| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.035029337069795954, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003502933706979595, | |
| "eval_loss": 1.2642643451690674, | |
| "eval_runtime": 170.7468, | |
| "eval_samples_per_second": 28.159, | |
| "eval_steps_per_second": 3.52, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010508801120938786, | |
| "grad_norm": 0.26421603560447693, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2586, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002101760224187757, | |
| "grad_norm": 0.2573237419128418, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2507, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031526403362816357, | |
| "grad_norm": 0.23207610845565796, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2601, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031526403362816357, | |
| "eval_loss": 1.229485034942627, | |
| "eval_runtime": 172.5126, | |
| "eval_samples_per_second": 27.87, | |
| "eval_steps_per_second": 3.484, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004203520448375514, | |
| "grad_norm": 0.2796209156513214, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.2384, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005254400560469393, | |
| "grad_norm": 0.28329601883888245, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.2393, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0063052806725632715, | |
| "grad_norm": 0.22264641523361206, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.1474, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0063052806725632715, | |
| "eval_loss": 1.1840261220932007, | |
| "eval_runtime": 172.502, | |
| "eval_samples_per_second": 27.872, | |
| "eval_steps_per_second": 3.484, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0073561607846571505, | |
| "grad_norm": 0.23280549049377441, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.1913, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008407040896751029, | |
| "grad_norm": 0.2081017643213272, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.1646, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009457921008844907, | |
| "grad_norm": 0.22857177257537842, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.1644, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009457921008844907, | |
| "eval_loss": 1.1528327465057373, | |
| "eval_runtime": 172.5822, | |
| "eval_samples_per_second": 27.859, | |
| "eval_steps_per_second": 3.482, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010508801120938787, | |
| "grad_norm": 0.21918490529060364, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.1566, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011559681233032665, | |
| "grad_norm": 0.21285656094551086, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.1424, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012610561345126543, | |
| "grad_norm": 0.2332816869020462, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.1502, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012610561345126543, | |
| "eval_loss": 1.129488468170166, | |
| "eval_runtime": 172.61, | |
| "eval_samples_per_second": 27.855, | |
| "eval_steps_per_second": 3.482, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013661441457220423, | |
| "grad_norm": 0.23356926441192627, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 1.1295, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014712321569314301, | |
| "grad_norm": 0.21442051231861115, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.1046, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01576320168140818, | |
| "grad_norm": 0.23844681680202484, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.0832, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01576320168140818, | |
| "eval_loss": 1.1117569208145142, | |
| "eval_runtime": 172.5645, | |
| "eval_samples_per_second": 27.862, | |
| "eval_steps_per_second": 3.483, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016814081793502057, | |
| "grad_norm": 0.24442023038864136, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.1128, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017864961905595937, | |
| "grad_norm": 0.23531076312065125, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.0972, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.018915842017689814, | |
| "grad_norm": 0.2517203390598297, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.1432, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.018915842017689814, | |
| "eval_loss": 1.0988001823425293, | |
| "eval_runtime": 172.5963, | |
| "eval_samples_per_second": 27.857, | |
| "eval_steps_per_second": 3.482, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.019966722129783693, | |
| "grad_norm": 0.2424170821905136, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 1.0881, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.021017602241877573, | |
| "grad_norm": 0.244013249874115, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.0868, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02206848235397145, | |
| "grad_norm": 0.26657232642173767, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 1.1314, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02206848235397145, | |
| "eval_loss": 1.0899685621261597, | |
| "eval_runtime": 172.583, | |
| "eval_samples_per_second": 27.859, | |
| "eval_steps_per_second": 3.482, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02311936246606533, | |
| "grad_norm": 0.24828645586967468, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.0957, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02417024257815921, | |
| "grad_norm": 0.24023310840129852, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 1.0662, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.025221122690253086, | |
| "grad_norm": 0.2469858080148697, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.1214, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.025221122690253086, | |
| "eval_loss": 1.083965539932251, | |
| "eval_runtime": 172.5642, | |
| "eval_samples_per_second": 27.862, | |
| "eval_steps_per_second": 3.483, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.026272002802346966, | |
| "grad_norm": 0.2567300498485565, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.1177, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.027322882914440846, | |
| "grad_norm": 0.25198131799697876, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.1116, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.028373763026534722, | |
| "grad_norm": 0.25876638293266296, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 1.0904, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.028373763026534722, | |
| "eval_loss": 1.0805628299713135, | |
| "eval_runtime": 172.5771, | |
| "eval_samples_per_second": 27.86, | |
| "eval_steps_per_second": 3.483, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.029424643138628602, | |
| "grad_norm": 0.2582884132862091, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.0749, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03047552325072248, | |
| "grad_norm": 0.26067253947257996, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.107, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.03152640336281636, | |
| "grad_norm": 0.2517987787723541, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.0924, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03152640336281636, | |
| "eval_loss": 1.078951358795166, | |
| "eval_runtime": 172.5708, | |
| "eval_samples_per_second": 27.861, | |
| "eval_steps_per_second": 3.483, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.032577283474910235, | |
| "grad_norm": 0.25309544801712036, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 1.0884, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.033628163587004115, | |
| "grad_norm": 0.2665356993675232, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.0868, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.034679043699097994, | |
| "grad_norm": 0.2470860630273819, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 1.0543, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.034679043699097994, | |
| "eval_loss": 1.0786346197128296, | |
| "eval_runtime": 172.5707, | |
| "eval_samples_per_second": 27.861, | |
| "eval_steps_per_second": 3.483, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.11747508813824e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |