| { | |
| "best_metric": 0.7834388131116452, | |
| "best_model_checkpoint": "nuc_arg_short_read/checkpoint-1000", | |
| "epoch": 0.6024244914731868, | |
| "eval_steps": 100, | |
| "global_step": 1466, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04109307581672488, | |
| "grad_norm": 31.502859115600586, | |
| "learning_rate": 3.2612551159618005e-05, | |
| "loss": 1.082, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04109307581672488, | |
| "eval_loss": 1.110230803489685, | |
| "eval_macro_f1_score": 0.231015523052847, | |
| "eval_micro_f1_score": 0.6498612395929695, | |
| "eval_runtime": 65.9015, | |
| "eval_samples_per_second": 131.302, | |
| "eval_steps_per_second": 16.418, | |
| "eval_weighted_f1_score": 0.635148001778528, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08218615163344976, | |
| "grad_norm": 20.506277084350586, | |
| "learning_rate": 3.0225102319236013e-05, | |
| "loss": 0.9583, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08218615163344976, | |
| "eval_loss": 1.0097736120224, | |
| "eval_macro_f1_score": 0.2658630277675259, | |
| "eval_micro_f1_score": 0.6996993524514339, | |
| "eval_runtime": 65.8265, | |
| "eval_samples_per_second": 131.452, | |
| "eval_steps_per_second": 16.437, | |
| "eval_weighted_f1_score": 0.6867369276159828, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12327922745017464, | |
| "grad_norm": 38.54680252075195, | |
| "learning_rate": 2.7837653478854025e-05, | |
| "loss": 0.8617, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12327922745017464, | |
| "eval_loss": 0.9992199540138245, | |
| "eval_macro_f1_score": 0.2775563277122497, | |
| "eval_micro_f1_score": 0.7024745605920444, | |
| "eval_runtime": 65.7273, | |
| "eval_samples_per_second": 131.65, | |
| "eval_steps_per_second": 16.462, | |
| "eval_weighted_f1_score": 0.6940687878434678, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16437230326689953, | |
| "grad_norm": 31.71833038330078, | |
| "learning_rate": 2.545020463847203e-05, | |
| "loss": 0.8274, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.16437230326689953, | |
| "eval_loss": 0.9398019909858704, | |
| "eval_macro_f1_score": 0.2873778821158207, | |
| "eval_micro_f1_score": 0.7252543940795559, | |
| "eval_runtime": 65.782, | |
| "eval_samples_per_second": 131.541, | |
| "eval_steps_per_second": 16.448, | |
| "eval_weighted_f1_score": 0.7146058315338393, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.20546537908362442, | |
| "grad_norm": 35.85011291503906, | |
| "learning_rate": 2.306275579809004e-05, | |
| "loss": 0.8531, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.20546537908362442, | |
| "eval_loss": 0.8932695388793945, | |
| "eval_macro_f1_score": 0.2954866176285143, | |
| "eval_micro_f1_score": 0.741327474560592, | |
| "eval_runtime": 65.7129, | |
| "eval_samples_per_second": 131.679, | |
| "eval_steps_per_second": 16.466, | |
| "eval_weighted_f1_score": 0.7279810893615292, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24655845490034928, | |
| "grad_norm": 20.54347801208496, | |
| "learning_rate": 2.0675306957708046e-05, | |
| "loss": 0.9093, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.24655845490034928, | |
| "eval_loss": 0.8818169236183167, | |
| "eval_macro_f1_score": 0.30056528194912985, | |
| "eval_micro_f1_score": 0.7472247918593895, | |
| "eval_runtime": 65.7581, | |
| "eval_samples_per_second": 131.588, | |
| "eval_steps_per_second": 16.454, | |
| "eval_weighted_f1_score": 0.7317018335209305, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.28765153071707417, | |
| "grad_norm": 32.46955108642578, | |
| "learning_rate": 1.8287858117326057e-05, | |
| "loss": 0.8248, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.28765153071707417, | |
| "eval_loss": 0.8534889817237854, | |
| "eval_macro_f1_score": 0.32642004813212766, | |
| "eval_micro_f1_score": 0.7561285846438482, | |
| "eval_runtime": 65.8232, | |
| "eval_samples_per_second": 131.458, | |
| "eval_steps_per_second": 16.438, | |
| "eval_weighted_f1_score": 0.7458471048255579, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.32874460653379906, | |
| "grad_norm": 25.37872886657715, | |
| "learning_rate": 1.5900409276944065e-05, | |
| "loss": 0.8564, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.32874460653379906, | |
| "eval_loss": 0.8019793033599854, | |
| "eval_macro_f1_score": 0.3347865283632992, | |
| "eval_micro_f1_score": 0.7738205365402405, | |
| "eval_runtime": 65.8491, | |
| "eval_samples_per_second": 131.407, | |
| "eval_steps_per_second": 16.432, | |
| "eval_weighted_f1_score": 0.7628080012858742, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.36983768235052394, | |
| "grad_norm": 28.011754989624023, | |
| "learning_rate": 1.3512960436562072e-05, | |
| "loss": 0.8075, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.36983768235052394, | |
| "eval_loss": 0.7745345234870911, | |
| "eval_macro_f1_score": 0.35349283320361347, | |
| "eval_micro_f1_score": 0.7870027752081407, | |
| "eval_runtime": 65.798, | |
| "eval_samples_per_second": 131.508, | |
| "eval_steps_per_second": 16.444, | |
| "eval_weighted_f1_score": 0.7762822583099493, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.41093075816724883, | |
| "grad_norm": 19.038227081298828, | |
| "learning_rate": 1.112551159618008e-05, | |
| "loss": 0.7665, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.41093075816724883, | |
| "eval_loss": 0.7573076486587524, | |
| "eval_macro_f1_score": 0.34864536541081076, | |
| "eval_micro_f1_score": 0.7922062904717854, | |
| "eval_runtime": 65.947, | |
| "eval_samples_per_second": 131.212, | |
| "eval_steps_per_second": 16.407, | |
| "eval_weighted_f1_score": 0.7834388131116452, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4520238339839737, | |
| "grad_norm": 26.79417610168457, | |
| "learning_rate": 8.73806275579809e-06, | |
| "loss": 0.7955, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.4520238339839737, | |
| "eval_loss": 0.7447549700737, | |
| "eval_macro_f1_score": 0.372113449187476, | |
| "eval_micro_f1_score": 0.794981498612396, | |
| "eval_runtime": 65.765, | |
| "eval_samples_per_second": 131.575, | |
| "eval_steps_per_second": 16.453, | |
| "eval_weighted_f1_score": 0.7855680502155937, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.49311690980069856, | |
| "grad_norm": 31.958662033081055, | |
| "learning_rate": 6.350613915416098e-06, | |
| "loss": 0.7154, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.49311690980069856, | |
| "eval_loss": 0.7216053009033203, | |
| "eval_macro_f1_score": 0.37899321696255506, | |
| "eval_micro_f1_score": 0.8055041628122109, | |
| "eval_runtime": 65.8483, | |
| "eval_samples_per_second": 131.408, | |
| "eval_steps_per_second": 16.432, | |
| "eval_weighted_f1_score": 0.795726477960455, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5342099856174235, | |
| "grad_norm": 14.647438049316406, | |
| "learning_rate": 3.963165075034106e-06, | |
| "loss": 0.7072, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5342099856174235, | |
| "eval_loss": 0.7128139734268188, | |
| "eval_macro_f1_score": 0.38961014388267884, | |
| "eval_micro_f1_score": 0.8093200740055504, | |
| "eval_runtime": 65.8124, | |
| "eval_samples_per_second": 131.48, | |
| "eval_steps_per_second": 16.441, | |
| "eval_weighted_f1_score": 0.8020259006536976, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5753030614341483, | |
| "grad_norm": 25.068248748779297, | |
| "learning_rate": 1.5757162346521146e-06, | |
| "loss": 0.7256, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5753030614341483, | |
| "eval_loss": 0.7055332064628601, | |
| "eval_macro_f1_score": 0.3934822923181016, | |
| "eval_micro_f1_score": 0.8125578168362627, | |
| "eval_runtime": 65.9442, | |
| "eval_samples_per_second": 131.217, | |
| "eval_steps_per_second": 16.408, | |
| "eval_weighted_f1_score": 0.8039225388312238, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1466, | |
| "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": 2607458880921600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |