| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02321262766945218, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046425255338904364, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 5.249, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00046425255338904364, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.8816, | |
| "eval_samples_per_second": 70.411, | |
| "eval_steps_per_second": 35.244, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001392757660167131, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018570102135561746, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002321262766945218, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032497678737233053, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003714020427112349, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004178272980501393, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5862, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00510677808727948, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0060352831940575676, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0060352831940575676, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.4691, | |
| "eval_samples_per_second": 79.082, | |
| "eval_steps_per_second": 39.585, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0064995357474466105, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006963788300835654, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007428040854224698, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007892293407613741, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008820798514391829, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009749303621169917, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 2.4739, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01021355617455896, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010677808727948004, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011142061281337047, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01160631383472609, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012070566388115135, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012070566388115135, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.4647, | |
| "eval_samples_per_second": 79.112, | |
| "eval_steps_per_second": 39.6, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012534818941504178, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012999071494893221, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013463324048282266, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014391829155060354, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.014856081708449397, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01532033426183844, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015784586815227482, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 3.1814, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.016248839368616527, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016713091922005572, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.017177344475394613, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.017641597028783658, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018105849582172703, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018105849582172703, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.7781, | |
| "eval_samples_per_second": 77.007, | |
| "eval_steps_per_second": 38.546, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018570102135561744, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01903435468895079, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019498607242339833, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.019962859795728878, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 1.0726, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02042711234911792, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020891364902506964, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02135561745589601, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02181987000928505, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02274837511606314, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02321262766945218, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1214754852962304.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |