| { | |
| "best_metric": 2.4247772693634033, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004064049418840933, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 1.3102930784225464, | |
| "learning_rate": 1e-05, | |
| "loss": 2.5034, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 2.5899617671966553, | |
| "eval_runtime": 87.9532, | |
| "eval_samples_per_second": 29.459, | |
| "eval_steps_per_second": 14.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 4.005129814147949, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4215, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 0.5886170864105225, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3631, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 5.3746018409729, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7237, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 0.6165680289268494, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5038, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "eval_loss": 2.5809969902038574, | |
| "eval_runtime": 88.775, | |
| "eval_samples_per_second": 29.186, | |
| "eval_steps_per_second": 14.599, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 12.503352165222168, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7031, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 0.42984622716903687, | |
| "learning_rate": 7e-05, | |
| "loss": 2.2362, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 5.048691749572754, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6304, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 0.43629446625709534, | |
| "learning_rate": 9e-05, | |
| "loss": 2.2568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 0.5820720791816711, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "eval_loss": 2.4975101947784424, | |
| "eval_runtime": 89.4687, | |
| "eval_samples_per_second": 28.96, | |
| "eval_steps_per_second": 14.486, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017881817442900105, | |
| "grad_norm": 0.4097574055194855, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.3559, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 1.6412928104400635, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.2916, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002113305697797285, | |
| "grad_norm": 1.0803278684616089, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.6974, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022758676745509225, | |
| "grad_norm": 0.5715447664260864, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.2765, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 0.769822895526886, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4568, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "eval_loss": 2.4460976123809814, | |
| "eval_runtime": 82.9489, | |
| "eval_samples_per_second": 31.236, | |
| "eval_steps_per_second": 15.624, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "grad_norm": 0.35771793127059937, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.2896, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027635536048118345, | |
| "grad_norm": 0.7394500970840454, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.4351, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 0.6383208632469177, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.4734, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003088677558319109, | |
| "grad_norm": 0.6234631538391113, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.4718, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 1.1141939163208008, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4053, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "eval_loss": 2.427879810333252, | |
| "eval_runtime": 84.8025, | |
| "eval_samples_per_second": 30.553, | |
| "eval_steps_per_second": 15.283, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003413801511826384, | |
| "grad_norm": 0.4734785258769989, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003576363488580021, | |
| "grad_norm": 0.908765971660614, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.4109, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037389254653336585, | |
| "grad_norm": 0.9276166558265686, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.1517, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 0.4119308292865753, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.4889, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "grad_norm": 0.4042227864265442, | |
| "learning_rate": 0.0, | |
| "loss": 2.3042, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "eval_loss": 2.4247772693634033, | |
| "eval_runtime": 91.9005, | |
| "eval_samples_per_second": 28.194, | |
| "eval_steps_per_second": 14.102, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 144886448259072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |