commit 090570c67f5a02d314b2429d84cbae78f0dcf72e Author: ModelHub XC Date: Sun Jul 19 11:38:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: AmberYifan/capmix-marin-8b-base-select Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1d699de --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-63/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4243b27 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: marin-community/marin-8b-base +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: marin-8b-base_select + results: [] +--- + + + +# marin-8b-base_select + +This model is a fine-tuned version of [marin-community/marin-8b-base](https://huggingface.co/marin-community/marin-8b-base) on the capmix_marin-8b-base__mix_select dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 1e-05 +- train_batch_size: 4 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 64 +- total_eval_batch_size: 32 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 0.03 +- num_epochs: 1 + +### Training results + + + +### Framework versions + +- Transformers 5.7.0 +- Pytorch 2.13.0+cu130 +- Datasets 4.0.0 +- Tokenizers 0.22.2 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..db8422c --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 5418005299200.0, + "train_loss": 0.49712625950101824, + "train_runtime": 409.6465, + "train_samples_per_second": 9.765, + "train_steps_per_second": 0.154 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c3af804 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|> + +' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|> + +' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/checkpoint-63/chat_template.jinja b/checkpoint-63/chat_template.jinja new file mode 100644 index 0000000..c3af804 --- /dev/null +++ b/checkpoint-63/chat_template.jinja @@ -0,0 +1,7 @@ +{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|> + +' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|> + +' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/checkpoint-63/config.json b/checkpoint-63/config.json new file mode 100644 index 0000000..728c271 --- /dev/null +++ b/checkpoint-63/config.json @@ -0,0 +1,51 @@ +{ + "_attn_implementation_autoset": false, + "add_cross_attention": false, + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "cross_attention_hidden_size": null, + "decoder_start_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128009, + "finetuning_task": null, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "is_decoder": false, + "max_position_embeddings": 4096, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "prefix": null, + "pretraining_tp": 1, + "pruned_heads": {}, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000, + "rope_type": "llama3" + }, + "sep_token_id": null, + "task_specific_params": null, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "torchscript": false, + "transformers_version": "5.7.0", + "use_bfloat16": false, + "use_cache": false, + "vocab_size": 128256 +} diff --git a/checkpoint-63/generation_config.json b/checkpoint-63/generation_config.json new file mode 100644 index 0000000..e5020b4 --- /dev/null +++ b/checkpoint-63/generation_config.json @@ -0,0 +1,37 @@ +{ + "_from_model_config": true, + "begin_suppress_tokens": [ + 128000, + 128001 + ], + "bos_token_id": 128000, + "decoder_start_token_id": 128000, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": [ + 128009, + 128001 + ], + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 128009, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict_in_generate": false, + "temperature": 1.0, + "top_k": 50, + "top_p": 1.0, + "transformers_version": "5.7.0", + "typical_p": 1.0, + "use_cache": true +} diff --git a/checkpoint-63/model.safetensors b/checkpoint-63/model.safetensors new file mode 100644 index 0000000..24853b7 --- /dev/null +++ b/checkpoint-63/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f746cf813385525ba5580b006c92209b1e4a3680c69c8cca944c18dc17a0dbb +size 16060556616 diff --git a/checkpoint-63/tokenizer.json b/checkpoint-63/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/checkpoint-63/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/checkpoint-63/tokenizer_config.json b/checkpoint-63/tokenizer_config.json new file mode 100644 index 0000000..74e8120 --- /dev/null +++ b/checkpoint-63/tokenizer_config.json @@ -0,0 +1,20 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": [ + "<|eom_id|>" + ], + "is_local": false, + "local_files_only": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "TokenizersBackend" +} diff --git a/checkpoint-63/trainer_state.json b/checkpoint-63/trainer_state.json new file mode 100644 index 0000000..10710e0 --- /dev/null +++ b/checkpoint-63/trainer_state.json @@ -0,0 +1,55 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 63, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.32, + "grad_norm": 0.4540108290704708, + "learning_rate": 8.202965893490877e-06, + "loss": 0.5189290046691895, + "step": 20 + }, + { + "epoch": 0.64, + "grad_norm": 0.40991677407712307, + "learning_rate": 3.3572880904458267e-06, + "loss": 0.4767247200012207, + "step": 40 + }, + { + "epoch": 0.96, + "grad_norm": 0.4387410289675732, + "learning_rate": 1.0572157452321097e-07, + "loss": 0.4906019687652588, + "step": 60 + } + ], + "logging_steps": 20, + "max_steps": 63, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5418005299200.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-63/training_args.bin b/checkpoint-63/training_args.bin new file mode 100644 index 0000000..c7dedc5 --- /dev/null +++ b/checkpoint-63/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2df73783539a415d81e049c69e7573958ce6f11d6be477f80dedd535a87ffa +size 7761 diff --git a/config.json b/config.json new file mode 100644 index 0000000..728c271 --- /dev/null +++ b/config.json @@ -0,0 +1,51 @@ +{ + "_attn_implementation_autoset": false, + "add_cross_attention": false, + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "cross_attention_hidden_size": null, + "decoder_start_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128009, + "finetuning_task": null, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "is_decoder": false, + "max_position_embeddings": 4096, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "prefix": null, + "pretraining_tp": 1, + "pruned_heads": {}, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000, + "rope_type": "llama3" + }, + "sep_token_id": null, + "task_specific_params": null, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "torchscript": false, + "transformers_version": "5.7.0", + "use_bfloat16": false, + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e5020b4 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,37 @@ +{ + "_from_model_config": true, + "begin_suppress_tokens": [ + 128000, + 128001 + ], + "bos_token_id": 128000, + "decoder_start_token_id": 128000, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": [ + 128009, + 128001 + ], + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 128009, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict_in_generate": false, + "temperature": 1.0, + "top_k": 50, + "top_p": 1.0, + "transformers_version": "5.7.0", + "typical_p": 1.0, + "use_cache": true +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..24853b7 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f746cf813385525ba5580b006c92209b1e4a3680c69c8cca944c18dc17a0dbb +size 16060556616 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..74e8120 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,20 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": [ + "<|eom_id|>" + ], + "is_local": false, + "local_files_only": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "TokenizersBackend" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..db8422c --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 5418005299200.0, + "train_loss": 0.49712625950101824, + "train_runtime": 409.6465, + "train_samples_per_second": 9.765, + "train_steps_per_second": 0.154 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..3655a1b --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,4 @@ +{"current_steps": 20, "total_steps": 63, "loss": 0.5189290046691895, "lr": 8.202965893490877e-06, "epoch": 0.32, "percentage": 31.75, "elapsed_time": "0:02:08", "remaining_time": "0:04:35"} +{"current_steps": 40, "total_steps": 63, "loss": 0.4767247200012207, "lr": 3.3572880904458267e-06, "epoch": 0.64, "percentage": 63.49, "elapsed_time": "0:04:14", "remaining_time": "0:02:26"} +{"current_steps": 60, "total_steps": 63, "loss": 0.4906019687652588, "lr": 1.0572157452321097e-07, "epoch": 0.96, "percentage": 95.24, "elapsed_time": "0:06:19", "remaining_time": "0:00:18"} +{"current_steps": 63, "total_steps": 63, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:06:49", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..e87688d --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,64 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 63, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.32, + "grad_norm": 0.4540108290704708, + "learning_rate": 8.202965893490877e-06, + "loss": 0.5189290046691895, + "step": 20 + }, + { + "epoch": 0.64, + "grad_norm": 0.40991677407712307, + "learning_rate": 3.3572880904458267e-06, + "loss": 0.4767247200012207, + "step": 40 + }, + { + "epoch": 0.96, + "grad_norm": 0.4387410289675732, + "learning_rate": 1.0572157452321097e-07, + "loss": 0.4906019687652588, + "step": 60 + }, + { + "epoch": 1.0, + "step": 63, + "total_flos": 5418005299200.0, + "train_loss": 0.49712625950101824, + "train_runtime": 409.6465, + "train_samples_per_second": 9.765, + "train_steps_per_second": 0.154 + } + ], + "logging_steps": 20, + "max_steps": 63, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5418005299200.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..c7dedc5 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2df73783539a415d81e049c69e7573958ce6f11d6be477f80dedd535a87ffa +size 7761 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..0b0a406 Binary files /dev/null and b/training_loss.png differ