| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001394583437927091, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 332.0751, | |
| "eval_samples_per_second": 45.463, | |
| "eval_steps_per_second": 22.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.578333751708365e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.367500627562547e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001394583437927091, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016735001255125095, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019524168130979276, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002231333500683346, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002510250188268764, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002789166875854182, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003068083563439601, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0003347000251025019, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003625916938610437, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003625916938610437, | |
| "eval_loss": NaN, | |
| "eval_runtime": 334.3864, | |
| "eval_samples_per_second": 45.148, | |
| "eval_steps_per_second": 22.576, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003904833626195855, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00041837503137812733, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004462667001366692, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000474158368895211, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005020500376537528, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005299417064122947, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0005578333751708364, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005857250439293783, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006136167126879202, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0006415083814464619, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0006694000502050038, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006972917189635455, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007251833877220874, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0007251833877220874, | |
| "eval_loss": NaN, | |
| "eval_runtime": 331.8422, | |
| "eval_samples_per_second": 45.495, | |
| "eval_steps_per_second": 22.749, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0007530750564806293, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.000780966725239171, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0008088583939977129, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0008367500627562547, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008646417315147965, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0008925334002733384, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0009204250690318801, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.000948316737790422, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0009762084065489639, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0010041000753075056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0010319917440660474, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0010598834128245894, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0010877750815831311, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0010877750815831311, | |
| "eval_loss": NaN, | |
| "eval_runtime": 330.5815, | |
| "eval_samples_per_second": 45.668, | |
| "eval_steps_per_second": 22.836, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0011156667503416729, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011435584191002148, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0011714500878587566, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0011993417566172984, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0012272334253758403, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.001255125094134382, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0012830167628929239, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0013109084316514656, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0013388001004100076, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0013666917691685493, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.001394583437927091, | |
| "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": 2148475962654720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |