| { | |
| "best_metric": 4.0032172203063965, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01631787214947171, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006527148859788684, | |
| "grad_norm": 0.8191147446632385, | |
| "learning_rate": 1e-05, | |
| "loss": 4.5952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006527148859788684, | |
| "eval_loss": 4.644200325012207, | |
| "eval_runtime": 162.2369, | |
| "eval_samples_per_second": 63.623, | |
| "eval_steps_per_second": 7.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013054297719577368, | |
| "grad_norm": 0.8031899333000183, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001958144657936605, | |
| "grad_norm": 0.8169269561767578, | |
| "learning_rate": 3e-05, | |
| "loss": 4.6883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026108595439154735, | |
| "grad_norm": 0.7823262810707092, | |
| "learning_rate": 4e-05, | |
| "loss": 4.547, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003263574429894342, | |
| "grad_norm": 0.8156715035438538, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00391628931587321, | |
| "grad_norm": 0.7746463418006897, | |
| "learning_rate": 6e-05, | |
| "loss": 4.485, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004569004201852078, | |
| "grad_norm": 0.6617835760116577, | |
| "learning_rate": 7e-05, | |
| "loss": 4.4756, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005221719087830947, | |
| "grad_norm": 0.5175589323043823, | |
| "learning_rate": 8e-05, | |
| "loss": 4.4369, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005874433973809815, | |
| "grad_norm": 0.3726535439491272, | |
| "learning_rate": 9e-05, | |
| "loss": 4.3528, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006527148859788684, | |
| "grad_norm": 0.575859785079956, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3215, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007179863745767552, | |
| "grad_norm": 0.7978506088256836, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 4.3095, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00783257863174642, | |
| "grad_norm": 0.8266698718070984, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 4.3506, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00848529351772529, | |
| "grad_norm": 0.6456958055496216, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 4.2903, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009138008403704156, | |
| "grad_norm": 0.4962930679321289, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.2426, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009790723289683025, | |
| "grad_norm": 0.4060556888580322, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010443438175661894, | |
| "grad_norm": 0.3522457182407379, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 4.1726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011096153061640763, | |
| "grad_norm": 0.36963698267936707, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 4.1933, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01174886794761963, | |
| "grad_norm": 0.3324430286884308, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.0834, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012401582833598499, | |
| "grad_norm": 0.33209967613220215, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 4.1266, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013054297719577368, | |
| "grad_norm": 0.3280082046985626, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.0839, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013707012605556235, | |
| "grad_norm": 0.32346111536026, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 4.0942, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014359727491535103, | |
| "grad_norm": 0.3204044997692108, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 4.0493, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015012442377513972, | |
| "grad_norm": 0.31801706552505493, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 4.0828, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01566515726349284, | |
| "grad_norm": 0.305008202791214, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 4.0288, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01631787214947171, | |
| "grad_norm": 0.2867254316806793, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.0314, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01631787214947171, | |
| "eval_loss": 4.0032172203063965, | |
| "eval_runtime": 162.334, | |
| "eval_samples_per_second": 63.585, | |
| "eval_steps_per_second": 7.953, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.133205889869414e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |