diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..14f613bac8bc25147f88a1349aa3f5a52defd003 --- /dev/null +++ b/README.md @@ -0,0 +1,143 @@ +--- +license: apache-2.0 +library_name: peft +tags: +- generated_from_trainer +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T +model-index: +- name: outputs/qlora-out + results: [] +--- + + + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) +
See axolotl config + +axolotl version: `0.4.1` +```yaml +adapter: qlora +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T +bf16: false +dataset_prepared_path: null +datasets: +- ds_tipe: json + path: instruct_dataset.jsonl + type: alpaca +debug: null +deepspeed: null +early_stopping_patience: null +eval_sample_packing: false +evals_per_epoch: 4 +flash_attention: false +fp16: null +fsdp: null +fsdp_config: null +gradient_accumulation_steps: 4 +gradient_checkpointing: true +group_by_length: false +learning_rate: 0.0002 +load_in_4bit: true +load_in_8bit: false +local_rank: null +logging_steps: 1 +lora_alpha: 16 +lora_dropout: 0.05 +lora_fan_in_fan_out: null +lora_model_dir: null +lora_r: 32 +lora_target_linear: true +lora_target_modules: null +lr_scheduler: cosine +micro_batch_size: 8 +model_type: LlamaForCausalLM +num_epochs: 4 +optimizer: paged_adamw_32bit +output_dir: ./outputs/qlora-out +pad_to_sequence_len: false +resume_from_checkpoint: null +sample_packing: false +saves_per_epoch: 1 +sequence_len: 4096 +special_tokens: null +strict: false +tf32: false +tokenizer_type: LlamaTokenizer +train_on_inputs: false +val_set_size: 0.05 +wandb_entity: null +wandb_log_model: null +wandb_name: null +wandb_project: null +wandb_watch: null +warmup_steps: 10 +weight_decay: 0.0 +xformers_attention: null + +``` + +

+ +# outputs/qlora-out + +This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset. +It achieves the following results on the evaluation set: +- Loss: 2.0250 + +## 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: 0.0002 +- train_batch_size: 8 +- eval_batch_size: 8 +- seed: 42 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 32 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 10 +- num_epochs: 4 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 2.3126 | 0.0336 | 1 | 2.3784 | +| 2.2933 | 0.2689 | 8 | 2.1781 | +| 2.0371 | 0.5378 | 16 | 2.0500 | +| 1.8653 | 0.8067 | 24 | 2.0289 | +| 2.0311 | 1.0756 | 32 | 2.0189 | +| 1.9591 | 1.3445 | 40 | 2.0106 | +| 1.994 | 1.6134 | 48 | 2.0106 | +| 1.9204 | 1.8824 | 56 | 2.0145 | +| 1.8178 | 2.1513 | 64 | 2.0155 | +| 1.8428 | 2.4202 | 72 | 2.0222 | +| 1.947 | 2.6891 | 80 | 2.0267 | +| 1.9806 | 2.9580 | 88 | 2.0258 | +| 1.7724 | 3.2269 | 96 | 2.0250 | +| 1.9376 | 3.4958 | 104 | 2.0250 | +| 1.8617 | 3.7647 | 112 | 2.0250 | + + +### Framework versions + +- PEFT 0.11.1 +- Transformers 4.41.1 +- Pytorch 2.1.2+cu121 +- Datasets 2.19.1 +- Tokenizers 0.19.1 \ No newline at end of file diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0a39bbdad47a61fa660b177ceb742e4446650f75 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "bias": "none", + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "q_proj", + "up_proj", + "v_proj", + "gate_proj", + "o_proj", + "k_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.bin b/adapter_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9add9d9b8d95eb54e3ab5488a2a06eeeab76f68 --- /dev/null +++ b/adapter_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7531b726f95412809587fcc499e50faffbe5e727b9daab9706232df4d2ceb1f +size 50573978 diff --git a/checkpoint-116/README.md b/checkpoint-116/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e1ccd431539a8f1507d8755a9c3ba5e5b2897978 --- /dev/null +++ b/checkpoint-116/README.md @@ -0,0 +1,202 @@ +--- +library_name: peft +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T +--- + +# 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 0.11.1 \ No newline at end of file diff --git a/checkpoint-116/adapter_config.json b/checkpoint-116/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0a39bbdad47a61fa660b177ceb742e4446650f75 --- /dev/null +++ b/checkpoint-116/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "bias": "none", + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "q_proj", + "up_proj", + "v_proj", + "gate_proj", + "o_proj", + "k_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-116/adapter_model.safetensors b/checkpoint-116/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e5b884992420ff005c68a3cc52b220ee2bf6ac4 --- /dev/null +++ b/checkpoint-116/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ec27ebcf5f24c2f7d9e44530925d231e0fe0a56af2b2ce9726a28e63052539 +size 50503848 diff --git a/checkpoint-116/optimizer.pt b/checkpoint-116/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..75e459cf139d9bf74f579c88eeff81123fd7b631 --- /dev/null +++ b/checkpoint-116/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c8dca975af015461e73b22c3dbc829d937945c2b54044b96c91e3d6f3c8aee +size 202035450 diff --git a/checkpoint-116/rng_state.pth b/checkpoint-116/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5cd7dbef6c61bfee8ae12fc0882e8a54c9e2d43 --- /dev/null +++ b/checkpoint-116/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e58c67c4bd21e73069046a43f61325523620adde1da147eb2afdc06e0896dc +size 14244 diff --git a/checkpoint-116/scheduler.pt b/checkpoint-116/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f09aa9eb766b3356ec7e327795e67e35471f1984 --- /dev/null +++ b/checkpoint-116/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68424c30349bda77a4657d1902f52c5a348248ab657a58e4aee2ebfc370c25ab +size 1064 diff --git a/checkpoint-116/special_tokens_map.json b/checkpoint-116/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-116/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-116/tokenizer.model b/checkpoint-116/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/checkpoint-116/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/checkpoint-116/tokenizer_config.json b/checkpoint-116/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86 --- /dev/null +++ b/checkpoint-116/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +} diff --git a/checkpoint-116/trainer_state.json b/checkpoint-116/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..eea2702f7adcc2092c6b66cfecfc0c30127a0612 --- /dev/null +++ b/checkpoint-116/trainer_state.json @@ -0,0 +1,965 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.899159663865546, + "eval_steps": 8, + "global_step": 116, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03361344537815126, + "grad_norm": 0.423828125, + "learning_rate": 2e-05, + "loss": 2.3126, + "step": 1 + }, + { + "epoch": 0.03361344537815126, + "eval_loss": 2.3783609867095947, + "eval_runtime": 10.4273, + "eval_samples_per_second": 4.795, + "eval_steps_per_second": 0.671, + "step": 1 + }, + { + "epoch": 0.06722689075630252, + "grad_norm": 0.4375, + "learning_rate": 4e-05, + "loss": 2.3746, + "step": 2 + }, + { + "epoch": 0.10084033613445378, + "grad_norm": 0.40625, + "learning_rate": 6e-05, + "loss": 2.5894, + "step": 3 + }, + { + "epoch": 0.13445378151260504, + "grad_norm": 0.451171875, + "learning_rate": 8e-05, + "loss": 2.3395, + "step": 4 + }, + { + "epoch": 0.16806722689075632, + "grad_norm": 0.40625, + "learning_rate": 0.0001, + "loss": 2.4187, + "step": 5 + }, + { + "epoch": 0.20168067226890757, + "grad_norm": 0.423828125, + "learning_rate": 0.00012, + "loss": 2.4575, + "step": 6 + }, + { + "epoch": 0.23529411764705882, + "grad_norm": 0.34375, + "learning_rate": 0.00014, + "loss": 2.1943, + "step": 7 + }, + { + "epoch": 0.2689075630252101, + "grad_norm": 0.33203125, + "learning_rate": 0.00016, + "loss": 2.2933, + "step": 8 + }, + { + "epoch": 0.2689075630252101, + "eval_loss": 2.1781439781188965, + "eval_runtime": 10.9815, + "eval_samples_per_second": 4.553, + "eval_steps_per_second": 0.637, + "step": 8 + }, + { + "epoch": 0.3025210084033613, + "grad_norm": 0.333984375, + "learning_rate": 0.00018, + "loss": 2.1869, + "step": 9 + }, + { + "epoch": 0.33613445378151263, + "grad_norm": 0.279296875, + "learning_rate": 0.0002, + "loss": 2.297, + "step": 10 + }, + { + "epoch": 0.3697478991596639, + "grad_norm": 0.30078125, + "learning_rate": 0.00019995608365087946, + "loss": 2.1138, + "step": 11 + }, + { + "epoch": 0.40336134453781514, + "grad_norm": 0.259765625, + "learning_rate": 0.00019982437317643217, + "loss": 2.0531, + "step": 12 + }, + { + "epoch": 0.4369747899159664, + "grad_norm": 0.3125, + "learning_rate": 0.0001996049842615217, + "loss": 2.0082, + "step": 13 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 0.33984375, + "learning_rate": 0.00019929810960135172, + "loss": 2.044, + "step": 14 + }, + { + "epoch": 0.5042016806722689, + "grad_norm": 0.310546875, + "learning_rate": 0.0001989040187322164, + "loss": 2.0348, + "step": 15 + }, + { + "epoch": 0.5378151260504201, + "grad_norm": 0.287109375, + "learning_rate": 0.00019842305779475968, + "loss": 2.0371, + "step": 16 + }, + { + "epoch": 0.5378151260504201, + "eval_loss": 2.0500473976135254, + "eval_runtime": 10.9871, + "eval_samples_per_second": 4.551, + "eval_steps_per_second": 0.637, + "step": 16 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.2734375, + "learning_rate": 0.0001978556492299504, + "loss": 2.0658, + "step": 17 + }, + { + "epoch": 0.6050420168067226, + "grad_norm": 0.302734375, + "learning_rate": 0.0001972022914080411, + "loss": 2.126, + "step": 18 + }, + { + "epoch": 0.6386554621848739, + "grad_norm": 0.2734375, + "learning_rate": 0.00019646355819083589, + "loss": 2.0384, + "step": 19 + }, + { + "epoch": 0.6722689075630253, + "grad_norm": 0.251953125, + "learning_rate": 0.00019564009842765225, + "loss": 2.0598, + "step": 20 + }, + { + "epoch": 0.7058823529411765, + "grad_norm": 0.27734375, + "learning_rate": 0.00019473263538541914, + "loss": 2.0817, + "step": 21 + }, + { + "epoch": 0.7394957983193278, + "grad_norm": 0.267578125, + "learning_rate": 0.0001937419661134121, + "loss": 2.0959, + "step": 22 + }, + { + "epoch": 0.773109243697479, + "grad_norm": 0.28125, + "learning_rate": 0.00019266896074318334, + "loss": 2.1694, + "step": 23 + }, + { + "epoch": 0.8067226890756303, + "grad_norm": 0.240234375, + "learning_rate": 0.00019151456172430183, + "loss": 1.8653, + "step": 24 + }, + { + "epoch": 0.8067226890756303, + "eval_loss": 2.028913736343384, + "eval_runtime": 11.0811, + "eval_samples_per_second": 4.512, + "eval_steps_per_second": 0.632, + "step": 24 + }, + { + "epoch": 0.8403361344537815, + "grad_norm": 0.2578125, + "learning_rate": 0.00019027978299657436, + "loss": 1.979, + "step": 25 + }, + { + "epoch": 0.8739495798319328, + "grad_norm": 0.2294921875, + "learning_rate": 0.00018896570909947475, + "loss": 2.0706, + "step": 26 + }, + { + "epoch": 0.907563025210084, + "grad_norm": 0.26171875, + "learning_rate": 0.0001875734942195637, + "loss": 2.1814, + "step": 27 + }, + { + "epoch": 0.9411764705882353, + "grad_norm": 0.255859375, + "learning_rate": 0.00018610436117673555, + "loss": 1.9951, + "step": 28 + }, + { + "epoch": 0.9747899159663865, + "grad_norm": 0.267578125, + "learning_rate": 0.0001845596003501826, + "loss": 2.1463, + "step": 29 + }, + { + "epoch": 1.0084033613445378, + "grad_norm": 0.27734375, + "learning_rate": 0.0001829405685450202, + "loss": 2.2055, + "step": 30 + }, + { + "epoch": 1.0420168067226891, + "grad_norm": 0.208984375, + "learning_rate": 0.00018124868780056814, + "loss": 2.0328, + "step": 31 + }, + { + "epoch": 1.0756302521008403, + "grad_norm": 0.2470703125, + "learning_rate": 0.00017948544414133534, + "loss": 2.0311, + "step": 32 + }, + { + "epoch": 1.0756302521008403, + "eval_loss": 2.0189168453216553, + "eval_runtime": 11.1124, + "eval_samples_per_second": 4.499, + "eval_steps_per_second": 0.63, + "step": 32 + }, + { + "epoch": 1.1092436974789917, + "grad_norm": 0.2080078125, + "learning_rate": 0.00017765238627180424, + "loss": 2.0399, + "step": 33 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 0.2265625, + "learning_rate": 0.00017575112421616202, + "loss": 1.9265, + "step": 34 + }, + { + "epoch": 1.1764705882352942, + "grad_norm": 0.205078125, + "learning_rate": 0.00017378332790417273, + "loss": 2.0815, + "step": 35 + }, + { + "epoch": 1.2100840336134453, + "grad_norm": 0.220703125, + "learning_rate": 0.00017175072570443312, + "loss": 2.0716, + "step": 36 + }, + { + "epoch": 1.2436974789915967, + "grad_norm": 0.23828125, + "learning_rate": 0.00016965510290629972, + "loss": 2.1353, + "step": 37 + }, + { + "epoch": 1.2773109243697478, + "grad_norm": 0.234375, + "learning_rate": 0.00016749830015182107, + "loss": 2.037, + "step": 38 + }, + { + "epoch": 1.3109243697478992, + "grad_norm": 0.2314453125, + "learning_rate": 0.00016528221181905217, + "loss": 2.1324, + "step": 39 + }, + { + "epoch": 1.3445378151260505, + "grad_norm": 0.236328125, + "learning_rate": 0.00016300878435817113, + "loss": 1.9591, + "step": 40 + }, + { + "epoch": 1.3445378151260505, + "eval_loss": 2.0105881690979004, + "eval_runtime": 11.061, + "eval_samples_per_second": 4.52, + "eval_steps_per_second": 0.633, + "step": 40 + }, + { + "epoch": 1.3781512605042017, + "grad_norm": 0.2294921875, + "learning_rate": 0.00016068001458185936, + "loss": 2.0045, + "step": 41 + }, + { + "epoch": 1.4117647058823528, + "grad_norm": 0.25390625, + "learning_rate": 0.0001582979479114472, + "loss": 1.8726, + "step": 42 + }, + { + "epoch": 1.4453781512605042, + "grad_norm": 0.24609375, + "learning_rate": 0.00015586467658036524, + "loss": 2.1408, + "step": 43 + }, + { + "epoch": 1.4789915966386555, + "grad_norm": 0.2392578125, + "learning_rate": 0.0001533823377964791, + "loss": 1.8444, + "step": 44 + }, + { + "epoch": 1.5126050420168067, + "grad_norm": 0.24609375, + "learning_rate": 0.00015085311186492206, + "loss": 1.8595, + "step": 45 + }, + { + "epoch": 1.5462184873949578, + "grad_norm": 0.24609375, + "learning_rate": 0.00014827922027307451, + "loss": 1.9338, + "step": 46 + }, + { + "epoch": 1.5798319327731094, + "grad_norm": 0.255859375, + "learning_rate": 0.0001456629237393713, + "loss": 1.9562, + "step": 47 + }, + { + "epoch": 1.6134453781512605, + "grad_norm": 0.267578125, + "learning_rate": 0.00014300652022765207, + "loss": 1.994, + "step": 48 + }, + { + "epoch": 1.6134453781512605, + "eval_loss": 2.010645866394043, + "eval_runtime": 10.957, + "eval_samples_per_second": 4.563, + "eval_steps_per_second": 0.639, + "step": 48 + }, + { + "epoch": 1.6470588235294117, + "grad_norm": 0.2890625, + "learning_rate": 0.00014031234292879725, + "loss": 1.9666, + "step": 49 + }, + { + "epoch": 1.680672268907563, + "grad_norm": 0.26953125, + "learning_rate": 0.00013758275821142382, + "loss": 1.8065, + "step": 50 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 0.30859375, + "learning_rate": 0.0001348201635434399, + "loss": 2.0882, + "step": 51 + }, + { + "epoch": 1.7478991596638656, + "grad_norm": 0.2734375, + "learning_rate": 0.00013202698538628376, + "loss": 1.9619, + "step": 52 + }, + { + "epoch": 1.7815126050420167, + "grad_norm": 0.271484375, + "learning_rate": 0.00012920567706369758, + "loss": 2.0829, + "step": 53 + }, + { + "epoch": 1.815126050420168, + "grad_norm": 0.30859375, + "learning_rate": 0.00012635871660690676, + "loss": 2.0254, + "step": 54 + }, + { + "epoch": 1.8487394957983194, + "grad_norm": 0.2734375, + "learning_rate": 0.00012348860457809838, + "loss": 2.0488, + "step": 55 + }, + { + "epoch": 1.8823529411764706, + "grad_norm": 0.294921875, + "learning_rate": 0.00012059786187410984, + "loss": 1.9204, + "step": 56 + }, + { + "epoch": 1.8823529411764706, + "eval_loss": 2.0145041942596436, + "eval_runtime": 10.9679, + "eval_samples_per_second": 4.559, + "eval_steps_per_second": 0.638, + "step": 56 + }, + { + "epoch": 1.9159663865546217, + "grad_norm": 0.279296875, + "learning_rate": 0.0001176890275122573, + "loss": 1.7729, + "step": 57 + }, + { + "epoch": 1.949579831932773, + "grad_norm": 0.294921875, + "learning_rate": 0.00011476465640024814, + "loss": 2.0228, + "step": 58 + }, + { + "epoch": 1.9831932773109244, + "grad_norm": 0.2734375, + "learning_rate": 0.00011182731709213659, + "loss": 1.869, + "step": 59 + }, + { + "epoch": 2.0168067226890756, + "grad_norm": 0.353515625, + "learning_rate": 0.00010887958953229349, + "loss": 1.8303, + "step": 60 + }, + { + "epoch": 2.0504201680672267, + "grad_norm": 0.294921875, + "learning_rate": 0.00010592406278937144, + "loss": 2.0863, + "step": 61 + }, + { + "epoch": 2.0840336134453783, + "grad_norm": 0.275390625, + "learning_rate": 0.00010296333278225599, + "loss": 1.9723, + "step": 62 + }, + { + "epoch": 2.1176470588235294, + "grad_norm": 0.3203125, + "learning_rate": 0.0001, + "loss": 1.9275, + "step": 63 + }, + { + "epoch": 2.1512605042016806, + "grad_norm": 0.28515625, + "learning_rate": 9.703666721774402e-05, + "loss": 1.8178, + "step": 64 + }, + { + "epoch": 2.1512605042016806, + "eval_loss": 2.015535831451416, + "eval_runtime": 11.0392, + "eval_samples_per_second": 4.529, + "eval_steps_per_second": 0.634, + "step": 64 + }, + { + "epoch": 2.184873949579832, + "grad_norm": 0.30078125, + "learning_rate": 9.407593721062859e-05, + "loss": 1.9097, + "step": 65 + }, + { + "epoch": 2.2184873949579833, + "grad_norm": 0.298828125, + "learning_rate": 9.112041046770653e-05, + "loss": 1.8793, + "step": 66 + }, + { + "epoch": 2.2521008403361344, + "grad_norm": 0.3359375, + "learning_rate": 8.817268290786343e-05, + "loss": 1.861, + "step": 67 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 0.31640625, + "learning_rate": 8.523534359975189e-05, + "loss": 1.8363, + "step": 68 + }, + { + "epoch": 2.3193277310924367, + "grad_norm": 0.31640625, + "learning_rate": 8.231097248774274e-05, + "loss": 1.8089, + "step": 69 + }, + { + "epoch": 2.3529411764705883, + "grad_norm": 0.3046875, + "learning_rate": 7.940213812589018e-05, + "loss": 1.814, + "step": 70 + }, + { + "epoch": 2.3865546218487395, + "grad_norm": 0.31640625, + "learning_rate": 7.651139542190164e-05, + "loss": 1.8281, + "step": 71 + }, + { + "epoch": 2.4201680672268906, + "grad_norm": 0.33203125, + "learning_rate": 7.364128339309326e-05, + "loss": 1.8428, + "step": 72 + }, + { + "epoch": 2.4201680672268906, + "eval_loss": 2.022204637527466, + "eval_runtime": 11.0405, + "eval_samples_per_second": 4.529, + "eval_steps_per_second": 0.634, + "step": 72 + }, + { + "epoch": 2.453781512605042, + "grad_norm": 0.357421875, + "learning_rate": 7.079432293630244e-05, + "loss": 1.904, + "step": 73 + }, + { + "epoch": 2.4873949579831933, + "grad_norm": 0.349609375, + "learning_rate": 6.797301461371625e-05, + "loss": 1.7909, + "step": 74 + }, + { + "epoch": 2.5210084033613445, + "grad_norm": 0.375, + "learning_rate": 6.517983645656014e-05, + "loss": 1.7367, + "step": 75 + }, + { + "epoch": 2.5546218487394956, + "grad_norm": 0.349609375, + "learning_rate": 6.24172417885762e-05, + "loss": 1.8942, + "step": 76 + }, + { + "epoch": 2.588235294117647, + "grad_norm": 0.34765625, + "learning_rate": 5.96876570712028e-05, + "loss": 1.8393, + "step": 77 + }, + { + "epoch": 2.6218487394957983, + "grad_norm": 0.35546875, + "learning_rate": 5.699347977234799e-05, + "loss": 1.8254, + "step": 78 + }, + { + "epoch": 2.6554621848739495, + "grad_norm": 0.349609375, + "learning_rate": 5.43370762606287e-05, + "loss": 1.9937, + "step": 79 + }, + { + "epoch": 2.689075630252101, + "grad_norm": 0.373046875, + "learning_rate": 5.172077972692553e-05, + "loss": 1.947, + "step": 80 + }, + { + "epoch": 2.689075630252101, + "eval_loss": 2.026715040206909, + "eval_runtime": 10.9879, + "eval_samples_per_second": 4.55, + "eval_steps_per_second": 0.637, + "step": 80 + }, + { + "epoch": 2.722689075630252, + "grad_norm": 0.326171875, + "learning_rate": 4.914688813507797e-05, + "loss": 1.9046, + "step": 81 + }, + { + "epoch": 2.7563025210084033, + "grad_norm": 0.35546875, + "learning_rate": 4.661766220352097e-05, + "loss": 1.9969, + "step": 82 + }, + { + "epoch": 2.7899159663865545, + "grad_norm": 0.361328125, + "learning_rate": 4.4135323419634766e-05, + "loss": 1.7827, + "step": 83 + }, + { + "epoch": 2.8235294117647056, + "grad_norm": 0.3515625, + "learning_rate": 4.170205208855281e-05, + "loss": 1.8887, + "step": 84 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 0.373046875, + "learning_rate": 3.931998541814069e-05, + "loss": 1.8327, + "step": 85 + }, + { + "epoch": 2.8907563025210083, + "grad_norm": 0.37890625, + "learning_rate": 3.69912156418289e-05, + "loss": 1.9086, + "step": 86 + }, + { + "epoch": 2.92436974789916, + "grad_norm": 0.390625, + "learning_rate": 3.471778818094785e-05, + "loss": 1.9553, + "step": 87 + }, + { + "epoch": 2.957983193277311, + "grad_norm": 0.376953125, + "learning_rate": 3.250169984817897e-05, + "loss": 1.9806, + "step": 88 + }, + { + "epoch": 2.957983193277311, + "eval_loss": 2.025836944580078, + "eval_runtime": 10.9648, + "eval_samples_per_second": 4.56, + "eval_steps_per_second": 0.638, + "step": 88 + }, + { + "epoch": 2.991596638655462, + "grad_norm": 0.36328125, + "learning_rate": 3.034489709370033e-05, + "loss": 1.8534, + "step": 89 + }, + { + "epoch": 3.0252100840336134, + "grad_norm": 0.396484375, + "learning_rate": 2.8249274295566864e-05, + "loss": 1.9497, + "step": 90 + }, + { + "epoch": 3.0588235294117645, + "grad_norm": 0.36328125, + "learning_rate": 2.6216672095827266e-05, + "loss": 1.845, + "step": 91 + }, + { + "epoch": 3.092436974789916, + "grad_norm": 0.380859375, + "learning_rate": 2.4248875783837987e-05, + "loss": 1.9815, + "step": 92 + }, + { + "epoch": 3.1260504201680672, + "grad_norm": 0.3515625, + "learning_rate": 2.234761372819577e-05, + "loss": 1.9955, + "step": 93 + }, + { + "epoch": 3.1596638655462184, + "grad_norm": 0.36328125, + "learning_rate": 2.0514555858664663e-05, + "loss": 1.7843, + "step": 94 + }, + { + "epoch": 3.19327731092437, + "grad_norm": 0.341796875, + "learning_rate": 1.875131219943187e-05, + "loss": 1.7952, + "step": 95 + }, + { + "epoch": 3.226890756302521, + "grad_norm": 0.345703125, + "learning_rate": 1.7059431454979824e-05, + "loss": 1.7724, + "step": 96 + }, + { + "epoch": 3.226890756302521, + "eval_loss": 2.0249805450439453, + "eval_runtime": 10.9854, + "eval_samples_per_second": 4.551, + "eval_steps_per_second": 0.637, + "step": 96 + }, + { + "epoch": 3.2605042016806722, + "grad_norm": 0.37890625, + "learning_rate": 1.5440399649817385e-05, + "loss": 1.8315, + "step": 97 + }, + { + "epoch": 3.2941176470588234, + "grad_norm": 0.369140625, + "learning_rate": 1.3895638823264446e-05, + "loss": 1.8848, + "step": 98 + }, + { + "epoch": 3.327731092436975, + "grad_norm": 0.349609375, + "learning_rate": 1.2426505780436326e-05, + "loss": 1.9429, + "step": 99 + }, + { + "epoch": 3.361344537815126, + "grad_norm": 0.349609375, + "learning_rate": 1.103429090052528e-05, + "loss": 1.9384, + "step": 100 + }, + { + "epoch": 3.3949579831932772, + "grad_norm": 0.349609375, + "learning_rate": 9.720217003425647e-06, + "loss": 1.7755, + "step": 101 + }, + { + "epoch": 3.4285714285714284, + "grad_norm": 0.36328125, + "learning_rate": 8.485438275698154e-06, + "loss": 1.7717, + "step": 102 + }, + { + "epoch": 3.46218487394958, + "grad_norm": 0.359375, + "learning_rate": 7.331039256816663e-06, + "loss": 1.826, + "step": 103 + }, + { + "epoch": 3.495798319327731, + "grad_norm": 0.357421875, + "learning_rate": 6.258033886587911e-06, + "loss": 1.9376, + "step": 104 + }, + { + "epoch": 3.495798319327731, + "eval_loss": 2.0250403881073, + "eval_runtime": 11.1154, + "eval_samples_per_second": 4.498, + "eval_steps_per_second": 0.63, + "step": 104 + }, + { + "epoch": 3.5294117647058822, + "grad_norm": 0.35546875, + "learning_rate": 5.267364614580861e-06, + "loss": 1.8187, + "step": 105 + }, + { + "epoch": 3.5630252100840334, + "grad_norm": 0.34765625, + "learning_rate": 4.359901572347758e-06, + "loss": 1.8652, + "step": 106 + }, + { + "epoch": 3.596638655462185, + "grad_norm": 0.365234375, + "learning_rate": 3.5364418091641373e-06, + "loss": 1.9462, + "step": 107 + }, + { + "epoch": 3.630252100840336, + "grad_norm": 0.361328125, + "learning_rate": 2.7977085919589254e-06, + "loss": 1.7895, + "step": 108 + }, + { + "epoch": 3.6638655462184873, + "grad_norm": 0.376953125, + "learning_rate": 2.144350770049597e-06, + "loss": 1.8026, + "step": 109 + }, + { + "epoch": 3.697478991596639, + "grad_norm": 0.3671875, + "learning_rate": 1.576942205240317e-06, + "loss": 1.6771, + "step": 110 + }, + { + "epoch": 3.73109243697479, + "grad_norm": 0.4140625, + "learning_rate": 1.0959812677835968e-06, + "loss": 1.6333, + "step": 111 + }, + { + "epoch": 3.764705882352941, + "grad_norm": 0.390625, + "learning_rate": 7.018903986483083e-07, + "loss": 1.8617, + "step": 112 + }, + { + "epoch": 3.764705882352941, + "eval_loss": 2.0250463485717773, + "eval_runtime": 10.9711, + "eval_samples_per_second": 4.557, + "eval_steps_per_second": 0.638, + "step": 112 + }, + { + "epoch": 3.7983193277310923, + "grad_norm": 0.345703125, + "learning_rate": 3.950157384783104e-07, + "loss": 1.8459, + "step": 113 + }, + { + "epoch": 3.831932773109244, + "grad_norm": 0.3671875, + "learning_rate": 1.7562682356786487e-07, + "loss": 1.805, + "step": 114 + }, + { + "epoch": 3.865546218487395, + "grad_norm": 0.373046875, + "learning_rate": 4.391634912056519e-08, + "loss": 1.7397, + "step": 115 + }, + { + "epoch": 3.899159663865546, + "grad_norm": 0.375, + "learning_rate": 0.0, + "loss": 1.6616, + "step": 116 + } + ], + "logging_steps": 1, + "max_steps": 116, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 29, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 7267163051655168.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-116/training_args.bin b/checkpoint-116/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..88b927d25682f0f145a1955404a39acbd3a16694 --- /dev/null +++ b/checkpoint-116/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ecf7623198831a8314ed416875045a0e7b9b7d3b0cc4a334c24e125cccc9c0 +size 5944 diff --git a/checkpoint-29/README.md b/checkpoint-29/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e1ccd431539a8f1507d8755a9c3ba5e5b2897978 --- /dev/null +++ b/checkpoint-29/README.md @@ -0,0 +1,202 @@ +--- +library_name: peft +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T +--- + +# 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 0.11.1 \ No newline at end of file diff --git a/checkpoint-29/adapter_config.json b/checkpoint-29/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0a39bbdad47a61fa660b177ceb742e4446650f75 --- /dev/null +++ b/checkpoint-29/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "bias": "none", + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "q_proj", + "up_proj", + "v_proj", + "gate_proj", + "o_proj", + "k_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-29/adapter_model.safetensors b/checkpoint-29/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..764a8c5017e56b4d8c139f2f7add3a15ec09bb66 --- /dev/null +++ b/checkpoint-29/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e40e118a7d580aa654fe038a2c2f2e1a0e845a70e267b1a7d403614369b8c4 +size 50503848 diff --git a/checkpoint-29/optimizer.pt b/checkpoint-29/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..03f20dbac42201bdf388f092109ed7d74311a3c7 --- /dev/null +++ b/checkpoint-29/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82dde275ce5d654ef486d2240ec5267e237fd39d912507ba7f31b3fc24ccd93e +size 202035450 diff --git a/checkpoint-29/rng_state.pth b/checkpoint-29/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5868332f8095f77e0f8e082ad7b8a17e00c3c8ff --- /dev/null +++ b/checkpoint-29/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d59eeb078be2200dbc7d7b0dc19d60d6acda60464b5de3991b614180e3c7850b +size 14244 diff --git a/checkpoint-29/scheduler.pt b/checkpoint-29/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f063c1a6852ef8c3a95f27c4a7fddee4c12090d --- /dev/null +++ b/checkpoint-29/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e0ea69a0f2d46a8611802e20de4ba9ab4c81307121d85f58745fed7e6bfae6 +size 1064 diff --git a/checkpoint-29/special_tokens_map.json b/checkpoint-29/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-29/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-29/tokenizer.model b/checkpoint-29/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/checkpoint-29/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/checkpoint-29/tokenizer_config.json b/checkpoint-29/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86 --- /dev/null +++ b/checkpoint-29/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +} diff --git a/checkpoint-29/trainer_state.json b/checkpoint-29/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..4e2ea182c289c3acd9b7267571a567f8e70aebdb --- /dev/null +++ b/checkpoint-29/trainer_state.json @@ -0,0 +1,268 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9747899159663865, + "eval_steps": 8, + "global_step": 29, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03361344537815126, + "grad_norm": 0.423828125, + "learning_rate": 2e-05, + "loss": 2.3126, + "step": 1 + }, + { + "epoch": 0.03361344537815126, + "eval_loss": 2.3783609867095947, + "eval_runtime": 10.4273, + "eval_samples_per_second": 4.795, + "eval_steps_per_second": 0.671, + "step": 1 + }, + { + "epoch": 0.06722689075630252, + "grad_norm": 0.4375, + "learning_rate": 4e-05, + "loss": 2.3746, + "step": 2 + }, + { + "epoch": 0.10084033613445378, + "grad_norm": 0.40625, + "learning_rate": 6e-05, + "loss": 2.5894, + "step": 3 + }, + { + "epoch": 0.13445378151260504, + "grad_norm": 0.451171875, + "learning_rate": 8e-05, + "loss": 2.3395, + "step": 4 + }, + { + "epoch": 0.16806722689075632, + "grad_norm": 0.40625, + "learning_rate": 0.0001, + "loss": 2.4187, + "step": 5 + }, + { + "epoch": 0.20168067226890757, + "grad_norm": 0.423828125, + "learning_rate": 0.00012, + "loss": 2.4575, + "step": 6 + }, + { + "epoch": 0.23529411764705882, + "grad_norm": 0.34375, + "learning_rate": 0.00014, + "loss": 2.1943, + "step": 7 + }, + { + "epoch": 0.2689075630252101, + "grad_norm": 0.33203125, + "learning_rate": 0.00016, + "loss": 2.2933, + "step": 8 + }, + { + "epoch": 0.2689075630252101, + "eval_loss": 2.1781439781188965, + "eval_runtime": 10.9815, + "eval_samples_per_second": 4.553, + "eval_steps_per_second": 0.637, + "step": 8 + }, + { + "epoch": 0.3025210084033613, + "grad_norm": 0.333984375, + "learning_rate": 0.00018, + "loss": 2.1869, + "step": 9 + }, + { + "epoch": 0.33613445378151263, + "grad_norm": 0.279296875, + "learning_rate": 0.0002, + "loss": 2.297, + "step": 10 + }, + { + "epoch": 0.3697478991596639, + "grad_norm": 0.30078125, + "learning_rate": 0.00019995608365087946, + "loss": 2.1138, + "step": 11 + }, + { + "epoch": 0.40336134453781514, + "grad_norm": 0.259765625, + "learning_rate": 0.00019982437317643217, + "loss": 2.0531, + "step": 12 + }, + { + "epoch": 0.4369747899159664, + "grad_norm": 0.3125, + "learning_rate": 0.0001996049842615217, + "loss": 2.0082, + "step": 13 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 0.33984375, + "learning_rate": 0.00019929810960135172, + "loss": 2.044, + "step": 14 + }, + { + "epoch": 0.5042016806722689, + "grad_norm": 0.310546875, + "learning_rate": 0.0001989040187322164, + "loss": 2.0348, + "step": 15 + }, + { + "epoch": 0.5378151260504201, + "grad_norm": 0.287109375, + "learning_rate": 0.00019842305779475968, + "loss": 2.0371, + "step": 16 + }, + { + "epoch": 0.5378151260504201, + "eval_loss": 2.0500473976135254, + "eval_runtime": 10.9871, + "eval_samples_per_second": 4.551, + "eval_steps_per_second": 0.637, + "step": 16 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.2734375, + "learning_rate": 0.0001978556492299504, + "loss": 2.0658, + "step": 17 + }, + { + "epoch": 0.6050420168067226, + "grad_norm": 0.302734375, + "learning_rate": 0.0001972022914080411, + "loss": 2.126, + "step": 18 + }, + { + "epoch": 0.6386554621848739, + "grad_norm": 0.2734375, + "learning_rate": 0.00019646355819083589, + "loss": 2.0384, + "step": 19 + }, + { + "epoch": 0.6722689075630253, + "grad_norm": 0.251953125, + "learning_rate": 0.00019564009842765225, + "loss": 2.0598, + "step": 20 + }, + { + "epoch": 0.7058823529411765, + "grad_norm": 0.27734375, + "learning_rate": 0.00019473263538541914, + "loss": 2.0817, + "step": 21 + }, + { + "epoch": 0.7394957983193278, + "grad_norm": 0.267578125, + "learning_rate": 0.0001937419661134121, + "loss": 2.0959, + "step": 22 + }, + { + "epoch": 0.773109243697479, + "grad_norm": 0.28125, + "learning_rate": 0.00019266896074318334, + "loss": 2.1694, + "step": 23 + }, + { + "epoch": 0.8067226890756303, + "grad_norm": 0.240234375, + "learning_rate": 0.00019151456172430183, + "loss": 1.8653, + "step": 24 + }, + { + "epoch": 0.8067226890756303, + "eval_loss": 2.028913736343384, + "eval_runtime": 11.0811, + "eval_samples_per_second": 4.512, + "eval_steps_per_second": 0.632, + "step": 24 + }, + { + "epoch": 0.8403361344537815, + "grad_norm": 0.2578125, + "learning_rate": 0.00019027978299657436, + "loss": 1.979, + "step": 25 + }, + { + "epoch": 0.8739495798319328, + "grad_norm": 0.2294921875, + "learning_rate": 0.00018896570909947475, + "loss": 2.0706, + "step": 26 + }, + { + "epoch": 0.907563025210084, + "grad_norm": 0.26171875, + "learning_rate": 0.0001875734942195637, + "loss": 2.1814, + "step": 27 + }, + { + "epoch": 0.9411764705882353, + "grad_norm": 0.255859375, + "learning_rate": 0.00018610436117673555, + "loss": 1.9951, + "step": 28 + }, + { + "epoch": 0.9747899159663865, + "grad_norm": 0.267578125, + "learning_rate": 0.0001845596003501826, + "loss": 2.1463, + "step": 29 + } + ], + "logging_steps": 1, + "max_steps": 116, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 29, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1832864956022784.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-29/training_args.bin b/checkpoint-29/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..88b927d25682f0f145a1955404a39acbd3a16694 --- /dev/null +++ b/checkpoint-29/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ecf7623198831a8314ed416875045a0e7b9b7d3b0cc4a334c24e125cccc9c0 +size 5944 diff --git a/checkpoint-58/README.md b/checkpoint-58/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e1ccd431539a8f1507d8755a9c3ba5e5b2897978 --- /dev/null +++ b/checkpoint-58/README.md @@ -0,0 +1,202 @@ +--- +library_name: peft +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T +--- + +# 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 0.11.1 \ No newline at end of file diff --git a/checkpoint-58/adapter_config.json b/checkpoint-58/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0a39bbdad47a61fa660b177ceb742e4446650f75 --- /dev/null +++ b/checkpoint-58/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "bias": "none", + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "q_proj", + "up_proj", + "v_proj", + "gate_proj", + "o_proj", + "k_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-58/adapter_model.safetensors b/checkpoint-58/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..293b8a12bdc0b1d75d8002826a2f4dc17fd43ba6 --- /dev/null +++ b/checkpoint-58/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0514e2d4f26f28359232745336d61398a454801cc15fddfe7a31da0e9ca16bfb +size 50503848 diff --git a/checkpoint-58/optimizer.pt b/checkpoint-58/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f070d1904700e66e31368c8996dd7be3d0f470fa --- /dev/null +++ b/checkpoint-58/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b28fb18bd58e9df2c1336a58195d19e24ade3f1dfcd422a1593a8a5924faaed1 +size 202035450 diff --git a/checkpoint-58/rng_state.pth b/checkpoint-58/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ba4abc6b670252f05288346fc7049517217c1d5 --- /dev/null +++ b/checkpoint-58/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc8579f44b16b95d7cae985becbc1ae965b9170a0b8005788db10c17496b22d +size 14244 diff --git a/checkpoint-58/scheduler.pt b/checkpoint-58/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e377bc38d38b096d2bcf506ad1e35afcd94de1c --- /dev/null +++ b/checkpoint-58/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffd843f86241f649ae5523a8aa7c9d13157ef6bc9ba4fe819ec88f7f7923587 +size 1064 diff --git a/checkpoint-58/special_tokens_map.json b/checkpoint-58/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-58/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-58/tokenizer.model b/checkpoint-58/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/checkpoint-58/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/checkpoint-58/tokenizer_config.json b/checkpoint-58/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86 --- /dev/null +++ b/checkpoint-58/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +} diff --git a/checkpoint-58/trainer_state.json b/checkpoint-58/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..3212294e1754f6e16d1e689f621527da91200aab --- /dev/null +++ b/checkpoint-58/trainer_state.json @@ -0,0 +1,503 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.949579831932773, + "eval_steps": 8, + "global_step": 58, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03361344537815126, + "grad_norm": 0.423828125, + "learning_rate": 2e-05, + "loss": 2.3126, + "step": 1 + }, + { + "epoch": 0.03361344537815126, + "eval_loss": 2.3783609867095947, + "eval_runtime": 10.4273, + "eval_samples_per_second": 4.795, + "eval_steps_per_second": 0.671, + "step": 1 + }, + { + "epoch": 0.06722689075630252, + "grad_norm": 0.4375, + "learning_rate": 4e-05, + "loss": 2.3746, + "step": 2 + }, + { + "epoch": 0.10084033613445378, + "grad_norm": 0.40625, + "learning_rate": 6e-05, + "loss": 2.5894, + "step": 3 + }, + { + "epoch": 0.13445378151260504, + "grad_norm": 0.451171875, + "learning_rate": 8e-05, + "loss": 2.3395, + "step": 4 + }, + { + "epoch": 0.16806722689075632, + "grad_norm": 0.40625, + "learning_rate": 0.0001, + "loss": 2.4187, + "step": 5 + }, + { + "epoch": 0.20168067226890757, + "grad_norm": 0.423828125, + "learning_rate": 0.00012, + "loss": 2.4575, + "step": 6 + }, + { + "epoch": 0.23529411764705882, + "grad_norm": 0.34375, + "learning_rate": 0.00014, + "loss": 2.1943, + "step": 7 + }, + { + "epoch": 0.2689075630252101, + "grad_norm": 0.33203125, + "learning_rate": 0.00016, + "loss": 2.2933, + "step": 8 + }, + { + "epoch": 0.2689075630252101, + "eval_loss": 2.1781439781188965, + "eval_runtime": 10.9815, + "eval_samples_per_second": 4.553, + "eval_steps_per_second": 0.637, + "step": 8 + }, + { + "epoch": 0.3025210084033613, + "grad_norm": 0.333984375, + "learning_rate": 0.00018, + "loss": 2.1869, + "step": 9 + }, + { + "epoch": 0.33613445378151263, + "grad_norm": 0.279296875, + "learning_rate": 0.0002, + "loss": 2.297, + "step": 10 + }, + { + "epoch": 0.3697478991596639, + "grad_norm": 0.30078125, + "learning_rate": 0.00019995608365087946, + "loss": 2.1138, + "step": 11 + }, + { + "epoch": 0.40336134453781514, + "grad_norm": 0.259765625, + "learning_rate": 0.00019982437317643217, + "loss": 2.0531, + "step": 12 + }, + { + "epoch": 0.4369747899159664, + "grad_norm": 0.3125, + "learning_rate": 0.0001996049842615217, + "loss": 2.0082, + "step": 13 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 0.33984375, + "learning_rate": 0.00019929810960135172, + "loss": 2.044, + "step": 14 + }, + { + "epoch": 0.5042016806722689, + "grad_norm": 0.310546875, + "learning_rate": 0.0001989040187322164, + "loss": 2.0348, + "step": 15 + }, + { + "epoch": 0.5378151260504201, + "grad_norm": 0.287109375, + "learning_rate": 0.00019842305779475968, + "loss": 2.0371, + "step": 16 + }, + { + "epoch": 0.5378151260504201, + "eval_loss": 2.0500473976135254, + "eval_runtime": 10.9871, + "eval_samples_per_second": 4.551, + "eval_steps_per_second": 0.637, + "step": 16 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.2734375, + "learning_rate": 0.0001978556492299504, + "loss": 2.0658, + "step": 17 + }, + { + "epoch": 0.6050420168067226, + "grad_norm": 0.302734375, + "learning_rate": 0.0001972022914080411, + "loss": 2.126, + "step": 18 + }, + { + "epoch": 0.6386554621848739, + "grad_norm": 0.2734375, + "learning_rate": 0.00019646355819083589, + "loss": 2.0384, + "step": 19 + }, + { + "epoch": 0.6722689075630253, + "grad_norm": 0.251953125, + "learning_rate": 0.00019564009842765225, + "loss": 2.0598, + "step": 20 + }, + { + "epoch": 0.7058823529411765, + "grad_norm": 0.27734375, + "learning_rate": 0.00019473263538541914, + "loss": 2.0817, + "step": 21 + }, + { + "epoch": 0.7394957983193278, + "grad_norm": 0.267578125, + "learning_rate": 0.0001937419661134121, + "loss": 2.0959, + "step": 22 + }, + { + "epoch": 0.773109243697479, + "grad_norm": 0.28125, + "learning_rate": 0.00019266896074318334, + "loss": 2.1694, + "step": 23 + }, + { + "epoch": 0.8067226890756303, + "grad_norm": 0.240234375, + "learning_rate": 0.00019151456172430183, + "loss": 1.8653, + "step": 24 + }, + { + "epoch": 0.8067226890756303, + "eval_loss": 2.028913736343384, + "eval_runtime": 11.0811, + "eval_samples_per_second": 4.512, + "eval_steps_per_second": 0.632, + "step": 24 + }, + { + "epoch": 0.8403361344537815, + "grad_norm": 0.2578125, + "learning_rate": 0.00019027978299657436, + "loss": 1.979, + "step": 25 + }, + { + "epoch": 0.8739495798319328, + "grad_norm": 0.2294921875, + "learning_rate": 0.00018896570909947475, + "loss": 2.0706, + "step": 26 + }, + { + "epoch": 0.907563025210084, + "grad_norm": 0.26171875, + "learning_rate": 0.0001875734942195637, + "loss": 2.1814, + "step": 27 + }, + { + "epoch": 0.9411764705882353, + "grad_norm": 0.255859375, + "learning_rate": 0.00018610436117673555, + "loss": 1.9951, + "step": 28 + }, + { + "epoch": 0.9747899159663865, + "grad_norm": 0.267578125, + "learning_rate": 0.0001845596003501826, + "loss": 2.1463, + "step": 29 + }, + { + "epoch": 1.0084033613445378, + "grad_norm": 0.27734375, + "learning_rate": 0.0001829405685450202, + "loss": 2.2055, + "step": 30 + }, + { + "epoch": 1.0420168067226891, + "grad_norm": 0.208984375, + "learning_rate": 0.00018124868780056814, + "loss": 2.0328, + "step": 31 + }, + { + "epoch": 1.0756302521008403, + "grad_norm": 0.2470703125, + "learning_rate": 0.00017948544414133534, + "loss": 2.0311, + "step": 32 + }, + { + "epoch": 1.0756302521008403, + "eval_loss": 2.0189168453216553, + "eval_runtime": 11.1124, + "eval_samples_per_second": 4.499, + "eval_steps_per_second": 0.63, + "step": 32 + }, + { + "epoch": 1.1092436974789917, + "grad_norm": 0.2080078125, + "learning_rate": 0.00017765238627180424, + "loss": 2.0399, + "step": 33 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 0.2265625, + "learning_rate": 0.00017575112421616202, + "loss": 1.9265, + "step": 34 + }, + { + "epoch": 1.1764705882352942, + "grad_norm": 0.205078125, + "learning_rate": 0.00017378332790417273, + "loss": 2.0815, + "step": 35 + }, + { + "epoch": 1.2100840336134453, + "grad_norm": 0.220703125, + "learning_rate": 0.00017175072570443312, + "loss": 2.0716, + "step": 36 + }, + { + "epoch": 1.2436974789915967, + "grad_norm": 0.23828125, + "learning_rate": 0.00016965510290629972, + "loss": 2.1353, + "step": 37 + }, + { + "epoch": 1.2773109243697478, + "grad_norm": 0.234375, + "learning_rate": 0.00016749830015182107, + "loss": 2.037, + "step": 38 + }, + { + "epoch": 1.3109243697478992, + "grad_norm": 0.2314453125, + "learning_rate": 0.00016528221181905217, + "loss": 2.1324, + "step": 39 + }, + { + "epoch": 1.3445378151260505, + "grad_norm": 0.236328125, + "learning_rate": 0.00016300878435817113, + "loss": 1.9591, + "step": 40 + }, + { + "epoch": 1.3445378151260505, + "eval_loss": 2.0105881690979004, + "eval_runtime": 11.061, + "eval_samples_per_second": 4.52, + "eval_steps_per_second": 0.633, + "step": 40 + }, + { + "epoch": 1.3781512605042017, + "grad_norm": 0.2294921875, + "learning_rate": 0.00016068001458185936, + "loss": 2.0045, + "step": 41 + }, + { + "epoch": 1.4117647058823528, + "grad_norm": 0.25390625, + "learning_rate": 0.0001582979479114472, + "loss": 1.8726, + "step": 42 + }, + { + "epoch": 1.4453781512605042, + "grad_norm": 0.24609375, + "learning_rate": 0.00015586467658036524, + "loss": 2.1408, + "step": 43 + }, + { + "epoch": 1.4789915966386555, + "grad_norm": 0.2392578125, + "learning_rate": 0.0001533823377964791, + "loss": 1.8444, + "step": 44 + }, + { + "epoch": 1.5126050420168067, + "grad_norm": 0.24609375, + "learning_rate": 0.00015085311186492206, + "loss": 1.8595, + "step": 45 + }, + { + "epoch": 1.5462184873949578, + "grad_norm": 0.24609375, + "learning_rate": 0.00014827922027307451, + "loss": 1.9338, + "step": 46 + }, + { + "epoch": 1.5798319327731094, + "grad_norm": 0.255859375, + "learning_rate": 0.0001456629237393713, + "loss": 1.9562, + "step": 47 + }, + { + "epoch": 1.6134453781512605, + "grad_norm": 0.267578125, + "learning_rate": 0.00014300652022765207, + "loss": 1.994, + "step": 48 + }, + { + "epoch": 1.6134453781512605, + "eval_loss": 2.010645866394043, + "eval_runtime": 10.957, + "eval_samples_per_second": 4.563, + "eval_steps_per_second": 0.639, + "step": 48 + }, + { + "epoch": 1.6470588235294117, + "grad_norm": 0.2890625, + "learning_rate": 0.00014031234292879725, + "loss": 1.9666, + "step": 49 + }, + { + "epoch": 1.680672268907563, + "grad_norm": 0.26953125, + "learning_rate": 0.00013758275821142382, + "loss": 1.8065, + "step": 50 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 0.30859375, + "learning_rate": 0.0001348201635434399, + "loss": 2.0882, + "step": 51 + }, + { + "epoch": 1.7478991596638656, + "grad_norm": 0.2734375, + "learning_rate": 0.00013202698538628376, + "loss": 1.9619, + "step": 52 + }, + { + "epoch": 1.7815126050420167, + "grad_norm": 0.271484375, + "learning_rate": 0.00012920567706369758, + "loss": 2.0829, + "step": 53 + }, + { + "epoch": 1.815126050420168, + "grad_norm": 0.30859375, + "learning_rate": 0.00012635871660690676, + "loss": 2.0254, + "step": 54 + }, + { + "epoch": 1.8487394957983194, + "grad_norm": 0.2734375, + "learning_rate": 0.00012348860457809838, + "loss": 2.0488, + "step": 55 + }, + { + "epoch": 1.8823529411764706, + "grad_norm": 0.294921875, + "learning_rate": 0.00012059786187410984, + "loss": 1.9204, + "step": 56 + }, + { + "epoch": 1.8823529411764706, + "eval_loss": 2.0145041942596436, + "eval_runtime": 10.9679, + "eval_samples_per_second": 4.559, + "eval_steps_per_second": 0.638, + "step": 56 + }, + { + "epoch": 1.9159663865546217, + "grad_norm": 0.279296875, + "learning_rate": 0.0001176890275122573, + "loss": 1.7729, + "step": 57 + }, + { + "epoch": 1.949579831932773, + "grad_norm": 0.294921875, + "learning_rate": 0.00011476465640024814, + "loss": 2.0228, + "step": 58 + } + ], + "logging_steps": 1, + "max_steps": 116, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 29, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3642534240976896.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-58/training_args.bin b/checkpoint-58/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..88b927d25682f0f145a1955404a39acbd3a16694 --- /dev/null +++ b/checkpoint-58/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ecf7623198831a8314ed416875045a0e7b9b7d3b0cc4a334c24e125cccc9c0 +size 5944 diff --git a/checkpoint-87/README.md b/checkpoint-87/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e1ccd431539a8f1507d8755a9c3ba5e5b2897978 --- /dev/null +++ b/checkpoint-87/README.md @@ -0,0 +1,202 @@ +--- +library_name: peft +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T +--- + +# 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 0.11.1 \ No newline at end of file diff --git a/checkpoint-87/adapter_config.json b/checkpoint-87/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0a39bbdad47a61fa660b177ceb742e4446650f75 --- /dev/null +++ b/checkpoint-87/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "bias": "none", + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "q_proj", + "up_proj", + "v_proj", + "gate_proj", + "o_proj", + "k_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-87/adapter_model.safetensors b/checkpoint-87/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86ff745963fa13d319bd529d5f883a509b07a436 --- /dev/null +++ b/checkpoint-87/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fef72baba3a599a0f5a186f4443823aa22f85d193757f7ea315286548447dc +size 50503848 diff --git a/checkpoint-87/optimizer.pt b/checkpoint-87/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..df01238e083dcee15d00bf34fa50db0dbae5b98c --- /dev/null +++ b/checkpoint-87/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfa37d8976d798cfa303636b904a50dc1e71b7e59e9bbaab96f1e5d55d3aba39 +size 202035450 diff --git a/checkpoint-87/rng_state.pth b/checkpoint-87/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..34fe356698c67ed9ccb6d45d2e99ba9af72365be --- /dev/null +++ b/checkpoint-87/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec74a27073291926f2fe614ff0ef4332fe0548a8186e26d09b67a4f8ef71ca1d +size 14244 diff --git a/checkpoint-87/scheduler.pt b/checkpoint-87/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..769177b071d8fbc5d172d02f4a8b213b334b7c86 --- /dev/null +++ b/checkpoint-87/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96dfdc4ac2eb14a7a5283672324c02dd21283974614857cbf29d0d55e24e2b3f +size 1064 diff --git a/checkpoint-87/special_tokens_map.json b/checkpoint-87/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-87/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-87/tokenizer.model b/checkpoint-87/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/checkpoint-87/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/checkpoint-87/tokenizer_config.json b/checkpoint-87/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86 --- /dev/null +++ b/checkpoint-87/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +} diff --git a/checkpoint-87/trainer_state.json b/checkpoint-87/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e293827e8a00458b70522a1ac45981c8522b1eba --- /dev/null +++ b/checkpoint-87/trainer_state.json @@ -0,0 +1,730 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.92436974789916, + "eval_steps": 8, + "global_step": 87, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03361344537815126, + "grad_norm": 0.423828125, + "learning_rate": 2e-05, + "loss": 2.3126, + "step": 1 + }, + { + "epoch": 0.03361344537815126, + "eval_loss": 2.3783609867095947, + "eval_runtime": 10.4273, + "eval_samples_per_second": 4.795, + "eval_steps_per_second": 0.671, + "step": 1 + }, + { + "epoch": 0.06722689075630252, + "grad_norm": 0.4375, + "learning_rate": 4e-05, + "loss": 2.3746, + "step": 2 + }, + { + "epoch": 0.10084033613445378, + "grad_norm": 0.40625, + "learning_rate": 6e-05, + "loss": 2.5894, + "step": 3 + }, + { + "epoch": 0.13445378151260504, + "grad_norm": 0.451171875, + "learning_rate": 8e-05, + "loss": 2.3395, + "step": 4 + }, + { + "epoch": 0.16806722689075632, + "grad_norm": 0.40625, + "learning_rate": 0.0001, + "loss": 2.4187, + "step": 5 + }, + { + "epoch": 0.20168067226890757, + "grad_norm": 0.423828125, + "learning_rate": 0.00012, + "loss": 2.4575, + "step": 6 + }, + { + "epoch": 0.23529411764705882, + "grad_norm": 0.34375, + "learning_rate": 0.00014, + "loss": 2.1943, + "step": 7 + }, + { + "epoch": 0.2689075630252101, + "grad_norm": 0.33203125, + "learning_rate": 0.00016, + "loss": 2.2933, + "step": 8 + }, + { + "epoch": 0.2689075630252101, + "eval_loss": 2.1781439781188965, + "eval_runtime": 10.9815, + "eval_samples_per_second": 4.553, + "eval_steps_per_second": 0.637, + "step": 8 + }, + { + "epoch": 0.3025210084033613, + "grad_norm": 0.333984375, + "learning_rate": 0.00018, + "loss": 2.1869, + "step": 9 + }, + { + "epoch": 0.33613445378151263, + "grad_norm": 0.279296875, + "learning_rate": 0.0002, + "loss": 2.297, + "step": 10 + }, + { + "epoch": 0.3697478991596639, + "grad_norm": 0.30078125, + "learning_rate": 0.00019995608365087946, + "loss": 2.1138, + "step": 11 + }, + { + "epoch": 0.40336134453781514, + "grad_norm": 0.259765625, + "learning_rate": 0.00019982437317643217, + "loss": 2.0531, + "step": 12 + }, + { + "epoch": 0.4369747899159664, + "grad_norm": 0.3125, + "learning_rate": 0.0001996049842615217, + "loss": 2.0082, + "step": 13 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 0.33984375, + "learning_rate": 0.00019929810960135172, + "loss": 2.044, + "step": 14 + }, + { + "epoch": 0.5042016806722689, + "grad_norm": 0.310546875, + "learning_rate": 0.0001989040187322164, + "loss": 2.0348, + "step": 15 + }, + { + "epoch": 0.5378151260504201, + "grad_norm": 0.287109375, + "learning_rate": 0.00019842305779475968, + "loss": 2.0371, + "step": 16 + }, + { + "epoch": 0.5378151260504201, + "eval_loss": 2.0500473976135254, + "eval_runtime": 10.9871, + "eval_samples_per_second": 4.551, + "eval_steps_per_second": 0.637, + "step": 16 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.2734375, + "learning_rate": 0.0001978556492299504, + "loss": 2.0658, + "step": 17 + }, + { + "epoch": 0.6050420168067226, + "grad_norm": 0.302734375, + "learning_rate": 0.0001972022914080411, + "loss": 2.126, + "step": 18 + }, + { + "epoch": 0.6386554621848739, + "grad_norm": 0.2734375, + "learning_rate": 0.00019646355819083589, + "loss": 2.0384, + "step": 19 + }, + { + "epoch": 0.6722689075630253, + "grad_norm": 0.251953125, + "learning_rate": 0.00019564009842765225, + "loss": 2.0598, + "step": 20 + }, + { + "epoch": 0.7058823529411765, + "grad_norm": 0.27734375, + "learning_rate": 0.00019473263538541914, + "loss": 2.0817, + "step": 21 + }, + { + "epoch": 0.7394957983193278, + "grad_norm": 0.267578125, + "learning_rate": 0.0001937419661134121, + "loss": 2.0959, + "step": 22 + }, + { + "epoch": 0.773109243697479, + "grad_norm": 0.28125, + "learning_rate": 0.00019266896074318334, + "loss": 2.1694, + "step": 23 + }, + { + "epoch": 0.8067226890756303, + "grad_norm": 0.240234375, + "learning_rate": 0.00019151456172430183, + "loss": 1.8653, + "step": 24 + }, + { + "epoch": 0.8067226890756303, + "eval_loss": 2.028913736343384, + "eval_runtime": 11.0811, + "eval_samples_per_second": 4.512, + "eval_steps_per_second": 0.632, + "step": 24 + }, + { + "epoch": 0.8403361344537815, + "grad_norm": 0.2578125, + "learning_rate": 0.00019027978299657436, + "loss": 1.979, + "step": 25 + }, + { + "epoch": 0.8739495798319328, + "grad_norm": 0.2294921875, + "learning_rate": 0.00018896570909947475, + "loss": 2.0706, + "step": 26 + }, + { + "epoch": 0.907563025210084, + "grad_norm": 0.26171875, + "learning_rate": 0.0001875734942195637, + "loss": 2.1814, + "step": 27 + }, + { + "epoch": 0.9411764705882353, + "grad_norm": 0.255859375, + "learning_rate": 0.00018610436117673555, + "loss": 1.9951, + "step": 28 + }, + { + "epoch": 0.9747899159663865, + "grad_norm": 0.267578125, + "learning_rate": 0.0001845596003501826, + "loss": 2.1463, + "step": 29 + }, + { + "epoch": 1.0084033613445378, + "grad_norm": 0.27734375, + "learning_rate": 0.0001829405685450202, + "loss": 2.2055, + "step": 30 + }, + { + "epoch": 1.0420168067226891, + "grad_norm": 0.208984375, + "learning_rate": 0.00018124868780056814, + "loss": 2.0328, + "step": 31 + }, + { + "epoch": 1.0756302521008403, + "grad_norm": 0.2470703125, + "learning_rate": 0.00017948544414133534, + "loss": 2.0311, + "step": 32 + }, + { + "epoch": 1.0756302521008403, + "eval_loss": 2.0189168453216553, + "eval_runtime": 11.1124, + "eval_samples_per_second": 4.499, + "eval_steps_per_second": 0.63, + "step": 32 + }, + { + "epoch": 1.1092436974789917, + "grad_norm": 0.2080078125, + "learning_rate": 0.00017765238627180424, + "loss": 2.0399, + "step": 33 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 0.2265625, + "learning_rate": 0.00017575112421616202, + "loss": 1.9265, + "step": 34 + }, + { + "epoch": 1.1764705882352942, + "grad_norm": 0.205078125, + "learning_rate": 0.00017378332790417273, + "loss": 2.0815, + "step": 35 + }, + { + "epoch": 1.2100840336134453, + "grad_norm": 0.220703125, + "learning_rate": 0.00017175072570443312, + "loss": 2.0716, + "step": 36 + }, + { + "epoch": 1.2436974789915967, + "grad_norm": 0.23828125, + "learning_rate": 0.00016965510290629972, + "loss": 2.1353, + "step": 37 + }, + { + "epoch": 1.2773109243697478, + "grad_norm": 0.234375, + "learning_rate": 0.00016749830015182107, + "loss": 2.037, + "step": 38 + }, + { + "epoch": 1.3109243697478992, + "grad_norm": 0.2314453125, + "learning_rate": 0.00016528221181905217, + "loss": 2.1324, + "step": 39 + }, + { + "epoch": 1.3445378151260505, + "grad_norm": 0.236328125, + "learning_rate": 0.00016300878435817113, + "loss": 1.9591, + "step": 40 + }, + { + "epoch": 1.3445378151260505, + "eval_loss": 2.0105881690979004, + "eval_runtime": 11.061, + "eval_samples_per_second": 4.52, + "eval_steps_per_second": 0.633, + "step": 40 + }, + { + "epoch": 1.3781512605042017, + "grad_norm": 0.2294921875, + "learning_rate": 0.00016068001458185936, + "loss": 2.0045, + "step": 41 + }, + { + "epoch": 1.4117647058823528, + "grad_norm": 0.25390625, + "learning_rate": 0.0001582979479114472, + "loss": 1.8726, + "step": 42 + }, + { + "epoch": 1.4453781512605042, + "grad_norm": 0.24609375, + "learning_rate": 0.00015586467658036524, + "loss": 2.1408, + "step": 43 + }, + { + "epoch": 1.4789915966386555, + "grad_norm": 0.2392578125, + "learning_rate": 0.0001533823377964791, + "loss": 1.8444, + "step": 44 + }, + { + "epoch": 1.5126050420168067, + "grad_norm": 0.24609375, + "learning_rate": 0.00015085311186492206, + "loss": 1.8595, + "step": 45 + }, + { + "epoch": 1.5462184873949578, + "grad_norm": 0.24609375, + "learning_rate": 0.00014827922027307451, + "loss": 1.9338, + "step": 46 + }, + { + "epoch": 1.5798319327731094, + "grad_norm": 0.255859375, + "learning_rate": 0.0001456629237393713, + "loss": 1.9562, + "step": 47 + }, + { + "epoch": 1.6134453781512605, + "grad_norm": 0.267578125, + "learning_rate": 0.00014300652022765207, + "loss": 1.994, + "step": 48 + }, + { + "epoch": 1.6134453781512605, + "eval_loss": 2.010645866394043, + "eval_runtime": 10.957, + "eval_samples_per_second": 4.563, + "eval_steps_per_second": 0.639, + "step": 48 + }, + { + "epoch": 1.6470588235294117, + "grad_norm": 0.2890625, + "learning_rate": 0.00014031234292879725, + "loss": 1.9666, + "step": 49 + }, + { + "epoch": 1.680672268907563, + "grad_norm": 0.26953125, + "learning_rate": 0.00013758275821142382, + "loss": 1.8065, + "step": 50 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 0.30859375, + "learning_rate": 0.0001348201635434399, + "loss": 2.0882, + "step": 51 + }, + { + "epoch": 1.7478991596638656, + "grad_norm": 0.2734375, + "learning_rate": 0.00013202698538628376, + "loss": 1.9619, + "step": 52 + }, + { + "epoch": 1.7815126050420167, + "grad_norm": 0.271484375, + "learning_rate": 0.00012920567706369758, + "loss": 2.0829, + "step": 53 + }, + { + "epoch": 1.815126050420168, + "grad_norm": 0.30859375, + "learning_rate": 0.00012635871660690676, + "loss": 2.0254, + "step": 54 + }, + { + "epoch": 1.8487394957983194, + "grad_norm": 0.2734375, + "learning_rate": 0.00012348860457809838, + "loss": 2.0488, + "step": 55 + }, + { + "epoch": 1.8823529411764706, + "grad_norm": 0.294921875, + "learning_rate": 0.00012059786187410984, + "loss": 1.9204, + "step": 56 + }, + { + "epoch": 1.8823529411764706, + "eval_loss": 2.0145041942596436, + "eval_runtime": 10.9679, + "eval_samples_per_second": 4.559, + "eval_steps_per_second": 0.638, + "step": 56 + }, + { + "epoch": 1.9159663865546217, + "grad_norm": 0.279296875, + "learning_rate": 0.0001176890275122573, + "loss": 1.7729, + "step": 57 + }, + { + "epoch": 1.949579831932773, + "grad_norm": 0.294921875, + "learning_rate": 0.00011476465640024814, + "loss": 2.0228, + "step": 58 + }, + { + "epoch": 1.9831932773109244, + "grad_norm": 0.2734375, + "learning_rate": 0.00011182731709213659, + "loss": 1.869, + "step": 59 + }, + { + "epoch": 2.0168067226890756, + "grad_norm": 0.353515625, + "learning_rate": 0.00010887958953229349, + "loss": 1.8303, + "step": 60 + }, + { + "epoch": 2.0504201680672267, + "grad_norm": 0.294921875, + "learning_rate": 0.00010592406278937144, + "loss": 2.0863, + "step": 61 + }, + { + "epoch": 2.0840336134453783, + "grad_norm": 0.275390625, + "learning_rate": 0.00010296333278225599, + "loss": 1.9723, + "step": 62 + }, + { + "epoch": 2.1176470588235294, + "grad_norm": 0.3203125, + "learning_rate": 0.0001, + "loss": 1.9275, + "step": 63 + }, + { + "epoch": 2.1512605042016806, + "grad_norm": 0.28515625, + "learning_rate": 9.703666721774402e-05, + "loss": 1.8178, + "step": 64 + }, + { + "epoch": 2.1512605042016806, + "eval_loss": 2.015535831451416, + "eval_runtime": 11.0392, + "eval_samples_per_second": 4.529, + "eval_steps_per_second": 0.634, + "step": 64 + }, + { + "epoch": 2.184873949579832, + "grad_norm": 0.30078125, + "learning_rate": 9.407593721062859e-05, + "loss": 1.9097, + "step": 65 + }, + { + "epoch": 2.2184873949579833, + "grad_norm": 0.298828125, + "learning_rate": 9.112041046770653e-05, + "loss": 1.8793, + "step": 66 + }, + { + "epoch": 2.2521008403361344, + "grad_norm": 0.3359375, + "learning_rate": 8.817268290786343e-05, + "loss": 1.861, + "step": 67 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 0.31640625, + "learning_rate": 8.523534359975189e-05, + "loss": 1.8363, + "step": 68 + }, + { + "epoch": 2.3193277310924367, + "grad_norm": 0.31640625, + "learning_rate": 8.231097248774274e-05, + "loss": 1.8089, + "step": 69 + }, + { + "epoch": 2.3529411764705883, + "grad_norm": 0.3046875, + "learning_rate": 7.940213812589018e-05, + "loss": 1.814, + "step": 70 + }, + { + "epoch": 2.3865546218487395, + "grad_norm": 0.31640625, + "learning_rate": 7.651139542190164e-05, + "loss": 1.8281, + "step": 71 + }, + { + "epoch": 2.4201680672268906, + "grad_norm": 0.33203125, + "learning_rate": 7.364128339309326e-05, + "loss": 1.8428, + "step": 72 + }, + { + "epoch": 2.4201680672268906, + "eval_loss": 2.022204637527466, + "eval_runtime": 11.0405, + "eval_samples_per_second": 4.529, + "eval_steps_per_second": 0.634, + "step": 72 + }, + { + "epoch": 2.453781512605042, + "grad_norm": 0.357421875, + "learning_rate": 7.079432293630244e-05, + "loss": 1.904, + "step": 73 + }, + { + "epoch": 2.4873949579831933, + "grad_norm": 0.349609375, + "learning_rate": 6.797301461371625e-05, + "loss": 1.7909, + "step": 74 + }, + { + "epoch": 2.5210084033613445, + "grad_norm": 0.375, + "learning_rate": 6.517983645656014e-05, + "loss": 1.7367, + "step": 75 + }, + { + "epoch": 2.5546218487394956, + "grad_norm": 0.349609375, + "learning_rate": 6.24172417885762e-05, + "loss": 1.8942, + "step": 76 + }, + { + "epoch": 2.588235294117647, + "grad_norm": 0.34765625, + "learning_rate": 5.96876570712028e-05, + "loss": 1.8393, + "step": 77 + }, + { + "epoch": 2.6218487394957983, + "grad_norm": 0.35546875, + "learning_rate": 5.699347977234799e-05, + "loss": 1.8254, + "step": 78 + }, + { + "epoch": 2.6554621848739495, + "grad_norm": 0.349609375, + "learning_rate": 5.43370762606287e-05, + "loss": 1.9937, + "step": 79 + }, + { + "epoch": 2.689075630252101, + "grad_norm": 0.373046875, + "learning_rate": 5.172077972692553e-05, + "loss": 1.947, + "step": 80 + }, + { + "epoch": 2.689075630252101, + "eval_loss": 2.026715040206909, + "eval_runtime": 10.9879, + "eval_samples_per_second": 4.55, + "eval_steps_per_second": 0.637, + "step": 80 + }, + { + "epoch": 2.722689075630252, + "grad_norm": 0.326171875, + "learning_rate": 4.914688813507797e-05, + "loss": 1.9046, + "step": 81 + }, + { + "epoch": 2.7563025210084033, + "grad_norm": 0.35546875, + "learning_rate": 4.661766220352097e-05, + "loss": 1.9969, + "step": 82 + }, + { + "epoch": 2.7899159663865545, + "grad_norm": 0.361328125, + "learning_rate": 4.4135323419634766e-05, + "loss": 1.7827, + "step": 83 + }, + { + "epoch": 2.8235294117647056, + "grad_norm": 0.3515625, + "learning_rate": 4.170205208855281e-05, + "loss": 1.8887, + "step": 84 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 0.373046875, + "learning_rate": 3.931998541814069e-05, + "loss": 1.8327, + "step": 85 + }, + { + "epoch": 2.8907563025210083, + "grad_norm": 0.37890625, + "learning_rate": 3.69912156418289e-05, + "loss": 1.9086, + "step": 86 + }, + { + "epoch": 2.92436974789916, + "grad_norm": 0.390625, + "learning_rate": 3.471778818094785e-05, + "loss": 1.9553, + "step": 87 + } + ], + "logging_steps": 1, + "max_steps": 116, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 29, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5464004832264192.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-87/training_args.bin b/checkpoint-87/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..88b927d25682f0f145a1955404a39acbd3a16694 --- /dev/null +++ b/checkpoint-87/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ecf7623198831a8314ed416875045a0e7b9b7d3b0cc4a334c24e125cccc9c0 +size 5944 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4fd46aded17c1e2a61e180b1bb90c4097c007cd9 --- /dev/null +++ b/config.json @@ -0,0 +1,44 @@ +{ + "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 4096, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 22, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "quantization_config": { + "_load_in_4bit": true, + "_load_in_8bit": false, + "bnb_4bit_compute_dtype": "float32", + "bnb_4bit_quant_storage": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "llm_int8_enable_fp32_cpu_offload": false, + "llm_int8_has_fp16_weight": false, + "llm_int8_skip_modules": null, + "llm_int8_threshold": 6.0, + "load_in_4bit": true, + "load_in_8bit": false, + "quant_method": "bitsandbytes" + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.41.1", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}