| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.0025437201907790143, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001271860095389507, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001271860095389507, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1062.8612, | |
| "eval_samples_per_second": 3.115, | |
| "eval_steps_per_second": 1.558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002543720190779014, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00038155802861685216, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005087440381558028, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006359300476947536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.275, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006359300476947536, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1054.8107, | |
| "eval_samples_per_second": 3.139, | |
| "eval_steps_per_second": 1.57, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007631160572337043, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000890302066772655, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010174880763116057, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011446740858505565, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012718600953895071, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012718600953895071, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1050.8878, | |
| "eval_samples_per_second": 3.151, | |
| "eval_steps_per_second": 1.576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013990461049284578, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0015262321144674086, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016534181240063592, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00178060413354531, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0019077901430842607, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0019077901430842607, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1063.3358, | |
| "eval_samples_per_second": 3.114, | |
| "eval_steps_per_second": 1.557, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0020349761526232114, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002162162162162162, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002289348171701113, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024165341812400635, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0025437201907790143, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.0129, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025437201907790143, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1063.2189, | |
| "eval_samples_per_second": 3.114, | |
| "eval_steps_per_second": 1.558, | |
| "step": 20 | |
| } | |
| ], | |
| "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": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7010683170324480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |