| { | |
| "best_metric": 10.827816009521484, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.0016205923264953342, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.4019744216511136e-05, | |
| "eval_loss": 10.839302062988281, | |
| "eval_runtime": 40.6851, | |
| "eval_samples_per_second": 191.593, | |
| "eval_steps_per_second": 95.809, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016205923264953342, | |
| "grad_norm": 0.13279838860034943, | |
| "learning_rate": 6e-05, | |
| "loss": 10.838, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002700987210825557, | |
| "eval_loss": 10.838739395141602, | |
| "eval_runtime": 40.228, | |
| "eval_samples_per_second": 193.771, | |
| "eval_steps_per_second": 96.898, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00032411846529906683, | |
| "grad_norm": 0.11057035624980927, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8342, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004861776979486002, | |
| "grad_norm": 0.10826054960489273, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8383, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005401974421651113, | |
| "eval_loss": 10.836539268493652, | |
| "eval_runtime": 40.3119, | |
| "eval_samples_per_second": 193.367, | |
| "eval_steps_per_second": 96.696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006482369305981337, | |
| "grad_norm": 0.11939119547605515, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.8375, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008102961632476671, | |
| "grad_norm": 0.1792188137769699, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.8329, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008102961632476671, | |
| "eval_loss": 10.833067893981934, | |
| "eval_runtime": 40.3375, | |
| "eval_samples_per_second": 193.244, | |
| "eval_steps_per_second": 96.635, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009723553958972004, | |
| "grad_norm": 0.16819672286510468, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.8347, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010803948843302227, | |
| "eval_loss": 10.82991886138916, | |
| "eval_runtime": 40.4851, | |
| "eval_samples_per_second": 192.54, | |
| "eval_steps_per_second": 96.282, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011344146285467338, | |
| "grad_norm": 0.14477704465389252, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.8313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0012964738611962673, | |
| "grad_norm": 0.14507289230823517, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.8301, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013504936054127784, | |
| "eval_loss": 10.828169822692871, | |
| "eval_runtime": 43.1769, | |
| "eval_samples_per_second": 180.536, | |
| "eval_steps_per_second": 90.28, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014585330938458006, | |
| "grad_norm": 0.13749462366104126, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.8264, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0016205923264953342, | |
| "grad_norm": 0.15239441394805908, | |
| "learning_rate": 0.0, | |
| "loss": 10.826, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016205923264953342, | |
| "eval_loss": 10.827816009521484, | |
| "eval_runtime": 40.5608, | |
| "eval_samples_per_second": 192.181, | |
| "eval_steps_per_second": 96.103, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 5074321932288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |