commit 0b30b36285b9913d7c9318748eb2e5a3396baaa5 Author: ModelHub XC Date: Fri May 1 07:27:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: magnifi/magnifi-module-classifier-04-17-relabelled-upsampled Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..778704e --- /dev/null +++ b/README.md @@ -0,0 +1,151 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors +tags: +- axolotl +- generated_from_trainer +datasets: +- Tifin-Sage/magnifi-module-classifier-04-17-relabelled-upsampled +model-index: +- name: magnifi-module-classifier-04-17-relabelled-upsampled + results: [] +--- + + + +[Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl) +
See axolotl config + +axolotl version: `0.16.0.dev0` +```yaml +base_model: Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors +hub_model_id: Tifin-Sage/magnifi-module-classifier-04-17-relabelled-upsampled + +load_in_8bit: false +load_in_4bit: false +strict: false + +chat_template: qwen3 +datasets: + - path: Tifin-Sage/magnifi-module-classifier-04-17-relabelled-upsampled + type: chat_template + split: train + field_messages: messages + message_property_mappings: + role: role + content: content + +val_set_size: 0.1 + +output_dir: /workspace/data/outputs/qwen3-4B/fft_magnifi-module-classifier-04-17-relabelled-upsampled/ +dataset_prepared_path: /workspace/data/datasets_prepared/magnifi-module-classifier-04-17-relabelled-upsampled + +sequence_len: 16000 +sample_packing: true +eval_sample_packing: true + + +wandb_project: sage-classifier +wandb_entity: +wandb_watch: +wandb_name: magnifi-module-classifier-04-17-relabelled-upsampled +wandb_log_model: + +gradient_accumulation_steps: 1 +micro_batch_size: 1 +num_epochs: 2 +optimizer: adamw_torch_fused +lr_scheduler: cosine +learning_rate: 2e-5 + +bf16: auto +tf32: true + +resume_from_checkpoint: +logging_steps: 1 + +evals_per_epoch: 2 +saves_per_epoch: 1 + +warmup_ratio: 0.1 +weight_decay: 0.0 +fsdp: + - full_shard + - auto_wrap + +fsdp_config: + fsdp_version: 2 + fsdp_offload_params: false + fsdp_cpu_ram_efficient_loading: true + fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP + fsdp_transformer_layer_cls_to_wrap: Qwen3DecoderLayer + fsdp_state_dict_type: FULL_STATE_DICT + fsdp_sharding_strategy: FULL_SHARD + fsdp_reshard_after_forward: true + fsdp_activation_checkpointing: true + +special_tokens: + +``` + +

+ +# magnifi-module-classifier-04-17-relabelled-upsampled + +This model is a fine-tuned version of [Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors](https://huggingface.co/Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors) on the Tifin-Sage/magnifi-module-classifier-04-17-relabelled-upsampled dataset. +It achieves the following results on the evaluation set: +- Loss: 0.2227 +- Ppl: 1.2494 +- Memory/max Active (gib): 34.91 +- Memory/max Allocated (gib): 34.91 +- Memory/device Reserved (gib): 57.25 + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 2e-05 +- train_batch_size: 1 +- eval_batch_size: 1 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 2 +- total_train_batch_size: 2 +- total_eval_batch_size: 2 +- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 47 +- training_steps: 478 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | Ppl | Active (gib) | Allocated (gib) | Reserved (gib) | +|:-------------:|:------:|:----:|:---------------:|:------:|:------------:|:---------------:|:--------------:| +| No log | 0 | 0 | 0.2049 | 1.2275 | 27.41 | 27.41 | 30.62 | +| 0.2339 | 0.5 | 120 | 0.2288 | 1.2571 | 34.91 | 34.91 | 59.04 | +| 0.2290 | 1.0 | 240 | 0.2166 | 1.2419 | 34.91 | 34.91 | 57.54 | +| 0.0898 | 1.5 | 360 | 0.2251 | 1.2524 | 34.91 | 34.91 | 57.54 | +| 0.1331 | 1.9917 | 478 | 0.2227 | 1.2494 | 34.91 | 34.91 | 57.25 | + + +### Framework versions + +- Transformers 5.5.4 +- Pytorch 2.10.0+cu128 +- Datasets 4.8.4 +- Tokenizers 0.22.2 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..77ea906 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,93 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{#- Determine the real last index: use provided value or default to messages length - 1 #} +{%- if real_last_index is defined and real_last_index is not none %} + {%- set ns.real_last_index = real_last_index %} +{%- else %} + {%- set ns.real_last_index = messages|length - 1 %} +{%- endif %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set content = message.content %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is defined and message.reasoning_content is not none %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in message.content %} + {%- set content = message.content.split('')[-1].lstrip('\n') %} + {%- set reasoning_content = message.content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.index0 == ns.real_last_index or (loop.index0 != ns.real_last_index and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- else %} + {{- '\n\n' }} + {%- endif %} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..f0b779c --- /dev/null +++ b/config.json @@ -0,0 +1,72 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "rope_parameters": { + "rope_theta": 5000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.5.4", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/debug.log b/debug.log new file mode 100644 index 0000000..619309c --- /dev/null +++ b/debug.log @@ -0,0 +1,3 @@ + Fetching 2 files: 0%| | 0/2 [00:00", + "errors": "replace", + "is_local": false, + "model_max_length": 1010000, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train.log b/train.log new file mode 100644 index 0000000..453b331 --- /dev/null +++ b/train.log @@ -0,0 +1,2396 @@ +The following values were not passed to `accelerate launch` and had defaults used instead: + `--num_processes` was set to a value of `2` + More than one GPU was found, enabling multi-GPU training. + If this was unintended please pass in `--num_processes=1`. + `--num_machines` was set to a value of `1` + `--mixed_precision` was set to a value of `'no'` + `--dynamo_backend` was set to a value of `'no'` +To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`. +[2026-04-17 02:08:45,271] [WARNING] [torchao] Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128). +[2026-04-17 02:08:45,439] [WARNING] [torchao] Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128). +[2026-04-17 02:08:47,222] [WARNING] [axolotl.utils.schemas.validation] sample_packing without flash, sdp, xformers, sage, or flex attention does not handle cross sample decontamination. +[2026-04-17 02:08:47,223] [INFO] [axolotl.utils.schemas.validation] Setting `pad_to_sequence_len: true` to prevent memory leaks when sample_packing +[2026-04-17 02:08:47,223] [WARNING] [axolotl.utils.schemas.validation] Configuring FSDP fields with the `fsdp_` prefix is deprecated. Please omit the `fsdp_` prefix from the any fields in `fsdp_config`. +[2026-04-17 02:08:47,467] [INFO] [axolotl.cli.config] config: +{ + "activation_offloading": false, + "axolotl_config_path": "/workspace/data/sage-classifier-train-scripts/qwen3/fft/qwen3-4B-train-v1-6-no-liger-flex-magnifi-module-classifier-04-17-relabelled-upsampled.yml", + "base_model": "Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors", + "base_model_config": "Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors", + "batch_size": 2, + "bf16": true, + "capabilities": { + "bf16": true, + "compute_capability": "sm_80", + "fp8": false, + "n_gpu": 2, + "n_node": 1, + "tf32": true + }, + "chat_template": "qwen3", + "context_parallel_size": 1, + "dataloader_num_workers": 2, + "dataloader_pin_memory": true, + "dataloader_prefetch_factor": 256, + "dataset_num_proc": 128, + "dataset_prepared_path": "/workspace/data/datasets_prepared/magnifi-module-classifier-04-17-relabelled-upsampled", + "datasets": [ + { + "chat_template": "tokenizer_default", + "field_messages": "messages", + "message_property_mappings": { + "content": "content", + "role": "role" + }, + "path": "Tifin-Sage/magnifi-module-classifier-04-17-relabelled-upsampled", + "split": "train", + "trust_remote_code": false, + "type": "chat_template" + } + ], + "ddp": true, + "device": "cuda:0", + "device_map": { + "": 0 + }, + "dion_rank_fraction": 1.0, + "dion_rank_multiple_of": 1, + "eaft_alpha": 1.0, + "eaft_k": 20, + "env_capabilities": { + "torch_version": "2.10.0" + }, + "eval_batch_size": 1, + "eval_causal_lm_metrics": [ + "sacrebleu", + "comet", + "ter", + "chrf" + ], + "eval_max_new_tokens": 128, + "eval_sample_packing": true, + "eval_steps": 0.25, + "eval_table_size": 0, + "evals_per_epoch": 2, + "experimental_skip_move_to_device": true, + "fp16": false, + "fsdp": [ + "full_shard", + "auto_wrap" + ], + "fsdp_config": { + "activation_checkpointing": true, + "auto_wrap_policy": "TRANSFORMER_BASED_WRAP", + "cpu_ram_efficient_loading": true, + "fsdp_version": 2, + "offload_params": false, + "reshard_after_forward": true, + "state_dict_type": "FULL_STATE_DICT", + "transformer_layer_cls_to_wrap": "Qwen3DecoderLayer" + }, + "fsdp_version": 2, + "generate_samples": false, + "generation_do_sample": true, + "generation_max_new_tokens": 50, + "generation_prompt_ratio": 0.5, + "generation_temperature": 0.7, + "gradient_accumulation_steps": 1, + "gradient_checkpointing": false, + "hub_model_id": "Tifin-Sage/magnifi-module-classifier-04-17-relabelled-upsampled", + "include_tkps": true, + "layer_offloading": false, + "learning_rate": 2e-05, + "lisa_layers_attribute": "model.layers", + "load_best_model_at_end": false, + "load_in_4bit": false, + "load_in_8bit": false, + "local_rank": 0, + "logging_steps": 1, + "lora_dropout": 0.0, + "loraplus_lr_embedding": 1e-06, + "lr_scheduler": "cosine", + "mean_resizing_embeddings": false, + "merge_method": "memory_efficient", + "micro_batch_size": 1, + "model_config_type": "qwen3", + "num_epochs": 2.0, + "num_generation_samples": 3, + "optimizer": "adamw_torch_fused", + "otel_metrics_host": "localhost", + "otel_metrics_port": 8000, + "output_dir": "/workspace/data/outputs/qwen3-4B/fft_magnifi-module-classifier-04-17-relabelled-upsampled/", + "pad_to_sequence_len": true, + "pretrain_multipack_attn": true, + "profiler_steps_start": 0, + "qlora_sharded_model_loading": false, + "quantize_moe_experts": false, + "ray_num_workers": 1, + "resources_per_worker": { + "GPU": 1 + }, + "sample_packing": true, + "sample_packing_bin_size": 200, + "sample_packing_group_size": 100000, + "save_only_model": false, + "save_safetensors": true, + "save_steps": 0.5, + "saves_per_epoch": 1, + "sequence_len": 16000, + "shuffle_before_merging_datasets": false, + "shuffle_merged_datasets": true, + "skip_prepare_dataset": false, + "streaming_multipack_buffer_size": 10000, + "strict": false, + "tensor_parallel_size": 1, + "tf32": true, + "tiled_mlp_use_original_mlp": true, + "tokenizer_config": "Tifin-Sage/magnifi-classifier-01-05-search-agent-3-epochs-3k-unknown-errors", + "tokenizer_save_jinja_files": true, + "torch_dtype": "torch.bfloat16", + "train_on_inputs": false, + "trl": { + "async_prefetch": false, + "log_completions": false, + "mask_truncated_completions": false, + "ref_model_mixup_alpha": 0.9, + "ref_model_sync_steps": 64, + "replay_buffer_size": 0, + "replay_recompute_logps": true, + "reroll_max_groups": 1, + "reroll_start_fraction": 1.0, + "reward_num_workers": 1, + "scale_rewards": true, + "skip_zero_advantage_batches": true, + "sync_ref_model": false, + "use_data_producer": false, + "use_vllm": false, + "vllm_lora_sync": false, + "vllm_server_host": "0.0.0.0", + "vllm_server_port": 8000 + }, + "use_otel_metrics": false, + "use_ray": false, + "use_wandb": true, + "val_set_size": 0.1, + "vllm": { + "device": "auto", + "dtype": "auto", + "gpu_memory_utilization": 0.9, + "host": "0.0.0.0", + "port": 8000 + }, + "wandb_name": "magnifi-module-classifier-04-17-relabelled-upsampled", + "wandb_project": "sage-classifier", + "warmup_ratio": 0.1, + "weight_decay": 0.0, + "world_size": 2 +} +[2026-04-17 02:08:51,607] [INFO] [axolotl.utils.data.shared] Loading prepared dataset from disk at /workspace/data/datasets_prepared/magnifi-module-classifier-04-17-relabelled-upsampled/6241b9d0f4bdccc4ed4f52e5adefd1bc... +[Gloo] Rank [Gloo] Rank 1 is connected to 1 peer ranks. Expected number of connected peer ranks is : 1 +0 is connected to 1 peer ranks. Expected number of connected peer ranks is : 1 +[2026-04-17 02:08:57,019] [INFO] [axolotl.utils.samplers.multipack] gather_len_batches: [54, 54] +[2026-04-17 02:08:57,129] [INFO] [axolotl.utils.trainer] sample_packing_eff_est across ranks: [0.9649779796600342, 0.9649779796600342] +[2026-04-17 02:09:01,870] [INFO] [axolotl.utils.samplers.multipack] gather_len_batches: [478, 478] +[2026-04-17 02:09:01,872] [INFO] [axolotl.utils.trainer] sample_packing_eff_est across ranks: [0.969444751739502, 0.9775572419166565] +[2026-04-17 02:09:01,874] [INFO] [axolotl.utils.data.sft] Maximum number of steps set at 478 +[2026-04-17 02:09:03,028] [INFO] [axolotl.loaders.patch_manager] Applying multipack dataloader patch for sample packing... + Fetching 2 files: 0%| | 0/2 [00:00