Upload folder using huggingface_hub

gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/20/log.txt

@@ -1,3 +1,4 @@
 
 
 ============================== EXP at 2026-05-07 10:51:08 ==============================
+test | name: sinst_11_ | {'exact_match': 0.0, 'rougeL': 20.8066} | lm_loss 8.6715 | avg. gen lenth: 35.60684769775679

gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/30/args.json

@@ -0,0 +1 @@
+{"model_path": ".//results/gpt2/train/contra/distillm/qwen1.5-1.8b_0.1B/", "ckpt_name": "contra/distillm/qwen1.5-1.8b_0.1B", "model_type": "gpt2", "teacher_model_type": null, "n_gpu": 1, "n_nodes": 1, "teacher_model_path": null, "teacher_ckpt_name": null, "teacher_model_fp16": false, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "type": "eval_main", "do_train": false, "do_valid": false, "do_eval": true, "base_path": "./", "load": null, "save": ".//results/gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/30", "log_interval": 10, "mid_log_num": 4, "save_interval": 1000, "eval_interval": 1000, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "only_save_last": false, "data_dir": ".//data/sinst/11_", "teacher_data_dir": null, "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": -1, "dev_ratio": 1, "gen_num": -1, "data_names": "sinst_11_", "prompt_type": null, "num_workers": 0, "max_prompt_length": 256, "min_prompt_length": 128, "json_data": true, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": false, "only_prompt": false, "distillm2_data_dir": null, "gt_data_dir": ".//data/sinst/11_", "batch_size": 32, "eval_batch_size": 64, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 512, "seed": 30, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": null, "training_epochs": 10000, "gradient_accumulation_steps": 1, "gradient_checkpointing": false, "attn_dtype": null, "lr": null, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": null, "warmup_iters": 0, "lr_decay_iters": null, "lr_decay_style": "noam", "scheduler_name": "constant_trm", "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": false, "gen_top_p": 1.0, "gen_num_beams": 2, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "distillm2_loss_type": "distillm_v2", "gradual_beta": false, "base_alpha_1": 0.1, "base_alpha_2": 0.1, "wandb": false, "generate_sgo_interval": 1, "top_k": 0, "top_p": 1.0, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 1.0, "peft": null, "peft_lora_r": 16, "peft_lora_alpha": 64, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "d_teacher": 1600, "d_student": 768, "num_teacher_layers": 48, "num_student_layers": 12, "use_mtl_otcfm": false, "velocity_d_model": 1024, "velocity_n_layers": 6, "velocity_head_dim": 512, "otcfm_ratio": 1.0, "ot_reg": 0.1, "ot_method": "sinkhorn", "ot_per_token": false, "ot_sigma": 0.0, "velocity_field_path": null, "projector_path": null, "num_distill_layers": 6, "velocity_epochs": 1, "velocity_update_interval": 2, "teacher_device": 0, "student_device": 0, "cross_tokenizer_sra": false, "teacher_tokenizer_path": null, "sra_loss_weight": 1.0, "sra_p": 1.0, "geom_loss_weight": 50.0, "teacher_layers_mapping": null, "student_encoder_layers_finetuned": null, "hidden_loss_weights": null, "use_ot_cfm": false, "use_l2_loss": false, "use_cosine_loss": false, "use_hybrid_loss": false, "hybrid_cosine_weight": 0.6, "hybrid_l2_weight": 0.4, "csd_mode": "SS", "wandb_project": "contra-kd", "wandb_name": null, "wandb_key": null, "deepspeed": true, "deepspeed_config": ".//configs/deepspeed/ds_config.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 1}

gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/30/log.txt

@@ -0,0 +1,4 @@
+
+
+============================== EXP at 2026-05-07 10:54:25 ==============================
+test | name: sinst_11_ | {'exact_match': 0.0, 'rougeL': 20.6644} | lm_loss 8.6715 | avg. gen lenth: 35.824675324675326

gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/40/args.json

@@ -0,0 +1 @@
+{"model_path": ".//results/gpt2/train/contra/distillm/qwen1.5-1.8b_0.1B/", "ckpt_name": "contra/distillm/qwen1.5-1.8b_0.1B", "model_type": "gpt2", "teacher_model_type": null, "n_gpu": 1, "n_nodes": 1, "teacher_model_path": null, "teacher_ckpt_name": null, "teacher_model_fp16": false, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "type": "eval_main", "do_train": false, "do_valid": false, "do_eval": true, "base_path": "./", "load": null, "save": ".//results/gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/40", "log_interval": 10, "mid_log_num": 4, "save_interval": 1000, "eval_interval": 1000, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "only_save_last": false, "data_dir": ".//data/sinst/11_", "teacher_data_dir": null, "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": -1, "dev_ratio": 1, "gen_num": -1, "data_names": "sinst_11_", "prompt_type": null, "num_workers": 0, "max_prompt_length": 256, "min_prompt_length": 128, "json_data": true, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": false, "only_prompt": false, "distillm2_data_dir": null, "gt_data_dir": ".//data/sinst/11_", "batch_size": 32, "eval_batch_size": 64, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 512, "seed": 40, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": null, "training_epochs": 10000, "gradient_accumulation_steps": 1, "gradient_checkpointing": false, "attn_dtype": null, "lr": null, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": null, "warmup_iters": 0, "lr_decay_iters": null, "lr_decay_style": "noam", "scheduler_name": "constant_trm", "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": false, "gen_top_p": 1.0, "gen_num_beams": 2, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "distillm2_loss_type": "distillm_v2", "gradual_beta": false, "base_alpha_1": 0.1, "base_alpha_2": 0.1, "wandb": false, "generate_sgo_interval": 1, "top_k": 0, "top_p": 1.0, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 1.0, "peft": null, "peft_lora_r": 16, "peft_lora_alpha": 64, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "d_teacher": 1600, "d_student": 768, "num_teacher_layers": 48, "num_student_layers": 12, "use_mtl_otcfm": false, "velocity_d_model": 1024, "velocity_n_layers": 6, "velocity_head_dim": 512, "otcfm_ratio": 1.0, "ot_reg": 0.1, "ot_method": "sinkhorn", "ot_per_token": false, "ot_sigma": 0.0, "velocity_field_path": null, "projector_path": null, "num_distill_layers": 6, "velocity_epochs": 1, "velocity_update_interval": 2, "teacher_device": 0, "student_device": 0, "cross_tokenizer_sra": false, "teacher_tokenizer_path": null, "sra_loss_weight": 1.0, "sra_p": 1.0, "geom_loss_weight": 50.0, "teacher_layers_mapping": null, "student_encoder_layers_finetuned": null, "hidden_loss_weights": null, "use_ot_cfm": false, "use_l2_loss": false, "use_cosine_loss": false, "use_hybrid_loss": false, "hybrid_cosine_weight": 0.6, "hybrid_l2_weight": 0.4, "csd_mode": "SS", "wandb_project": "contra-kd", "wandb_name": null, "wandb_key": null, "deepspeed": true, "deepspeed_config": ".//configs/deepspeed/ds_config.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 1}

gpt2/eval_main/contra_distillm_qwen1.5-1.8b_0.1B/sinst_11_-512/40/log.txt

@@ -0,0 +1,3 @@
+
+
+============================== EXP at 2026-05-07 10:57:43 ==============================