| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0153846153846153, | |
| "eval_steps": 50, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06153846153846154, | |
| "grad_norm": 2.5551578998565674, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5015, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06153846153846154, | |
| "eval_loss": 1.9502390623092651, | |
| "eval_runtime": 3.1313, | |
| "eval_samples_per_second": 8.623, | |
| "eval_steps_per_second": 4.471, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12307692307692308, | |
| "grad_norm": 3.457622528076172, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6852, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.18461538461538463, | |
| "grad_norm": 3.9540300369262695, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.9428, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.24615384615384617, | |
| "grad_norm": 4.253664016723633, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1933, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 2.051302909851074, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.3646, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.36923076923076925, | |
| "grad_norm": 2.010624885559082, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2732, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4307692307692308, | |
| "grad_norm": 2.0207128524780273, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.3799, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "grad_norm": 2.6285526752471924, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5559, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5538461538461539, | |
| "grad_norm": 1.5692611932754517, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.1225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.5529125928878784, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.676923076923077, | |
| "grad_norm": 2.1200125217437744, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1675, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7384615384615385, | |
| "grad_norm": 2.0532970428466797, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2506, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.283276915550232, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.9155, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8615384615384616, | |
| "grad_norm": 1.2680752277374268, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9374, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.449583888053894, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0173, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9846153846153847, | |
| "grad_norm": 1.8077707290649414, | |
| "learning_rate": 8e-05, | |
| "loss": 1.239, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0461538461538462, | |
| "grad_norm": 6.680090427398682, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.5489, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1076923076923078, | |
| "grad_norm": 0.9765293002128601, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8236, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1692307692307693, | |
| "grad_norm": 0.8778647780418396, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.8098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 1.2021186351776123, | |
| "learning_rate": 0.0001, | |
| "loss": 0.945, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2923076923076924, | |
| "grad_norm": 0.8680479526519775, | |
| "learning_rate": 9.970689785771798e-05, | |
| "loss": 0.8755, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.353846153846154, | |
| "grad_norm": 0.8105959892272949, | |
| "learning_rate": 9.883102778550434e-05, | |
| "loss": 0.7208, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4153846153846155, | |
| "grad_norm": 0.9586474895477295, | |
| "learning_rate": 9.738265855914013e-05, | |
| "loss": 0.7929, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.476923076923077, | |
| "grad_norm": 1.152060627937317, | |
| "learning_rate": 9.537877098354786e-05, | |
| "loss": 0.8189, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.9032147526741028, | |
| "learning_rate": 9.284285880837946e-05, | |
| "loss": 0.8127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.8633611798286438, | |
| "learning_rate": 8.980465328528219e-05, | |
| "loss": 0.6254, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6615384615384614, | |
| "grad_norm": 1.0637147426605225, | |
| "learning_rate": 8.629977459615655e-05, | |
| "loss": 0.8617, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7230769230769232, | |
| "grad_norm": 1.1698484420776367, | |
| "learning_rate": 8.236931423909138e-05, | |
| "loss": 0.962, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7846153846153845, | |
| "grad_norm": 1.2579647302627563, | |
| "learning_rate": 7.805935326811912e-05, | |
| "loss": 0.7148, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 0.8797979354858398, | |
| "learning_rate": 7.342042203498951e-05, | |
| "loss": 0.6799, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9076923076923076, | |
| "grad_norm": 0.9369248151779175, | |
| "learning_rate": 6.850690776699573e-05, | |
| "loss": 0.7911, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.9692307692307693, | |
| "grad_norm": 1.1235183477401733, | |
| "learning_rate": 6.337641692646106e-05, | |
| "loss": 0.861, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0307692307692307, | |
| "grad_norm": 3.2580151557922363, | |
| "learning_rate": 5.808909982763825e-05, | |
| "loss": 1.0444, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.0923076923076924, | |
| "grad_norm": 0.6802517771720886, | |
| "learning_rate": 5.270694542927088e-05, | |
| "loss": 0.4869, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 0.7931990027427673, | |
| "learning_rate": 4.729305457072913e-05, | |
| "loss": 0.5766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.2153846153846155, | |
| "grad_norm": 0.9201847910881042, | |
| "learning_rate": 4.1910900172361764e-05, | |
| "loss": 0.6061, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.276923076923077, | |
| "grad_norm": 0.7804703712463379, | |
| "learning_rate": 3.6623583073538966e-05, | |
| "loss": 0.5625, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.3384615384615386, | |
| "grad_norm": 0.7250446081161499, | |
| "learning_rate": 3.149309223300428e-05, | |
| "loss": 0.5647, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.7047279477119446, | |
| "learning_rate": 2.65795779650105e-05, | |
| "loss": 0.4682, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 0.9160324335098267, | |
| "learning_rate": 2.194064673188089e-05, | |
| "loss": 0.6123, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.523076923076923, | |
| "grad_norm": 0.8389458656311035, | |
| "learning_rate": 1.7630685760908622e-05, | |
| "loss": 0.5937, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.5846153846153848, | |
| "grad_norm": 0.7738927602767944, | |
| "learning_rate": 1.3700225403843469e-05, | |
| "loss": 0.4901, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.646153846153846, | |
| "grad_norm": 0.8202934861183167, | |
| "learning_rate": 1.0195346714717813e-05, | |
| "loss": 0.5782, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.707692307692308, | |
| "grad_norm": 0.9444193243980408, | |
| "learning_rate": 7.157141191620548e-06, | |
| "loss": 0.5208, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 0.8349220752716064, | |
| "learning_rate": 4.621229016452156e-06, | |
| "loss": 0.5911, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.830769230769231, | |
| "grad_norm": 0.75601726770401, | |
| "learning_rate": 2.6173414408598827e-06, | |
| "loss": 0.5208, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.8923076923076922, | |
| "grad_norm": 0.8191360831260681, | |
| "learning_rate": 1.1689722144956671e-06, | |
| "loss": 0.5153, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.953846153846154, | |
| "grad_norm": 1.0536468029022217, | |
| "learning_rate": 2.9310214228202013e-07, | |
| "loss": 0.6799, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0153846153846153, | |
| "grad_norm": 8.771407127380371, | |
| "learning_rate": 0.0, | |
| "loss": 1.3893, | |
| "step": 49 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 49, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.117332469927117e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |