| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008979347500748278, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000299311583358276, | |
| "grad_norm": 0.05946137011051178, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 10.3657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000299311583358276, | |
| "eval_loss": 10.365893363952637, | |
| "eval_runtime": 18.9886, | |
| "eval_samples_per_second": 74.097, | |
| "eval_steps_per_second": 18.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000598623166716552, | |
| "grad_norm": 0.05658948794007301, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 10.366, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008979347500748278, | |
| "grad_norm": 0.052172206342220306, | |
| "learning_rate": 6e-06, | |
| "loss": 10.3669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001197246333433104, | |
| "grad_norm": 0.05011365935206413, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 10.3677, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001197246333433104, | |
| "eval_loss": 10.365880012512207, | |
| "eval_runtime": 20.4682, | |
| "eval_samples_per_second": 68.741, | |
| "eval_steps_per_second": 17.197, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00149655791679138, | |
| "grad_norm": 0.06148688867688179, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017958695001496557, | |
| "grad_norm": 0.05421898886561394, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 10.3664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0020951810835079317, | |
| "grad_norm": 0.06663057208061218, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 10.366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002394492666866208, | |
| "grad_norm": 0.05399148538708687, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 10.3652, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002394492666866208, | |
| "eval_loss": 10.365796089172363, | |
| "eval_runtime": 20.18, | |
| "eval_samples_per_second": 69.723, | |
| "eval_steps_per_second": 17.443, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026938042502244837, | |
| "grad_norm": 0.0587196908891201, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 10.3655, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00299311583358276, | |
| "grad_norm": 0.05112240090966225, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 10.3677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032924274169410356, | |
| "grad_norm": 0.05123414471745491, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 10.3667, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0035917390002993114, | |
| "grad_norm": 0.059187568724155426, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 10.3661, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0035917390002993114, | |
| "eval_loss": 10.365715026855469, | |
| "eval_runtime": 20.3652, | |
| "eval_samples_per_second": 69.089, | |
| "eval_steps_per_second": 17.284, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0038910505836575876, | |
| "grad_norm": 0.05100542679429054, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 10.3675, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004190362167015863, | |
| "grad_norm": 0.05083156004548073, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 10.3669, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004489673750374139, | |
| "grad_norm": 0.057125844061374664, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 10.3649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004788985333732416, | |
| "grad_norm": 0.05517284944653511, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 10.3674, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004788985333732416, | |
| "eval_loss": 10.365657806396484, | |
| "eval_runtime": 20.3282, | |
| "eval_samples_per_second": 69.214, | |
| "eval_steps_per_second": 17.316, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0050882969170906915, | |
| "grad_norm": 0.0575844943523407, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 10.3663, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005387608500448967, | |
| "grad_norm": 0.05611433461308479, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 10.3675, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005686920083807243, | |
| "grad_norm": 0.05365666002035141, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 10.3664, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00598623166716552, | |
| "grad_norm": 0.05828257277607918, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 10.3639, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00598623166716552, | |
| "eval_loss": 10.365618705749512, | |
| "eval_runtime": 20.3165, | |
| "eval_samples_per_second": 69.254, | |
| "eval_steps_per_second": 17.326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0062855432505237955, | |
| "grad_norm": 0.05960177257657051, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 10.3644, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006584854833882071, | |
| "grad_norm": 0.050702810287475586, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 10.3665, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006884166417240347, | |
| "grad_norm": 0.05289774015545845, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 10.3656, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007183478000598623, | |
| "grad_norm": 0.061270881444215775, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 10.365, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007183478000598623, | |
| "eval_loss": 10.365599632263184, | |
| "eval_runtime": 19.9383, | |
| "eval_samples_per_second": 70.568, | |
| "eval_steps_per_second": 17.654, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0074827895839568994, | |
| "grad_norm": 0.053589362651109695, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 10.3649, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007782101167315175, | |
| "grad_norm": 0.05652034282684326, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 10.3647, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008081412750673452, | |
| "grad_norm": 0.05931362509727478, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 10.3637, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008380724334031727, | |
| "grad_norm": 0.055247027426958084, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 10.3635, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008380724334031727, | |
| "eval_loss": 10.365592956542969, | |
| "eval_runtime": 20.3235, | |
| "eval_samples_per_second": 69.23, | |
| "eval_steps_per_second": 17.32, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008680035917390003, | |
| "grad_norm": 0.05701150745153427, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 10.3639, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008979347500748278, | |
| "grad_norm": 0.055218130350112915, | |
| "learning_rate": 0.0, | |
| "loss": 10.3632, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1569073397760.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |