| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024752475247524754, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004950495049504951, | |
| "grad_norm": 0.5114933252334595, | |
| "learning_rate": 5e-06, | |
| "loss": 2.5697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004950495049504951, | |
| "eval_loss": 2.622131824493408, | |
| "eval_runtime": 15.1063, | |
| "eval_samples_per_second": 56.334, | |
| "eval_steps_per_second": 28.2, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009900990099009901, | |
| "grad_norm": 0.5429823398590088, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6019, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014851485148514852, | |
| "grad_norm": 1.1041313409805298, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.5231, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019801980198019802, | |
| "grad_norm": 0.9193277359008789, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6823, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024752475247524753, | |
| "grad_norm": 0.7951717972755432, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.3677, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029702970297029703, | |
| "grad_norm": 0.9375802874565125, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3939, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034653465346534654, | |
| "grad_norm": 0.6394500136375427, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.8128, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0039603960396039604, | |
| "grad_norm": 0.6920015215873718, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5449, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004455445544554455, | |
| "grad_norm": 0.808408260345459, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.5139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0049504950495049506, | |
| "grad_norm": 0.5451938509941101, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6134, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005445544554455445, | |
| "grad_norm": 0.9277445673942566, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 2.5469, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005940594059405941, | |
| "grad_norm": 0.9077724814414978, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 2.7174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006435643564356435, | |
| "grad_norm": 0.7381893396377563, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 2.759, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006435643564356435, | |
| "eval_loss": 2.598520278930664, | |
| "eval_runtime": 13.6057, | |
| "eval_samples_per_second": 62.548, | |
| "eval_steps_per_second": 31.311, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006930693069306931, | |
| "grad_norm": 0.7455027103424072, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 2.5129, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007425742574257425, | |
| "grad_norm": 0.7870685458183289, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 2.716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007920792079207921, | |
| "grad_norm": 0.7373952865600586, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 2.6652, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008415841584158416, | |
| "grad_norm": 0.709264874458313, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 2.6148, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00891089108910891, | |
| "grad_norm": 0.8849121928215027, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 2.5974, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009405940594059406, | |
| "grad_norm": 0.6484812498092651, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 2.6253, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009900990099009901, | |
| "grad_norm": 0.7150304913520813, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 2.5675, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010396039603960397, | |
| "grad_norm": 0.848437488079071, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 2.5794, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01089108910891089, | |
| "grad_norm": 1.2628787755966187, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 2.7266, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011386138613861386, | |
| "grad_norm": 0.8389996290206909, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 2.4219, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011881188118811881, | |
| "grad_norm": 0.8797109127044678, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 2.5167, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012376237623762377, | |
| "grad_norm": 0.7067325115203857, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 2.266, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01287128712871287, | |
| "grad_norm": 1.0020214319229126, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 2.5468, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01287128712871287, | |
| "eval_loss": 2.526824951171875, | |
| "eval_runtime": 13.5807, | |
| "eval_samples_per_second": 62.662, | |
| "eval_steps_per_second": 31.368, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013366336633663366, | |
| "grad_norm": 0.6852343678474426, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 2.6977, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013861386138613862, | |
| "grad_norm": 0.6660365462303162, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 2.3572, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014356435643564357, | |
| "grad_norm": 0.6907557249069214, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 2.4936, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01485148514851485, | |
| "grad_norm": 0.7001723051071167, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.5243, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015346534653465346, | |
| "grad_norm": 0.6474969387054443, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 2.566, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015841584158415842, | |
| "grad_norm": 0.7469086647033691, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 2.4028, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016336633663366337, | |
| "grad_norm": 1.4682289361953735, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 3.0202, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016831683168316833, | |
| "grad_norm": 0.647513747215271, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 2.6409, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017326732673267328, | |
| "grad_norm": 0.5837624073028564, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 2.3664, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01782178217821782, | |
| "grad_norm": 0.5973520874977112, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 2.2474, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018316831683168316, | |
| "grad_norm": 0.6770974397659302, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 2.4933, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01881188118811881, | |
| "grad_norm": 0.7002883553504944, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 2.4098, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019306930693069307, | |
| "grad_norm": 0.5202279090881348, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 2.3545, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019306930693069307, | |
| "eval_loss": 2.5015273094177246, | |
| "eval_runtime": 13.8909, | |
| "eval_samples_per_second": 61.263, | |
| "eval_steps_per_second": 30.667, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": 0.6241593956947327, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 2.3477, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020297029702970298, | |
| "grad_norm": 0.7181453108787537, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 2.5936, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020792079207920793, | |
| "grad_norm": 0.590019941329956, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 2.5446, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02128712871287129, | |
| "grad_norm": 0.6002688407897949, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 2.5584, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02178217821782178, | |
| "grad_norm": 0.6000116467475891, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 2.3596, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022277227722772276, | |
| "grad_norm": 0.48489993810653687, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 2.4035, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02277227722772277, | |
| "grad_norm": 0.590663492679596, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 2.5489, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023267326732673267, | |
| "grad_norm": 0.7829977869987488, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 2.6551, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023762376237623763, | |
| "grad_norm": 0.6934583783149719, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 2.5088, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.024257425742574258, | |
| "grad_norm": 0.5398517847061157, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 2.4165, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024752475247524754, | |
| "grad_norm": 0.7464584112167358, | |
| "learning_rate": 0.0, | |
| "loss": 2.5148, | |
| "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": 1624279061889024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |