Model save

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen3-1.7B
+tags:
+- base_model:adapter:Qwen/Qwen3-1.7B
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: tivd-gsm8k-colocate
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# tivd-gsm8k-colocate
+
+This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on an unknown 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: 3
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 24
+- 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: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 4.57.6
+- Pytorch 2.9.1+cu128
+- Datasets 4.8.4
+- Tokenizers 0.22.2

tivd_runtime_config.json

@@ -0,0 +1,202 @@
+{
+  "accelerator_config": {
+    "dispatch_batches": null,
+    "even_batches": true,
+    "gradient_accumulation_kwargs": null,
+    "non_blocking": false,
+    "split_batches": false,
+    "use_seedable_sampler": true
+  },
+  "adafactor": false,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "auto_find_batch_size": false,
+  "auto_launch_vllm_server": false,
+  "average_tokens_across_devices": true,
+  "batch_eval_metrics": false,
+  "bf16": true,
+  "bf16_full_eval": false,
+  "bootstrap_truncated_completions": true,
+  "data_seed": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": 0,
+  "dataloader_persistent_workers": false,
+  "dataloader_pin_memory": true,
+  "dataloader_prefetch_factor": null,
+  "ddp_backend": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_find_unused_parameters": null,
+  "ddp_timeout": 1800,
+  "debug": [],
+  "deepspeed": null,
+  "difficulty_threshold": 6.0,
+  "disable_tqdm": false,
+  "do_eval": false,
+  "do_predict": false,
+  "do_train": false,
+  "enable_thinking": true,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "eval_do_concat_batches": true,
+  "eval_on_start": false,
+  "eval_steps": null,
+  "eval_strategy": "no",
+  "eval_use_gather_object": false,
+  "fp16": false,
+  "fp16_backend": "auto",
+  "fp16_full_eval": false,
+  "fp16_opt_level": "O1",
+  "fsdp": [],
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_grad_ckpt": false,
+    "xla_fsdp_v2": false
+  },
+  "fsdp_min_num_params": 0,
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "full_determinism": false,
+  "gamma": 1.0,
+  "gradient_accumulation_steps": 8,
+  "gradient_checkpointing": false,
+  "gradient_checkpointing_kwargs": null,
+  "greater_is_better": null,
+  "group_by_length": false,
+  "half_precision_backend": "auto",
+  "hub_always_push": false,
+  "hub_model_id": "swadeshb/tivd-gsm8k-colocate",
+  "hub_private_repo": false,
+  "hub_revision": null,
+  "hub_strategy": "every_save",
+  "hub_token": "<HUB_TOKEN>",
+  "ignore_data_skip": false,
+  "include_for_metrics": [],
+  "include_inputs_for_metrics": false,
+  "include_num_input_tokens_seen": "no",
+  "include_tokens_per_second": false,
+  "jit_mode_eval": false,
+  "label_names": [],
+  "label_smoothing_factor": 0.0,
+  "learning_rate": 1e-05,
+  "length_column_name": "length",
+  "liger_kernel_config": null,
+  "load_best_model_at_end": false,
+  "local_rank": 0,
+  "log_completions": true,
+  "log_completions_every_n_steps": 50,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "outputs/tivd_gsm8k_colocate/runs/Apr15_08-45-31_e2e-72-102",
+  "logging_first_step": false,
+  "logging_nan_inf_filter": true,
+  "logging_steps": 1.0,
+  "logging_strategy": "steps",
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_r": 16,
+  "lora_target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj",
+  "lr_scheduler_kwargs": null,
+  "lr_scheduler_type": "linear",
+  "max_completion_length": 2048,
+  "max_grad_norm": 1.0,
+  "max_prompt_length": 768,
+  "max_steps": -1,
+  "metric_for_best_model": null,
+  "min_p": 0.0,
+  "mp_parameters": "",
+  "neftune_noise_alpha": null,
+  "no_cuda": false,
+  "num_generations": 8,
+  "num_train_epochs": 3.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "optim_target_modules": null,
+  "output_dir": "outputs/tivd_gsm8k_colocate",
+  "overwrite_output_dir": false,
+  "parallelism_config": null,
+  "past_index": -1,
+  "per_device_eval_batch_size": 8,
+  "per_device_train_batch_size": 3,
+  "per_gpu_eval_batch_size": null,
+  "per_gpu_train_batch_size": null,
+  "prediction_loss_only": false,
+  "project": "huggingface",
+  "push_to_hub": true,
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "ray_scope": "last",
+  "remove_unused_columns": false,
+  "repetition_penalty": 1.0,
+  "report_to": [
+    "wandb"
+  ],
+  "restore_callback_states_from_checkpoint": false,
+  "resume_from_checkpoint": null,
+  "run_name": null,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "save_safetensors": true,
+  "save_steps": 100,
+  "save_strategy": "steps",
+  "save_total_limit": 1,
+  "score_batch_size": 3,
+  "seed": 42,
+  "skip_memory_metrics": true,
+  "soft_value_temperature": 1.0,
+  "steps_per_generation": 1,
+  "student_load_in_4bit": false,
+  "student_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "system_prompt": "You are a careful mathematical reasoner. Solve the problem step by step. End with a concise final answer in the form Final Answer: \\boxed{...}.",
+  "target_ema_decay": 0.99,
+  "target_estimator": "td_lambda",
+  "target_sync_steps": 64,
+  "target_update_strategy": "hard",
+  "td_lambda": 0.95,
+  "teacher_load_in_4bit": true,
+  "teacher_model_name_or_path": "Qwen/Qwen3-4B",
+  "temperature": 1.0,
+  "tf32": null,
+  "top_k": -1,
+  "top_p": 1.0,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "torch_empty_cache_steps": null,
+  "torchdynamo": null,
+  "tpu_metrics_debug": false,
+  "tpu_num_cores": null,
+  "trackio_space_id": "trackio",
+  "trust_remote_code": true,
+  "use_cpu": false,
+  "use_legacy_prediction_loop": false,
+  "use_liger_kernel": false,
+  "use_lora": true,
+  "use_mps_device": false,
+  "use_vllm": true,
+  "vllm_cuda_visible_devices": "1",
+  "vllm_enable_prefix_caching": true,
+  "vllm_enable_sleep_mode": true,
+  "vllm_extra_args": null,
+  "vllm_fail_if_world_size_gt_1": true,
+  "vllm_gpu_memory_utilization": 0.3,
+  "vllm_group_port": null,
+  "vllm_kv_cache_dtype": "fp8",
+  "vllm_max_model_length": 3072,
+  "vllm_mode": "colocate",
+  "vllm_model_impl": "vllm",
+  "vllm_quantization": "bitsandbytes",
+  "vllm_server_base_url": null,
+  "vllm_server_host": "127.0.0.1",
+  "vllm_server_port": 8011,
+  "vllm_server_timeout": 300.0,
+  "vllm_tensor_parallel_size": 1,
+  "wandb_project": "tivd",
+  "wandb_run_name": null,
+  "warmup_ratio": 0.0,
+  "warmup_steps": 0,
+  "weight_decay": 0.0
+}