| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9888412017167383, |
| "eval_steps": 500, |
| "global_step": 216, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13733905579399142, |
| "grad_norm": 0.27025100588798523, |
| "learning_rate": 4.0909090909090915e-05, |
| "loss": 0.3649, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.27467811158798283, |
| "grad_norm": 0.11594237387180328, |
| "learning_rate": 4.9812354578598874e-05, |
| "loss": 0.2691, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.41201716738197425, |
| "grad_norm": 0.10208791494369507, |
| "learning_rate": 4.905487021607461e-05, |
| "loss": 0.243, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5493562231759657, |
| "grad_norm": 0.09452749043703079, |
| "learning_rate": 4.773356008364812e-05, |
| "loss": 0.2153, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6866952789699571, |
| "grad_norm": 0.09533349424600601, |
| "learning_rate": 4.587939457093295e-05, |
| "loss": 0.2063, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8240343347639485, |
| "grad_norm": 0.10009749233722687, |
| "learning_rate": 4.353583374602933e-05, |
| "loss": 0.1957, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9613733905579399, |
| "grad_norm": 0.16674572229385376, |
| "learning_rate": 4.0757808688362954e-05, |
| "loss": 0.1897, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.109871244635193, |
| "grad_norm": 0.1086713895201683, |
| "learning_rate": 3.7610433950740665e-05, |
| "loss": 0.1845, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2472103004291846, |
| "grad_norm": 0.0993642583489418, |
| "learning_rate": 3.4167481329421206e-05, |
| "loss": 0.1439, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.384549356223176, |
| "grad_norm": 0.08131585270166397, |
| "learning_rate": 3.0509650715736976e-05, |
| "loss": 0.1454, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5218884120171674, |
| "grad_norm": 0.08821457624435425, |
| "learning_rate": 2.6722678559039272e-05, |
| "loss": 0.1357, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6592274678111587, |
| "grad_norm": 0.08488401770591736, |
| "learning_rate": 2.2895328276992324e-05, |
| "loss": 0.1333, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7965665236051502, |
| "grad_norm": 0.09474518895149231, |
| "learning_rate": 1.911730971629566e-05, |
| "loss": 0.1277, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.9339055793991418, |
| "grad_norm": 0.0876115933060646, |
| "learning_rate": 1.5477176429911934e-05, |
| "loss": 0.1212, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.082403433476395, |
| "grad_norm": 0.083305723965168, |
| "learning_rate": 1.2060250056840089e-05, |
| "loss": 0.117, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.219742489270386, |
| "grad_norm": 0.0787946954369545, |
| "learning_rate": 8.946620455212438e-06, |
| "loss": 0.0876, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.3570815450643776, |
| "grad_norm": 0.08819948136806488, |
| "learning_rate": 6.209268463901047e-06, |
| "loss": 0.0865, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.494420600858369, |
| "grad_norm": 0.0846785455942154, |
| "learning_rate": 3.912355293510298e-06, |
| "loss": 0.087, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.6317596566523607, |
| "grad_norm": 0.07895786315202713, |
| "learning_rate": 2.109718641980815e-06, |
| "loss": 0.0844, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.769098712446352, |
| "grad_norm": 0.07565450668334961, |
| "learning_rate": 8.436107845804842e-07, |
| "loss": 0.0863, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.9064377682403433, |
| "grad_norm": 0.07621210813522339, |
| "learning_rate": 1.437082163835035e-07, |
| "loss": 0.0849, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.9888412017167383, |
| "step": 216, |
| "total_flos": 6237706816323584.0, |
| "train_loss": 0.15508435997698042, |
| "train_runtime": 58329.4214, |
| "train_samples_per_second": 1.917, |
| "train_steps_per_second": 0.004 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 216, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6237706816323584.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
