| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9957805907172996, | |
| "eval_steps": 500, | |
| "global_step": 118, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008438818565400843, | |
| "grad_norm": 0.9650136232376099, | |
| "learning_rate": 2.4999999999999998e-05, | |
| "loss": 2.8582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04219409282700422, | |
| "grad_norm": 1.779584288597107, | |
| "learning_rate": 0.000125, | |
| "loss": 2.8146, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08438818565400844, | |
| "grad_norm": 2.2833831310272217, | |
| "learning_rate": 0.00025, | |
| "loss": 2.5451, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12658227848101267, | |
| "grad_norm": 5.367890357971191, | |
| "learning_rate": 0.0002994074763922825, | |
| "loss": 1.6976, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16877637130801687, | |
| "grad_norm": 1.000970482826233, | |
| "learning_rate": 0.0002958034371120616, | |
| "loss": 1.4928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2109704641350211, | |
| "grad_norm": 0.7289397120475769, | |
| "learning_rate": 0.000289003441114775, | |
| "loss": 1.3257, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25316455696202533, | |
| "grad_norm": 0.511790931224823, | |
| "learning_rate": 0.0002791565417651033, | |
| "loss": 1.2616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29535864978902954, | |
| "grad_norm": 0.5492662191390991, | |
| "learning_rate": 0.00026647857940770634, | |
| "loss": 1.2023, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.33755274261603374, | |
| "grad_norm": 0.33897170424461365, | |
| "learning_rate": 0.0002512474502277316, | |
| "loss": 1.1788, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.379746835443038, | |
| "grad_norm": 0.24469247460365295, | |
| "learning_rate": 0.00023379701487054785, | |
| "loss": 1.1525, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4219409282700422, | |
| "grad_norm": 0.21288429200649261, | |
| "learning_rate": 0.00021450978034147806, | |
| "loss": 1.1336, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4641350210970464, | |
| "grad_norm": 0.22459806501865387, | |
| "learning_rate": 0.00019380851559554636, | |
| "loss": 1.1152, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 0.21257351338863373, | |
| "learning_rate": 0.00017214698460037218, | |
| "loss": 1.1092, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5485232067510548, | |
| "grad_norm": 0.2138395607471466, | |
| "learning_rate": 0.00015, | |
| "loss": 1.0926, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5907172995780591, | |
| "grad_norm": 0.19117598235607147, | |
| "learning_rate": 0.00012785301539962782, | |
| "loss": 1.0938, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6329113924050633, | |
| "grad_norm": 0.18693800270557404, | |
| "learning_rate": 0.00010619148440445364, | |
| "loss": 1.0873, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6751054852320675, | |
| "grad_norm": 0.22816094756126404, | |
| "learning_rate": 8.549021965852197e-05, | |
| "loss": 1.0805, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7172995780590717, | |
| "grad_norm": 0.20088453590869904, | |
| "learning_rate": 6.620298512945214e-05, | |
| "loss": 1.0702, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.759493670886076, | |
| "grad_norm": 0.19913840293884277, | |
| "learning_rate": 4.8752549772268444e-05, | |
| "loss": 1.0596, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8016877637130801, | |
| "grad_norm": 0.20332343876361847, | |
| "learning_rate": 3.352142059229365e-05, | |
| "loss": 1.0629, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8438818565400844, | |
| "grad_norm": 0.1878909319639206, | |
| "learning_rate": 2.0843458234896666e-05, | |
| "loss": 1.0765, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8860759493670886, | |
| "grad_norm": 0.25477486848831177, | |
| "learning_rate": 1.0996558885224993e-05, | |
| "loss": 1.0739, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9282700421940928, | |
| "grad_norm": 0.19258134067058563, | |
| "learning_rate": 4.1965628879383875e-06, | |
| "loss": 1.0637, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9704641350210971, | |
| "grad_norm": 0.19716647267341614, | |
| "learning_rate": 5.925236077174655e-07, | |
| "loss": 1.0732, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9957805907172996, | |
| "eval_loss": 1.6185935735702515, | |
| "eval_runtime": 1.1156, | |
| "eval_samples_per_second": 1.793, | |
| "eval_steps_per_second": 0.896, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.9957805907172996, | |
| "step": 118, | |
| "total_flos": 3.483831540687831e+17, | |
| "train_loss": 1.2929974753977889, | |
| "train_runtime": 1281.4902, | |
| "train_samples_per_second": 5.906, | |
| "train_steps_per_second": 0.092 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 118, | |
| "num_input_tokens_seen": 0, | |
| "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": 3.483831540687831e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |