500096321106, + "learning_rate": 1.923106995853349e-05, + "loss": 0.024, + "step": 62 + }, + { + "epoch": 4.571428571428571, + "grad_norm": 6.284483432769775, + "learning_rate": 1.9167921953165827e-05, + "loss": 0.1092, + "step": 64 + }, + { + "epoch": 4.714285714285714, + "grad_norm": 3.3121423721313477, + "learning_rate": 1.9102394413130348e-05, + "loss": 0.0401, + "step": 66 + }, + { + "epoch": 4.857142857142857, + "grad_norm": 8.295348167419434, + "learning_rate": 1.9034504346103825e-05, + "loss": 0.3237, + "step": 68 + }, + { + "epoch": 5.0, + "grad_norm": 2.1199071407318115, + "learning_rate": 1.896426937295704e-05, + "loss": 0.0375, + "step": 70 + }, + { + "epoch": 5.142857142857143, + "grad_norm": 0.45601171255111694, + "learning_rate": 1.8891707723181294e-05, + "loss": 0.0319, + "step": 72 + }, + { + "epoch": 5.285714285714286, + "grad_norm": 1.0054666996002197, + "learning_rate": 1.881683823015694e-05, + "loss": 0.0097, + "step": 74 + }, + { + "epoch": 5.428571428571429, + "grad_norm": 0.8899504542350769, + "learning_rate": 1.873968032626518e-05, + "loss": 0.0769, + "step": 76 + }, + { + "epoch": 5.571428571428571, + "grad_norm": 0.49617600440979004, + "learning_rate": 1.866025403784439e-05, + "loss": 0.0479, + "step": 78 + }, + { + "epoch": 5.714285714285714, + "grad_norm": 0.16562028229236603, + "learning_rate": 1.8578579979992266e-05, + "loss": 0.0051, + "step": 80 + }, + { + "epoch": 5.857142857142857, + "grad_norm": 11.048959732055664, + "learning_rate": 1.8494679351215212e-05, + "loss": 0.0984, + "step": 82 + }, + { + "epoch": 6.0, + "grad_norm": 7.846388816833496, + "learning_rate": 1.8408573927926225e-05, + "loss": 0.116, + "step": 84 + }, + { + "epoch": 6.142857142857143, + "grad_norm": 0.11113756895065308, + "learning_rate": 1.8320286058792845e-05, + "loss": 0.0027, + "step": 86 + }, + { + "epoch": 6.285714285714286, + "grad_norm": 3.4302117824554443, + "learning_rate": 1.8229838658936566e-05, + "loss": 0.0197, + "step": 88 + }, + { + "epoch": 6.428571428571429, + "grad_norm": 4.105597496032715, + "learning_rate": 1.81372552039852e-05, + "loss": 0.1183, + "step": 90 + }, + { + "epoch": 6.571428571428571, + "grad_norm": 3.2223429679870605, + "learning_rate": 1.804255972397977e-05, + "loss": 0.006, + "step": 92 + }, + { + "epoch": 6.714285714285714, + "grad_norm": 4.856196403503418, + "learning_rate": 1.7945776797137544e-05, + "loss": 0.0062, + "step": 94 + }, + { + "epoch": 6.857142857142857, + "grad_norm": 1.22345769405365, + "learning_rate": 1.7846931543472722e-05, + "loss": 0.0037, + "step": 96 + }, + { + "epoch": 7.0, + "grad_norm": 8.841476440429688, + "learning_rate": 1.7746049618276545e-05, + "loss": 0.0885, + "step": 98 + }, + { + "epoch": 7.142857142857143, + "grad_norm": 1.7171941995620728, + "learning_rate": 1.7643157205458483e-05, + "loss": 0.0732, + "step": 100 + }, + { + "epoch": 7.285714285714286, + "grad_norm": 0.2902078628540039, + "learning_rate": 1.753828101075017e-05, + "loss": 0.0019, + "step": 102 + }, + { + "epoch": 7.428571428571429, + "grad_norm": 6.003970623016357, + "learning_rate": 1.7431448254773943e-05, + "loss": 0.0219, + "step": 104 + }, + { + "epoch": 7.571428571428571, + "grad_norm": 0.211229145526886, + "learning_rate": 1.7322686665977738e-05, + "loss": 0.0014, + "step": 106 + }, + { + "epoch": 7.714285714285714, + "grad_norm": 14.436793327331543, + "learning_rate": 1.7212024473438145e-05, + "loss": 0.1415, + "step": 108 + }, + { + "epoch": 7.857142857142857, + "grad_norm": 0.05790628120303154, + "learning_rate": 1.7099490399533583e-05, + "loss": 0.0008, + "step": 110 + }, + { + "epoch": 8.0, + "grad_norm": 0.17556001245975494, + "learning_rate": 1.6985113652489374e-05, + "loss": 0.0044, + "step": 112 + }, + { + "epoch": 8.142857142857142, + "grad_norm": 0.38069918751716614, + "learning_rate": 1.6868923918796753e-05, + "loss": 0.001, + "step": 114 + }, + { + "epoch": 8.285714285714286, + "grad_norm": 0.093246690928936, + "learning_rate": 1.6750951355507763e-05, + "loss": 0.0321, + "step": 116 + }, + { + "epoch": 8.428571428571429, + "grad_norm": 0.15035825967788696, + "learning_rate": 1.6631226582407954e-05, + "loss": 0.0036, + "step": 118 + }, + { + "epoch": 8.571428571428571, + "grad_norm": 0.06252682954072952, + "learning_rate": 1.650978067406904e-05, + "loss": 0.0035, + "step": 120 + }, + { + "epoch": 8.714285714285714, + "grad_norm": 6.229085922241211, + "learning_rate": 1.638664515178348e-05, + "loss": 0.1034, + "step": 122 + }, + { + "epoch": 8.857142857142858, + "grad_norm": 2.403806686401367, + "learning_rate": 1.626185197538314e-05, + "loss": 0.036, + "step": 124 + }, + { + "epoch": 9.0, + "grad_norm": 0.07740367949008942, + "learning_rate": 1.613543353494409e-05, + "loss": 0.0006, + "step": 126 + }, + { + "epoch": 9.142857142857142, + "grad_norm": 0.322050541639328, + "learning_rate": 1.600742264237979e-05, + "loss": 0.0013, + "step": 128 + }, + { + "epoch": 9.285714285714286, + "grad_norm": 0.1652839183807373, + "learning_rate": 1.5877852522924733e-05, + "loss": 0.0008, + "step": 130 + }, + { + "epoch": 9.428571428571429, + "grad_norm": 0.048877034336328506, + "learning_rate": 1.574675680651084e-05, + "loss": 0.0008, + "step": 132 + }, + { + "epoch": 9.571428571428571, + "grad_norm": 0.06231057271361351, + "learning_rate": 1.561416951903881e-05, + "loss": 0.0022, + "step": 134 + }, + { + "epoch": 9.714285714285714, + "grad_norm": 0.03611210733652115, + "learning_rate": 1.5480125073546705e-05, + "loss": 0.0389, + "step": 136 + }, + { + "epoch": 9.857142857142858, + "grad_norm": 0.52008056640625, + "learning_rate": 1.5344658261278013e-05, + "loss": 0.0089, + "step": 138 + }, + { + "epoch": 10.0, + "grad_norm": 0.42384108901023865, + "learning_rate": 1.5207804242651625e-05, + "loss": 0.0015, + "step": 140 + }, + { + "epoch": 10.142857142857142, + "grad_norm": 0.055933400988578796, + "learning_rate": 1.5069598538135905e-05, + "loss": 0.0004, + "step": 142 + }, + { + "epoch": 10.285714285714286, + "grad_norm": 0.0212051160633564, + "learning_rate": 1.4930077019029376e-05, + "loss": 0.0072, + "step": 144 + }, + { + "epoch": 10.428571428571429, + "grad_norm": 0.03581853583455086, + "learning_rate": 1.4789275898150309e-05, + "loss": 0.0006, + "step": 146 + }, + { + "epoch": 10.571428571428571, + "grad_norm": 0.021400820463895798, + "learning_rate": 1.4647231720437687e-05, + "loss": 0.0005, + "step": 148 + }, + { + "epoch": 10.714285714285714, + "grad_norm": 1.3550739288330078, + "learning_rate": 1.450398135346597e-05, + "loss": 0.0332, + "step": 150 + }, + { + "epoch": 10.857142857142858, + "grad_norm": 0.014044591225683689, + "learning_rate": 1.4359561977876102e-05, + "loss": 0.0003, + "step": 152 + }, + { + "epoch": 11.0, + "grad_norm": 0.056435056030750275, + "learning_rate": 1.4214011077725293e-05, + "loss": 0.0004, + "step": 154 + }, + { + "epoch": 11.142857142857142, + "grad_norm": 0.012104465626180172, + "learning_rate": 1.4067366430758004e-05, + "loss": 0.0214, + "step": 156 + }, + { + "epoch": 11.285714285714286, + "grad_norm": 0.022569801658391953, + "learning_rate": 1.3919666098600753e-05, + "loss": 0.0003, + "step": 158 + }, + { + "epoch": 11.428571428571429, + "grad_norm": 0.019581535831093788, + "learning_rate": 1.3770948416883205e-05, + "loss": 0.0003, + "step": 160 + }, + { + "epoch": 11.571428571428571, + "grad_norm": 0.012900936417281628, + "learning_rate": 1.362125198528817e-05, + "loss": 0.0003, + "step": 162 + }, + { + "epoch": 11.714285714285714, + "grad_norm": 0.283460795879364, + "learning_rate": 1.347061565753303e-05, + "loss": 0.0151, + "step": 164 + }, + { + "epoch": 11.857142857142858, + "grad_norm": 0.02773939073085785, + "learning_rate": 1.3319078531285286e-05, + "loss": 0.0002, + "step": 166 + }, + { + "epoch": 12.0, + "grad_norm": 0.015381716191768646, + "learning_rate": 1.3166679938014728e-05, + "loss": 0.0002, + "step": 168 + }, + { + "epoch": 12.142857142857142, + "grad_norm": 0.013684879057109356, + "learning_rate": 1.301345943278496e-05, + "loss": 0.0002, + "step": 170 + }, + { + "epoch": 12.285714285714286, + "grad_norm": 0.011124438606202602, + "learning_rate": 1.2859456783986892e-05, + "loss": 0.0002, + "step": 172 + }, + { + "epoch": 12.428571428571429, + "grad_norm": 0.2694200873374939, + "learning_rate": 1.270471196301684e-05, + "loss": 0.0059, + "step": 174 + }, + { + "epoch": 12.571428571428571, + "grad_norm": 0.25839900970458984, + "learning_rate": 1.2549265133901934e-05, + "loss": 0.007, + "step": 176 + }, + { + "epoch": 12.714285714285714, + "grad_norm": 0.28028616309165955, + "learning_rate": 1.2393156642875579e-05, + "loss": 0.0081, + "step": 178 + }, + { + "epoch": 12.857142857142858, + "grad_norm": 0.007691177539527416, + "learning_rate": 1.2236427007905558e-05, + "loss": 0.0004, + "step": 180 + }, + { + "epoch": 13.0, + "grad_norm": 0.03421185538172722, + "learning_rate": 1.2079116908177592e-05, + "loss": 0.0002, + "step": 182 + }, + { + "epoch": 13.142857142857142, + "grad_norm": 0.21886347234249115, + "learning_rate": 1.1921267173537085e-05, + "loss": 0.0106, + "step": 184 + }, + { + "epoch": 13.285714285714286, + "grad_norm": 0.12066204100847244, + "learning_rate": 1.1762918773891691e-05, + "loss": 0.0039, + "step": 186 + }, + { + "epoch": 13.428571428571429, + "grad_norm": 0.009790458716452122, + "learning_rate": 1.1604112808577603e-05, + "loss": 0.0001, + "step": 188 + }, + { + "epoch": 13.571428571428571, + "grad_norm": 0.006134828552603722, + "learning_rate": 1.1444890495692214e-05, + "loss": 0.0001, + "step": 190 + }, + { + "epoch": 13.714285714285714, + "grad_norm": 0.007279029581695795, + "learning_rate": 1.1285293161395948e-05, + "loss": 0.0082, + "step": 192 + }, + { + "epoch": 13.857142857142858, + "grad_norm": 0.007834681309759617, + "learning_rate": 1.1125362229186056e-05, + "loss": 0.0001, + "step": 194 + }, + { + "epoch": 14.0, + "grad_norm": 0.011400113813579082, + "learning_rate": 1.0965139209145153e-05, + "loss": 0.0001, + "step": 196 + }, + { + "epoch": 14.142857142857142, + "grad_norm": 0.005645982455462217, + "learning_rate": 1.0804665687167262e-05, + "loss": 0.0001, + "step": 198 + }, + { + "epoch": 14.285714285714286, + "grad_norm": 0.007113787345588207, + "learning_rate": 1.0643983314164195e-05, + "loss": 0.0046, + "step": 200 + }, + { + "epoch": 14.428571428571429, + "grad_norm": 0.00671082129701972, + "learning_rate": 1.0483133795255072e-05, + "loss": 0.0001, + "step": 202 + }, + { + "epoch": 14.571428571428571, + "grad_norm": 0.10411105304956436, + "learning_rate": 1.0322158878941733e-05, + "loss": 0.0092, + "step": 204 + }, + { + "epoch": 14.714285714285714, + "grad_norm": 0.007047938648611307, + "learning_rate": 1.0161100346272913e-05, + "loss": 0.0046, + "step": 206 + }, + { + "epoch": 14.857142857142858, + "grad_norm": 0.006609996780753136, + "learning_rate": 1e-05, + "loss": 0.0001, + "step": 208 + }, + { + "epoch": 15.0, + "grad_norm": 0.00515047088265419, + "learning_rate": 9.838899653727088e-06, + "loss": 0.0001, + "step": 210 + }, + { + "epoch": 15.142857142857142, + "grad_norm": 0.005954743828624487, + "learning_rate": 9.677841121058274e-06, + "loss": 0.0001, + "step": 212 + }, + { + "epoch": 15.285714285714286, + "grad_norm": 0.19431306421756744, + "learning_rate": 9.516866204744932e-06, + "loss": 0.0046, + "step": 214 + }, + { + "epoch": 15.428571428571429, + "grad_norm": 0.007638772018253803, + "learning_rate": 9.356016685835807e-06, + "loss": 0.0045, + "step": 216 + }, + { + "epoch": 15.571428571428571, + "grad_norm": 0.10914219170808792, + "learning_rate": 9.195334312832742e-06, + "loss": 0.0092, + "step": 218 + }, + { + "epoch": 15.714285714285714, + "grad_norm": 0.005956027191132307, + "learning_rate": 9.034860790854848e-06, + "loss": 0.0001, + "step": 220 + }, + { + "epoch": 15.857142857142858, + "grad_norm": 0.006127700675278902, + "learning_rate": 8.874637770813947e-06, + "loss": 0.0001, + "step": 222 + }, + { + "epoch": 16.0, + "grad_norm": 0.006942708045244217, + "learning_rate": 8.714706838604056e-06, + "loss": 0.0001, + "step": 224 + }, + { + "epoch": 16.142857142857142, + "grad_norm": 0.17752425372600555, + "learning_rate": 8.55510950430779e-06, + "loss": 0.0098, + "step": 226 + }, + { + "epoch": 16.285714285714285, + "grad_norm": 0.004300012718886137, + "learning_rate": 8.395887191422397e-06, + "loss": 0.0001, + "step": 228 + }, + { + "epoch": 16.428571428571427, + "grad_norm": 0.0063268570229411125, + "learning_rate": 8.23708122610831e-06, + "loss": 0.0075, + "step": 230 + }, + { + "epoch": 16.571428571428573, + "grad_norm": 0.005733097437769175, + "learning_rate": 8.078732826462917e-06, + "loss": 0.0001, + "step": 232 + }, + { + "epoch": 16.714285714285715, + "grad_norm": 0.0077501749619841576, + "learning_rate": 7.92088309182241e-06, + "loss": 0.0001, + "step": 234 + }, + { + "epoch": 16.857142857142858, + "grad_norm": 0.005072280764579773, + "learning_rate": 7.763572992094448e-06, + "loss": 0.0001, + "step": 236 + }, + { + "epoch": 17.0, + "grad_norm": 0.007300873752683401, + "learning_rate": 7.606843357124426e-06, + "loss": 0.0001, + "step": 238 + }, + { + "epoch": 17.142857142857142, + "grad_norm": 0.10978183150291443, + "learning_rate": 7.450734866098066e-06, + "loss": 0.0036, + "step": 240 + }, + { + "epoch": 17.285714285714285, + "grad_norm": 0.005480973981320858, + "learning_rate": 7.2952880369831635e-06, + "loss": 0.0061, + "step": 242 + }, + { + "epoch": 17.428571428571427, + "grad_norm": 0.2027699053287506, + "learning_rate": 7.140543216013109e-06, + "loss": 0.0035, + "step": 244 + }, + { + "epoch": 17.571428571428573, + "grad_norm": 0.0048587811179459095, + "learning_rate": 6.986540567215043e-06, + "loss": 0.0001, + "step": 246 + }, + { + "epoch": 17.714285714285715, + "grad_norm": 0.005718125496059656, + "learning_rate": 6.833320061985278e-06, + "loss": 0.0001, + "step": 248 + }, + { + "epoch": 17.857142857142858, + "grad_norm": 0.0035847134422510862, + "learning_rate": 6.680921468714718e-06, + "loss": 0.0052, + "step": 250 + }, + { + "epoch": 18.0, + "grad_norm": 0.0035746165085583925, + "learning_rate": 6.529384342466971e-06, + "loss": 0.0001, + "step": 252 + }, + { + "epoch": 18.142857142857142, + "grad_norm": 0.00451216846704483, + "learning_rate": 6.378748014711834e-06, + "loss": 0.0001, + "step": 254 + }, + { + "epoch": 18.285714285714285, + "grad_norm": 0.004890494979918003, + "learning_rate": 6.229051583116796e-06, + "loss": 0.0001, + "step": 256 + }, + { + "epoch": 18.428571428571427, + "grad_norm": 0.004625991452485323, + "learning_rate": 6.080333901399252e-06, + "loss": 0.0058, + "step": 258 + }, + { + "epoch": 18.571428571428573, + "grad_norm": 0.005847033113241196, + "learning_rate": 5.932633569242e-06, + "loss": 0.0001, + "step": 260 + }, + { + "epoch": 18.714285714285715, + "grad_norm": 0.006245823111385107, + "learning_rate": 5.785988922274711e-06, + "loss": 0.0072, + "step": 262 + }, + { + "epoch": 18.857142857142858, + "grad_norm": 0.08823557943105698, + "learning_rate": 5.640438022123898e-06, + "loss": 0.0034, + "step": 264 + }, + { + "epoch": 19.0, + "grad_norm": 0.004038456827402115, + "learning_rate": 5.496018646534032e-06, + "loss": 0.0001, + "step": 266 + }, + { + "epoch": 19.142857142857142, + "grad_norm": 0.005825538653880358, + "learning_rate": 5.352768279562315e-06, + "loss": 0.0056, + "step": 268 + }, + { + "epoch": 19.285714285714285, + "grad_norm": 0.004666970111429691, + "learning_rate": 5.210724101849696e-06, + "loss": 0.0001, + "step": 270 + }, + { + "epoch": 19.428571428571427, + "grad_norm": 0.004332971293479204, + "learning_rate": 5.069922980970626e-06, + "loss": 0.0001, + "step": 272 + }, + { + "epoch": 19.571428571428573, + "grad_norm": 0.09540804475545883, + "learning_rate": 4.930401461864099e-06, + "loss": 0.0085, + "step": 274 + }, + { + "epoch": 19.714285714285715, + "grad_norm": 0.004319526720792055, + "learning_rate": 4.7921957573483756e-06, + "loss": 0.0001, + "step": 276 + }, + { + "epoch": 19.857142857142858, + "grad_norm": 0.00582715030759573, + "learning_rate": 4.655341738721989e-06, + "loss": 0.0001, + "step": 278 + }, + { + "epoch": 20.0, + "grad_norm": 0.005314113572239876, + "learning_rate": 4.519874926453303e-06, + "loss": 0.0001, + "step": 280 + }, + { + "epoch": 20.142857142857142, + "grad_norm": 0.006195093505084515, + "learning_rate": 4.385830480961192e-06, + "loss": 0.0001, + "step": 282 + }, + { + "epoch": 20.285714285714285, + "grad_norm": 0.004151402972638607, + "learning_rate": 4.2532431934891646e-06, + "loss": 0.0001, + "step": 284 + }, + { + "epoch": 20.428571428571427, + "grad_norm": 0.004392064176499844, + "learning_rate": 4.12214747707527e-06, + "loss": 0.0047, + "step": 286 + }, + { + "epoch": 20.571428571428573, + "grad_norm": 0.004756106063723564, + "learning_rate": 3.99257735762021e-06, + "loss": 0.0001, + "step": 288 + }, + { + "epoch": 20.714285714285715, + "grad_norm": 0.004611567594110966, + "learning_rate": 3.864566465055913e-06, + "loss": 0.0022, + "step": 290 + }, + { + "epoch": 20.857142857142858, + "grad_norm": 0.004500643815845251, + "learning_rate": 3.738148024616863e-06, + "loss": 0.0001, + "step": 292 + }, + { + "epoch": 21.0, + "grad_norm": 0.0058865793980658054, + "learning_rate": 3.6133548482165225e-06, + "loss": 0.0081, + "step": 294 + }, + { + "epoch": 21.142857142857142, + "grad_norm": 0.096845842897892, + "learning_rate": 3.4902193259309627e-06, + "loss": 0.0037, + "step": 296 + }, + { + "epoch": 21.285714285714285, + "grad_norm": 0.0038972089532762766, + "learning_rate": 3.3687734175920505e-06, + "loss": 0.0001, + "step": 298 + }, + { + "epoch": 21.428571428571427, + "grad_norm": 0.004685294348746538, + "learning_rate": 3.2490486444922396e-06, + "loss": 0.0001, + "step": 300 + }, + { + "epoch": 21.571428571428573, + "grad_norm": 0.20793084800243378, + "learning_rate": 3.131076081203247e-06, + "loss": 0.0019, + "step": 302 + }, + { + "epoch": 21.714285714285715, + "grad_norm": 0.0035532894544303417, + "learning_rate": 3.0148863475106315e-06, + "loss": 0.0058, + "step": 304 + }, + { + "epoch": 21.857142857142858, + "grad_norm": 0.2300863116979599, + "learning_rate": 2.900509600466418e-06, + "loss": 0.0025, + "step": 306 + }, + { + "epoch": 22.0, + "grad_norm": 0.007288255728781223, + "learning_rate": 2.7879755265618558e-06, + "loss": 0.0001, + "step": 308 + }, + { + "epoch": 22.142857142857142, + "grad_norm": 0.005309649743139744, + "learning_rate": 2.6773133340222677e-06, + "loss": 0.0016, + "step": 310 + }, + { + "epoch": 22.285714285714285, + "grad_norm": 0.003941751550883055, + "learning_rate": 2.5685517452260566e-06, + "loss": 0.0001, + "step": 312 + }, + { + "epoch": 22.428571428571427, + "grad_norm": 0.004016744904220104, + "learning_rate": 2.4617189892498326e-06, + "loss": 0.0001, + "step": 314 + }, + { + "epoch": 22.571428571428573, + "grad_norm": 0.13147950172424316, + "learning_rate": 2.3568427945415163e-06, + "loss": 0.0064, + "step": 316 + }, + { + "epoch": 22.714285714285715, + "grad_norm": 0.003918132279068232, + "learning_rate": 2.2539503817234553e-06, + "loss": 0.0001, + "step": 318 + }, + { + "epoch": 22.857142857142858, + "grad_norm": 0.004725574050098658, + "learning_rate": 2.153068456527283e-06, + "loss": 0.0001, + "step": 320 + }, + { + "epoch": 23.0, + "grad_norm": 0.3711271584033966, + "learning_rate": 2.0542232028624585e-06, + "loss": 0.0175, + "step": 322 + }, + { + "epoch": 23.142857142857142, + "grad_norm": 0.18150761723518372, + "learning_rate": 1.9574402760202315e-06, + "loss": 0.0023, + "step": 324 + }, + { + "epoch": 23.285714285714285, + "grad_norm": 0.13696324825286865, + "learning_rate": 1.8627447960148036e-06, + "loss": 0.0045, + "step": 326 + }, + { + "epoch": 23.428571428571427, + "grad_norm": 0.004304251167923212, + "learning_rate": 1.7701613410634367e-06, + "loss": 0.0001, + "step": 328 + }, + { + "epoch": 23.571428571428573, + "grad_norm": 0.005392234306782484, + "learning_rate": 1.6797139412071583e-06, + "loss": 0.0001, + "step": 330 + }, + { + "epoch": 23.714285714285715, + "grad_norm": 0.004501474089920521, + "learning_rate": 1.5914260720737796e-06, + "loss": 0.0001, + "step": 332 + }, + { + "epoch": 23.857142857142858, + "grad_norm": 0.0033914605155587196, + "learning_rate": 1.5053206487847916e-06, + "loss": 0.0047, + "step": 334 + }, + { + "epoch": 24.0, + "grad_norm": 0.005722349975258112, + "learning_rate": 1.4214200200077343e-06, + "loss": 0.0001, + "step": 336 + }, + { + "epoch": 24.142857142857142, + "grad_norm": 0.0028757653199136257, + "learning_rate": 1.339745962155613e-06, + "loss": 0.0001, + "step": 338 + }, + { + "epoch": 24.285714285714285, + "grad_norm": 0.004367240238934755, + "learning_rate": 1.2603196737348211e-06, + "loss": 0.0012, + "step": 340 + }, + { + "epoch": 24.428571428571427, + "grad_norm": 0.004103364888578653, + "learning_rate": 1.1831617698430609e-06, + "loss": 0.0001, + "step": 342 + }, + { + "epoch": 24.571428571428573, + "grad_norm": 0.12380176037549973, + "learning_rate": 1.1082922768187098e-06, + "loss": 0.0053, + "step": 344 + }, + { + "epoch": 24.714285714285715, + "grad_norm": 0.11978839337825775, + "learning_rate": 1.0357306270429623e-06, + "loss": 0.0045, + "step": 346 + }, + { + "epoch": 24.857142857142858, + "grad_norm": 0.15920782089233398, + "learning_rate": 9.65495653896179e-07, + "loss": 0.0008, + "step": 348 + }, + { + "epoch": 25.0, + "grad_norm": 0.005539704114198685, + "learning_rate": 8.976055868696543e-07, + "loss": 0.0001, + "step": 350 + }, + { + "epoch": 25.142857142857142, + "grad_norm": 0.004604020155966282, + "learning_rate": 8.320780468341761e-07, + "loss": 0.0001, + "step": 352 + }, + { + "epoch": 25.285714285714285, + "grad_norm": 0.19128715991973877, + "learning_rate": 7.689300414665124e-07, + "loss": 0.0012, + "step": 354 + }, + { + "epoch": 25.428571428571427, + "grad_norm": 0.0033012081403285265, + "learning_rate": 7.08177960835068e-07, + "loss": 0.0067, + "step": 356 + }, + { + "epoch": 25.571428571428573, + "grad_norm": 0.09938196837902069, + "learning_rate": 6.498375731458529e-07, + "loss": 0.0005, + "step": 358 + }, + { + "epoch": 25.714285714285715, + "grad_norm": 0.0049908701330423355, + "learning_rate": 5.939240206498287e-07, + "loss": 0.0001, + "step": 360 + }, + { + "epoch": 25.857142857142858, + "grad_norm": 0.0035182549618184566, + "learning_rate": 5.404518157127481e-07, + "loss": 0.0046, + "step": 362 + }, + { + "epoch": 26.0, + "grad_norm": 0.0068074483424425125, + "learning_rate": 4.894348370484648e-07, + "loss": 0.0001, + "step": 364 + }, + { + "epoch": 26.142857142857142, + "grad_norm": 0.004269490484148264, + "learning_rate": 4.408863261167096e-07, + "loss": 0.0001, + "step": 366 + }, + { + "epoch": 26.285714285714285, + "grad_norm": 0.12823165953159332, + "learning_rate": 3.9481888368627764e-07, + "loss": 0.0042, + "step": 368 + }, + { + "epoch": 26.428571428571427, + "grad_norm": 0.0035812160931527615, + "learning_rate": 3.5124446656448654e-07, + "loss": 0.0001, + "step": 370 + }, + { + "epoch": 26.571428571428573, + "grad_norm": 0.00431048171594739, + "learning_rate": 3.101743844937943e-07, + "loss": 0.0059, + "step": 372 + }, + { + "epoch": 26.714285714285715, + "grad_norm": 0.004997176583856344, + "learning_rate": 2.716192972163556e-07, + "loss": 0.0001, + "step": 374 + }, + { + "epoch": 26.857142857142858, + "grad_norm": 0.004221776034682989, + "learning_rate": 2.355892117072789e-07, + "loss": 0.0001, + "step": 376 + }, + { + "epoch": 27.0, + "grad_norm": 0.007233808748424053, + "learning_rate": 2.0209347957732328e-07, + "loss": 0.0008, + "step": 378 + }, + { + "epoch": 27.142857142857142, + "grad_norm": 0.0030983760952949524, + "learning_rate": 1.711407946456789e-07, + "loss": 0.0001, + "step": 380 + }, + { + "epoch": 27.285714285714285, + "grad_norm": 0.13253678381443024, + "learning_rate": 1.4273919068349184e-07, + "loss": 0.0014, + "step": 382 + }, + { + "epoch": 27.428571428571427, + "grad_norm": 0.003873329609632492, + "learning_rate": 1.1689603932869664e-07, + "loss": 0.0001, + "step": 384 + }, + { + "epoch": 27.571428571428573, + "grad_norm": 0.005466313101351261, + "learning_rate": 9.36180481727067e-08, + "loss": 0.0046, + "step": 386 + }, + { + "epoch": 27.714285714285715, + "grad_norm": 0.004763293080031872, + "learning_rate": 7.291125901946027e-08, + "loss": 0.0001, + "step": 388 + }, + { + "epoch": 27.857142857142858, + "grad_norm": 0.11048487573862076, + "learning_rate": 5.4781046317267103e-08, + "loss": 0.0048, + "step": 390 + }, + { + "epoch": 28.0, + "grad_norm": 0.007729329634457827, + "learning_rate": 3.923211576387087e-08, + "loss": 0.0001, + "step": 392 + }, + { + "epoch": 28.142857142857142, + "grad_norm": 0.003292845096439123, + "learning_rate": 2.6268503085089547e-08, + "loss": 0.0001, + "step": 394 + }, + { + "epoch": 28.285714285714285, + "grad_norm": 0.00781972985714674, + "learning_rate": 1.5893572987333293e-08, + "loss": 0.0001, + "step": 396 + }, + { + "epoch": 28.428571428571427, + "grad_norm": 0.14954733848571777, + "learning_rate": 8.110018284304132e-09, + "loss": 0.0049, + "step": 398 + }, + { + "epoch": 28.571428571428573, + "grad_norm": 0.005883893929421902, + "learning_rate": 2.9198591980705847e-09, + "loss": 0.0007, + "step": 400 + }, + { + "epoch": 28.714285714285715, + "grad_norm": 0.13555946946144104, + "learning_rate": 3.244428347204398e-10, + "loss": 0.0008, + "step": 402 + } + ], + "logging_steps": 2, + "max_steps": 402, + "num_input_tokens_seen": 0, + "num_train_epochs": 29, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.0685712456679424e+16, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-402/training_args.bin b/checkpoint-402/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5e40431601fe0fda63821c355ca2518b79c42df --- /dev/null +++ b/checkpoint-402/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25a0ccf5317ebd8f7cfcaefcfdfd3860c0c2887188910c19a4b9dde7e5910b1 +size 6520 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4dcbec3802b4ff59bc65d39f71bf790538040ae2 --- /dev/null +++ b/config.json @@ -0,0 +1,48 @@ +{ + "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": 3584, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 16, + "num_hidden_layers": 42, + "num_key_value_heads": 8, + "pad_token_id": 0, + "quantization_config": { + "_load_in_4bit": false, + "_load_in_8bit": true, + "bnb_4bit_compute_dtype": "float32", + "bnb_4bit_quant_storage": "uint8", + "bnb_4bit_quant_type": "fp4", + "bnb_4bit_use_double_quant": false, + "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": false, + "load_in_8bit": true, + "quant_method": "bitsandbytes" + }, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.3", + "use_cache": false, + "vocab_size": 256000 +} 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..3ade6be57196932063a48c1329fbf9c2e7e154d1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2013 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

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

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

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

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

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "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 +}