| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9984, | |
| "eval_steps": 500, | |
| "global_step": 156, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.3039781153202057, | |
| "learning_rate": 2.9924022525939684e-05, | |
| "loss": 0.678, | |
| "num_input_tokens_seen": 163840, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.2683364450931549, | |
| "learning_rate": 2.9696859780634016e-05, | |
| "loss": 0.6551, | |
| "num_input_tokens_seen": 327680, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.246008038520813, | |
| "learning_rate": 2.9320812997628184e-05, | |
| "loss": 0.6372, | |
| "num_input_tokens_seen": 491520, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.23320266604423523, | |
| "learning_rate": 2.8799691654882365e-05, | |
| "loss": 0.6201, | |
| "num_input_tokens_seen": 655360, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.24441155791282654, | |
| "learning_rate": 2.8138774883503317e-05, | |
| "loss": 0.5965, | |
| "num_input_tokens_seen": 819200, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.2341088205575943, | |
| "learning_rate": 2.7344757988404845e-05, | |
| "loss": 0.5959, | |
| "num_input_tokens_seen": 983040, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.23481066524982452, | |
| "learning_rate": 2.6425684622660387e-05, | |
| "loss": 0.6006, | |
| "num_input_tokens_seen": 1146880, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.2456846982240677, | |
| "learning_rate": 2.5390865302643993e-05, | |
| "loss": 0.594, | |
| "num_input_tokens_seen": 1310720, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.25728079676628113, | |
| "learning_rate": 2.425078308942815e-05, | |
| "loss": 0.5825, | |
| "num_input_tokens_seen": 1474560, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.2505452334880829, | |
| "learning_rate": 2.3016987391917016e-05, | |
| "loss": 0.5871, | |
| "num_input_tokens_seen": 1638400, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.27519550919532776, | |
| "learning_rate": 2.1701976967524388e-05, | |
| "loss": 0.5771, | |
| "num_input_tokens_seen": 1802240, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.2705497741699219, | |
| "learning_rate": 2.0319073305638035e-05, | |
| "loss": 0.5544, | |
| "num_input_tokens_seen": 1966080, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.2861919701099396, | |
| "learning_rate": 1.888228567653781e-05, | |
| "loss": 0.5768, | |
| "num_input_tokens_seen": 2129920, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.29395216703414917, | |
| "learning_rate": 1.7406169212866405e-05, | |
| "loss": 0.5534, | |
| "num_input_tokens_seen": 2293760, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.285727322101593, | |
| "learning_rate": 1.5905677461334292e-05, | |
| "loss": 0.5597, | |
| "num_input_tokens_seen": 2457600, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.30645114183425903, | |
| "learning_rate": 1.4396010898358778e-05, | |
| "loss": 0.571, | |
| "num_input_tokens_seen": 2621440, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.2912521958351135, | |
| "learning_rate": 1.2892462944223613e-05, | |
| "loss": 0.5572, | |
| "num_input_tokens_seen": 2785280, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.3027022182941437, | |
| "learning_rate": 1.1410265035686639e-05, | |
| "loss": 0.5686, | |
| "num_input_tokens_seen": 2949120, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.32110294699668884, | |
| "learning_rate": 9.964432326500933e-06, | |
| "loss": 0.5525, | |
| "num_input_tokens_seen": 3112960, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.31834056973457336, | |
| "learning_rate": 8.569611578954186e-06, | |
| "loss": 0.5594, | |
| "num_input_tokens_seen": 3276800, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.3223641812801361, | |
| "learning_rate": 7.239932787335147e-06, | |
| "loss": 0.5709, | |
| "num_input_tokens_seen": 3440640, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.32236120104789734, | |
| "learning_rate": 5.988866036430314e-06, | |
| "loss": 0.5555, | |
| "num_input_tokens_seen": 3604480, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.32125550508499146, | |
| "learning_rate": 4.829085045121636e-06, | |
| "loss": 0.5597, | |
| "num_input_tokens_seen": 3768320, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.325810968875885, | |
| "learning_rate": 3.772338777433482e-06, | |
| "loss": 0.5432, | |
| "num_input_tokens_seen": 3932160, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.32014375925064087, | |
| "learning_rate": 2.829332421651404e-06, | |
| "loss": 0.5363, | |
| "num_input_tokens_seen": 4096000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.32001549005508423, | |
| "learning_rate": 2.0096189432334194e-06, | |
| "loss": 0.5582, | |
| "num_input_tokens_seen": 4259840, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.33245849609375, | |
| "learning_rate": 1.321502310118649e-06, | |
| "loss": 0.5539, | |
| "num_input_tokens_seen": 4423680, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.3493448495864868, | |
| "learning_rate": 7.719533707928178e-07, | |
| "loss": 0.5529, | |
| "num_input_tokens_seen": 4587520, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.3279431462287903, | |
| "learning_rate": 3.665392372935922e-07, | |
| "loss": 0.5584, | |
| "num_input_tokens_seen": 4751360, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3298741281032562, | |
| "learning_rate": 1.0936688852919042e-07, | |
| "loss": 0.5503, | |
| "num_input_tokens_seen": 4915200, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 0.33253204822540283, | |
| "learning_rate": 3.0415652272480776e-09, | |
| "loss": 0.5549, | |
| "num_input_tokens_seen": 5079040, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9984, | |
| "num_input_tokens_seen": 5111808, | |
| "step": 156, | |
| "total_flos": 2.1873318928633037e+17, | |
| "train_loss": 0.5760276004289969, | |
| "train_runtime": 1768.2955, | |
| "train_samples_per_second": 5.655, | |
| "train_steps_per_second": 0.088 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 156, | |
| "num_input_tokens_seen": 5111808, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1873318928633037e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |