| { | |
| "best_global_step": 10, | |
| "best_metric": 6.16926861, | |
| "best_model_checkpoint": "/workspace/output/v2-20250515-195801/checkpoint-10", | |
| "epoch": 0.9142857142857143, | |
| "eval_steps": 200, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09142857142857143, | |
| "grad_norm": 0.7688332200050354, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5431413650512695, | |
| "memory(GiB)": 12.53, | |
| "step": 1, | |
| "token_acc": 0.3338632750397456, | |
| "train_speed(iter/s)": 0.015387 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 0.6465986967086792, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 5.647396087646484, | |
| "memory(GiB)": 12.53, | |
| "step": 2, | |
| "token_acc": 0.2569832402234637, | |
| "train_speed(iter/s)": 0.018663 | |
| }, | |
| { | |
| "epoch": 0.2742857142857143, | |
| "grad_norm": 0.587317943572998, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 6.177090644836426, | |
| "memory(GiB)": 12.53, | |
| "step": 3, | |
| "token_acc": 0.22197802197802197, | |
| "train_speed(iter/s)": 0.02005 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "grad_norm": 0.5506355166435242, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 5.510315895080566, | |
| "memory(GiB)": 12.53, | |
| "step": 4, | |
| "token_acc": 0.30404217926186294, | |
| "train_speed(iter/s)": 0.020818 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.8027998805046082, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 5.994874954223633, | |
| "memory(GiB)": 12.53, | |
| "step": 5, | |
| "token_acc": 0.25, | |
| "train_speed(iter/s)": 0.021333 | |
| }, | |
| { | |
| "epoch": 0.5485714285714286, | |
| "grad_norm": 0.5449244379997253, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 6.046208381652832, | |
| "memory(GiB)": 12.53, | |
| "step": 6, | |
| "token_acc": 0.26285714285714284, | |
| "train_speed(iter/s)": 0.021655 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.47846531867980957, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 5.421955585479736, | |
| "memory(GiB)": 12.53, | |
| "step": 7, | |
| "token_acc": 0.29635499207606975, | |
| "train_speed(iter/s)": 0.02188 | |
| }, | |
| { | |
| "epoch": 0.7314285714285714, | |
| "grad_norm": 1.1539274454116821, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 5.888291835784912, | |
| "memory(GiB)": 12.53, | |
| "step": 8, | |
| "token_acc": 0.26814516129032256, | |
| "train_speed(iter/s)": 0.022058 | |
| }, | |
| { | |
| "epoch": 0.8228571428571428, | |
| "grad_norm": 0.5060173869132996, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 5.689397811889648, | |
| "memory(GiB)": 12.53, | |
| "step": 9, | |
| "token_acc": 0.3213166144200627, | |
| "train_speed(iter/s)": 0.022183 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.5739685297012329, | |
| "learning_rate": 0.0, | |
| "loss": 5.450071334838867, | |
| "memory(GiB)": 12.53, | |
| "step": 10, | |
| "token_acc": 0.2916666666666667, | |
| "train_speed(iter/s)": 0.02228 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "eval_loss": 6.169268608093262, | |
| "eval_runtime": 15.4702, | |
| "eval_samples_per_second": 4.719, | |
| "eval_steps_per_second": 0.646, | |
| "eval_token_acc": 0.32, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "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": 9393951731613696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |