| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01576320168140818, | |
| "eval_steps": 9, | |
| "global_step": 45, | |
| "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 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.852863789662208e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |