| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0024570175492478457, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.914035098495691e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.914035098495691e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4031.4742, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 2.126, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.828070196991382e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014742105295487072, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00019656140393982765, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00024570175492478455, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00029484210590974145, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00034398245689469835, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003931228078796553, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004422631588646122, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004914035098495691, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000540543860834526, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005896842118194829, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006388245628044398, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006879649137893967, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0007371052647743536, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007862456157593106, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008353859667442674, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0008845263177292244, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009336666687141812, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0009828070196991382, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001031947370684095, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001081087721669052, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001130228072654009, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0011793684236389658, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012285087746239228, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0012285087746239228, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4032.2267, | |
| "eval_samples_per_second": 4.25, | |
| "eval_steps_per_second": 2.125, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0012776491256088797, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0013267894765938365, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0013759298275787934, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0014250701785637504, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0014742105295487073, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015233508805336641, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0015724912315186212, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.001621631582503578, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0016707719334885349, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.001719912284473492, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017690526354584488, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0018181929864434056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0018673333374283625, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0019164736884133195, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0019656140393982764, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020147543903832332, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00206389474136819, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002113035092353147, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002162175443338104, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002211315794323061, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002260456145308018, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0023095964962929747, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0023587368472779316, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0024078771982628884, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0024570175492478457, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0024570175492478457, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4032.1031, | |
| "eval_samples_per_second": 4.25, | |
| "eval_steps_per_second": 2.125, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.478754782950195e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |