| { | |
| "best_metric": 1.2864845991134644, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0033690735889898675, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.684536794494934e-05, | |
| "eval_loss": 1.7877610921859741, | |
| "eval_runtime": 1523.965, | |
| "eval_samples_per_second": 16.401, | |
| "eval_steps_per_second": 4.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016845367944949338, | |
| "grad_norm": 2.426577091217041, | |
| "learning_rate": 4.34e-05, | |
| "loss": 1.3885, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00033690735889898676, | |
| "grad_norm": 1.8919321298599243, | |
| "learning_rate": 8.68e-05, | |
| "loss": 1.2056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005053610383484802, | |
| "grad_norm": 1.6490509510040283, | |
| "learning_rate": 0.0001302, | |
| "loss": 1.1562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006738147177979735, | |
| "grad_norm": 1.9635969400405884, | |
| "learning_rate": 0.0001736, | |
| "loss": 1.2593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008422683972474669, | |
| "grad_norm": 2.6593801975250244, | |
| "learning_rate": 0.000217, | |
| "loss": 1.4405, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008422683972474669, | |
| "eval_loss": 1.2864845991134644, | |
| "eval_runtime": 1523.8808, | |
| "eval_samples_per_second": 16.402, | |
| "eval_steps_per_second": 4.101, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010107220766969603, | |
| "grad_norm": 1.269593596458435, | |
| "learning_rate": 0.00021673569945319091, | |
| "loss": 1.118, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0011791757561464536, | |
| "grad_norm": 1.360644817352295, | |
| "learning_rate": 0.00021594408545846038, | |
| "loss": 1.1112, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.001347629435595947, | |
| "grad_norm": 1.5711684226989746, | |
| "learning_rate": 0.0002146290146796179, | |
| "loss": 1.2133, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0015160831150454403, | |
| "grad_norm": 2.1071293354034424, | |
| "learning_rate": 0.0002127968940093076, | |
| "loss": 1.3488, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0016845367944949338, | |
| "grad_norm": 3.1953670978546143, | |
| "learning_rate": 0.00021045664935527106, | |
| "loss": 1.4487, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0016845367944949338, | |
| "eval_loss": 1.4198808670043945, | |
| "eval_runtime": 1523.9284, | |
| "eval_samples_per_second": 16.402, | |
| "eval_steps_per_second": 4.101, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0018529904739444272, | |
| "grad_norm": 1.4960129261016846, | |
| "learning_rate": 0.00020761968215422217, | |
| "loss": 1.1833, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0020214441533939207, | |
| "grad_norm": 1.6748398542404175, | |
| "learning_rate": 0.00020429981382519356, | |
| "loss": 1.1911, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0021898978328434137, | |
| "grad_norm": 1.67674720287323, | |
| "learning_rate": 0.00020051321843297219, | |
| "loss": 1.166, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.002358351512292907, | |
| "grad_norm": 1.8275052309036255, | |
| "learning_rate": 0.0001962783438896818, | |
| "loss": 1.2584, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0025268051917424006, | |
| "grad_norm": 3.4226462841033936, | |
| "learning_rate": 0.0001916158220784091, | |
| "loss": 1.4667, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0025268051917424006, | |
| "eval_loss": 1.3877193927764893, | |
| "eval_runtime": 1524.1947, | |
| "eval_samples_per_second": 16.399, | |
| "eval_steps_per_second": 4.1, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.002695258871191894, | |
| "grad_norm": 1.4711071252822876, | |
| "learning_rate": 0.00018654836833674362, | |
| "loss": 1.2392, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0028637125506413875, | |
| "grad_norm": 1.2519170045852661, | |
| "learning_rate": 0.0001811006707899361, | |
| "loss": 1.1692, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0030321662300908806, | |
| "grad_norm": 1.6822906732559204, | |
| "learning_rate": 0.0001752992700728339, | |
| "loss": 1.2182, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.003200619909540374, | |
| "grad_norm": 1.8712016344070435, | |
| "learning_rate": 0.00016917243002657602, | |
| "loss": 1.2522, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0033690735889898675, | |
| "grad_norm": 4.799688339233398, | |
| "learning_rate": 0.00016275, | |
| "loss": 1.4872, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0033690735889898675, | |
| "eval_loss": 1.3280550241470337, | |
| "eval_runtime": 1524.6163, | |
| "eval_samples_per_second": 16.394, | |
| "eval_steps_per_second": 4.099, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.790140366598963e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |