| { | |
| "best_metric": 3.2138640880584717, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.06042296072507553, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002014098690835851, | |
| "eval_loss": 4.046324729919434, | |
| "eval_runtime": 3.3502, | |
| "eval_samples_per_second": 62.684, | |
| "eval_steps_per_second": 31.342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006042296072507553, | |
| "grad_norm": 1.7598676681518555, | |
| "learning_rate": 0.00012, | |
| "loss": 16.3005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010070493454179255, | |
| "eval_loss": 4.011149883270264, | |
| "eval_runtime": 3.3537, | |
| "eval_samples_per_second": 62.618, | |
| "eval_steps_per_second": 31.309, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012084592145015106, | |
| "grad_norm": 1.6913790702819824, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 15.909, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01812688821752266, | |
| "grad_norm": 2.3050012588500977, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 15.9939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02014098690835851, | |
| "eval_loss": 3.7587292194366455, | |
| "eval_runtime": 3.3702, | |
| "eval_samples_per_second": 62.311, | |
| "eval_steps_per_second": 31.155, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02416918429003021, | |
| "grad_norm": 2.7639949321746826, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 15.4059, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030211480362537766, | |
| "grad_norm": 2.826650857925415, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 14.5314, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030211480362537766, | |
| "eval_loss": 3.493231773376465, | |
| "eval_runtime": 3.389, | |
| "eval_samples_per_second": 61.964, | |
| "eval_steps_per_second": 30.982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03625377643504532, | |
| "grad_norm": 2.270655870437622, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 13.6001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04028197381671702, | |
| "eval_loss": 3.3178932666778564, | |
| "eval_runtime": 3.3642, | |
| "eval_samples_per_second": 62.422, | |
| "eval_steps_per_second": 31.211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04229607250755287, | |
| "grad_norm": 2.6858649253845215, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 13.4503, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04833836858006042, | |
| "grad_norm": 2.5652761459350586, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 12.9221, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.050352467270896276, | |
| "eval_loss": 3.234055757522583, | |
| "eval_runtime": 3.3732, | |
| "eval_samples_per_second": 62.256, | |
| "eval_steps_per_second": 31.128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.054380664652567974, | |
| "grad_norm": 2.6937625408172607, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 12.7559, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06042296072507553, | |
| "grad_norm": 2.1777639389038086, | |
| "learning_rate": 0.0, | |
| "loss": 12.2795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06042296072507553, | |
| "eval_loss": 3.2138640880584717, | |
| "eval_runtime": 3.3794, | |
| "eval_samples_per_second": 62.142, | |
| "eval_steps_per_second": 31.071, | |
| "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": 130370638970880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |