| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9968186638388123, | |
| "eval_steps": 500, | |
| "global_step": 235, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.042417815482502653, | |
| "grad_norm": 0.8155243915035402, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.6415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08483563096500531, | |
| "grad_norm": 0.3724018495341306, | |
| "learning_rate": 9.975707393083328e-06, | |
| "loss": 0.4089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12725344644750794, | |
| "grad_norm": 0.28463462503464637, | |
| "learning_rate": 9.85729110226596e-06, | |
| "loss": 0.3616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16967126193001061, | |
| "grad_norm": 0.297538920144775, | |
| "learning_rate": 9.642632564563576e-06, | |
| "loss": 0.3331, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21208907741251326, | |
| "grad_norm": 0.2991153079080703, | |
| "learning_rate": 9.33598501898256e-06, | |
| "loss": 0.3282, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2545068928950159, | |
| "grad_norm": 0.2618563036667496, | |
| "learning_rate": 8.943424372477455e-06, | |
| "loss": 0.305, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29692470837751855, | |
| "grad_norm": 0.2945290407529977, | |
| "learning_rate": 8.472728812079436e-06, | |
| "loss": 0.3293, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33934252386002123, | |
| "grad_norm": 0.2686931795972466, | |
| "learning_rate": 7.933224688089059e-06, | |
| "loss": 0.3093, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.38176033934252385, | |
| "grad_norm": 0.24826628745526108, | |
| "learning_rate": 7.3356017219999236e-06, | |
| "loss": 0.2981, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4241781548250265, | |
| "grad_norm": 0.2770179971302181, | |
| "learning_rate": 6.691701200618925e-06, | |
| "loss": 0.2925, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46659597030752914, | |
| "grad_norm": 0.2581961736174019, | |
| "learning_rate": 6.014281353099601e-06, | |
| "loss": 0.2999, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5090137857900318, | |
| "grad_norm": 0.2686100147543252, | |
| "learning_rate": 5.3167645597022855e-06, | |
| "loss": 0.3111, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5514316012725344, | |
| "grad_norm": 1.1286877967357856, | |
| "learning_rate": 4.612971401080521e-06, | |
| "loss": 0.2747, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5938494167550371, | |
| "grad_norm": 0.27687544341997167, | |
| "learning_rate": 3.916846817634618e-06, | |
| "loss": 0.2929, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6362672322375398, | |
| "grad_norm": 0.27713605473267083, | |
| "learning_rate": 3.2421838048042516e-06, | |
| "loss": 0.291, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6786850477200425, | |
| "grad_norm": 0.2658744274079011, | |
| "learning_rate": 2.602350118994782e-06, | |
| "loss": 0.2846, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.721102863202545, | |
| "grad_norm": 0.2771317958447051, | |
| "learning_rate": 2.0100234091793778e-06, | |
| "loss": 0.2883, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7635206786850477, | |
| "grad_norm": 0.26274869656822974, | |
| "learning_rate": 1.4769400222728974e-06, | |
| "loss": 0.2904, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8059384941675504, | |
| "grad_norm": 0.25909723594124506, | |
| "learning_rate": 1.0136624594416828e-06, | |
| "loss": 0.2808, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.848356309650053, | |
| "grad_norm": 0.2815262998286053, | |
| "learning_rate": 6.29370090964262e-07, | |
| "loss": 0.2844, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8907741251325557, | |
| "grad_norm": 0.27545396785421056, | |
| "learning_rate": 3.3167727641356064e-07, | |
| "loss": 0.273, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9331919406150583, | |
| "grad_norm": 0.27726375004859716, | |
| "learning_rate": 1.2648249392289925e-07, | |
| "loss": 0.2713, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.26279284026638045, | |
| "learning_rate": 1.785146788478298e-08, | |
| "loss": 0.2891, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9968186638388123, | |
| "step": 235, | |
| "total_flos": 412229836996608.0, | |
| "train_loss": 0.3199658251823263, | |
| "train_runtime": 20135.6606, | |
| "train_samples_per_second": 1.498, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 235, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 412229836996608.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |