| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.6535464525222778, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.7296, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.0043237209320068, | |
| "learning_rate": 9.978490638616671e-06, | |
| "loss": 1.1007, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.1549423933029175, | |
| "learning_rate": 9.873583924954152e-06, | |
| "loss": 0.972, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 3.9684245586395264, | |
| "learning_rate": 9.68316749134364e-06, | |
| "loss": 1.4319, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.5548748970031738, | |
| "learning_rate": 9.410582299213574e-06, | |
| "loss": 1.2878, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 2.273371934890747, | |
| "learning_rate": 9.060611006213833e-06, | |
| "loss": 0.8514, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 1.2761274576187134, | |
| "learning_rate": 8.639394051847472e-06, | |
| "loss": 1.1175, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.957119345664978, | |
| "learning_rate": 8.154321920070415e-06, | |
| "loss": 0.8047, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 6.853240966796875, | |
| "learning_rate": 7.613905469171247e-06, | |
| "loss": 1.0589, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.4756696224212646, | |
| "learning_rate": 7.02762660406497e-06, | |
| "loss": 0.6791, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 5.216459274291992, | |
| "learning_rate": 6.405771911037698e-06, | |
| "loss": 1.0538, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.377304196357727, | |
| "learning_rate": 5.759252173912573e-06, | |
| "loss": 0.883, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 6.482784748077393, | |
| "learning_rate": 5.099410938325351e-06, | |
| "loss": 0.9499, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 6.192553520202637, | |
| "learning_rate": 4.43782548295514e-06, | |
| "loss": 1.0224, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.5093391537666321, | |
| "learning_rate": 3.786103689779861e-06, | |
| "loss": 0.695, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.030840277671814, | |
| "learning_rate": 3.1556803773799616e-06, | |
| "loss": 0.5973, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.9577879905700684, | |
| "learning_rate": 2.5576166707349387e-06, | |
| "loss": 0.6599, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.8994718790054321, | |
| "learning_rate": 2.0024059276803742e-06, | |
| "loss": 0.7363, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 3.4781222343444824, | |
| "learning_rate": 1.499789627152874e-06, | |
| "loss": 0.7894, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.7506103515625, | |
| "learning_rate": 1.0585864495652899e-06, | |
| "loss": 0.9814, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.9295775890350342, | |
| "learning_rate": 6.865375481914017e-07, | |
| "loss": 0.9046, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 5.636131286621094, | |
| "learning_rate": 3.9017072635896716e-07, | |
| "loss": 0.8721, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 1.5328168869018555, | |
| "learning_rate": 1.7468590353731495e-07, | |
| "loss": 0.899, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.8393186330795288, | |
| "learning_rate": 4.3863879880142737e-08, | |
| "loss": 0.703, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.1779817342758179, | |
| "learning_rate": 0.0, | |
| "loss": 0.8335, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 250, | |
| "total_flos": 9900634722822144.0, | |
| "train_loss": 0.9045761451721192, | |
| "train_runtime": 431.9804, | |
| "train_samples_per_second": 2.315, | |
| "train_steps_per_second": 0.579 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "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": 9900634722822144.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |