| { | |
| "best_metric": 2.1166605949401855, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.0125786163522013, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08050314465408805, | |
| "grad_norm": 0.6034995913505554, | |
| "learning_rate": 0.0002989354846774545, | |
| "loss": 2.6016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08050314465408805, | |
| "eval_loss": 2.547182321548462, | |
| "eval_runtime": 0.2907, | |
| "eval_samples_per_second": 171.983, | |
| "eval_steps_per_second": 44.716, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1610062893081761, | |
| "grad_norm": 0.47087833285331726, | |
| "learning_rate": 0.0002957587267523652, | |
| "loss": 2.613, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24150943396226415, | |
| "grad_norm": 0.537595808506012, | |
| "learning_rate": 0.00029051982559491393, | |
| "loss": 2.6825, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3220125786163522, | |
| "grad_norm": 0.46131274104118347, | |
| "learning_rate": 0.00028330140180592156, | |
| "loss": 2.4223, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4025157232704403, | |
| "grad_norm": 0.3705180883407593, | |
| "learning_rate": 0.00027421729424061787, | |
| "loss": 2.4515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4830188679245283, | |
| "grad_norm": 0.4309248626232147, | |
| "learning_rate": 0.0002634107647018905, | |
| "loss": 2.5544, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5635220125786163, | |
| "grad_norm": 0.5281741619110107, | |
| "learning_rate": 0.00025105223861607306, | |
| "loss": 2.3864, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6440251572327044, | |
| "grad_norm": 0.4097701907157898, | |
| "learning_rate": 0.00023733661732216452, | |
| "loss": 2.3523, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7245283018867924, | |
| "grad_norm": 0.38945168256759644, | |
| "learning_rate": 0.00022248020436128478, | |
| "loss": 2.4146, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8050314465408805, | |
| "grad_norm": 0.3679025173187256, | |
| "learning_rate": 0.00020671729424061788, | |
| "loss": 2.4092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8855345911949686, | |
| "grad_norm": 0.3378962576389313, | |
| "learning_rate": 0.00019029647746907283, | |
| "loss": 2.2826, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9660377358490566, | |
| "grad_norm": 0.5190917253494263, | |
| "learning_rate": 0.0001734767201364573, | |
| "loss": 2.3413, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0465408805031446, | |
| "grad_norm": 0.7958456873893738, | |
| "learning_rate": 0.0001565232798635427, | |
| "loss": 3.9815, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1270440251572327, | |
| "grad_norm": 0.5557073950767517, | |
| "learning_rate": 0.00013970352253092714, | |
| "loss": 2.1314, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2075471698113207, | |
| "grad_norm": 0.7198206186294556, | |
| "learning_rate": 0.00012328270575938212, | |
| "loss": 2.3228, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2880503144654087, | |
| "grad_norm": 0.5077990889549255, | |
| "learning_rate": 0.00010751979563871518, | |
| "loss": 2.3659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.3685534591194968, | |
| "grad_norm": 0.49712374806404114, | |
| "learning_rate": 9.266338267783541e-05, | |
| "loss": 2.1345, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.449056603773585, | |
| "grad_norm": 0.32097068428993225, | |
| "learning_rate": 7.894776138392688e-05, | |
| "loss": 2.2236, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.529559748427673, | |
| "grad_norm": 0.3021276891231537, | |
| "learning_rate": 6.658923529810946e-05, | |
| "loss": 2.3423, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.610062893081761, | |
| "grad_norm": 0.4367467761039734, | |
| "learning_rate": 5.578270575938211e-05, | |
| "loss": 2.0804, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6905660377358491, | |
| "grad_norm": 0.26613855361938477, | |
| "learning_rate": 4.669859819407844e-05, | |
| "loss": 2.3269, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.7710691823899372, | |
| "grad_norm": 0.4290255308151245, | |
| "learning_rate": 3.948017440508607e-05, | |
| "loss": 2.3011, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.8515723270440252, | |
| "grad_norm": 0.24024897813796997, | |
| "learning_rate": 3.4241273247634805e-05, | |
| "loss": 2.0737, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.9320754716981132, | |
| "grad_norm": 0.3076782524585724, | |
| "learning_rate": 3.10645153225455e-05, | |
| "loss": 2.2157, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0125786163522013, | |
| "grad_norm": 0.45735964179039, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.6545, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0125786163522013, | |
| "eval_loss": 2.1166605949401855, | |
| "eval_runtime": 0.2883, | |
| "eval_samples_per_second": 173.43, | |
| "eval_steps_per_second": 45.092, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": 1.11070068867072e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |