| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.037064492216456635, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014825796886582653, | |
| "grad_norm": 2.8474559783935547, | |
| "learning_rate": 1e-05, | |
| "loss": 5.225, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014825796886582653, | |
| "eval_loss": 2.508056402206421, | |
| "eval_runtime": 69.5324, | |
| "eval_samples_per_second": 8.169, | |
| "eval_steps_per_second": 1.021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029651593773165306, | |
| "grad_norm": 2.3535349369049072, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6645, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004447739065974796, | |
| "grad_norm": 2.6361703872680664, | |
| "learning_rate": 3e-05, | |
| "loss": 4.8725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005930318754633061, | |
| "grad_norm": 4.400317192077637, | |
| "learning_rate": 4e-05, | |
| "loss": 4.7542, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007412898443291327, | |
| "grad_norm": 2.6915769577026367, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008895478131949592, | |
| "grad_norm": 3.3075225353240967, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5994, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010378057820607857, | |
| "grad_norm": 3.946103572845459, | |
| "learning_rate": 7e-05, | |
| "loss": 4.6332, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011860637509266123, | |
| "grad_norm": 4.162266731262207, | |
| "learning_rate": 8e-05, | |
| "loss": 4.7407, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013343217197924388, | |
| "grad_norm": 5.167053699493408, | |
| "learning_rate": 9e-05, | |
| "loss": 4.3724, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013343217197924388, | |
| "eval_loss": 1.8550039529800415, | |
| "eval_runtime": 69.5376, | |
| "eval_samples_per_second": 8.168, | |
| "eval_steps_per_second": 1.021, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014825796886582653, | |
| "grad_norm": 4.388719081878662, | |
| "learning_rate": 0.0001, | |
| "loss": 3.382, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01630837657524092, | |
| "grad_norm": 5.396074295043945, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 3.0693, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017790956263899184, | |
| "grad_norm": 5.097604751586914, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01927353595255745, | |
| "grad_norm": 5.280440807342529, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.0353, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020756115641215715, | |
| "grad_norm": 3.470097780227661, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.1178, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02223869532987398, | |
| "grad_norm": 4.099720478057861, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.1429, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023721275018532245, | |
| "grad_norm": 3.006298065185547, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.0927, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025203854707190512, | |
| "grad_norm": 1.9103775024414062, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.6789, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.026686434395848776, | |
| "grad_norm": 3.037099599838257, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.3045, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026686434395848776, | |
| "eval_loss": 0.32767146825790405, | |
| "eval_runtime": 69.5401, | |
| "eval_samples_per_second": 8.168, | |
| "eval_steps_per_second": 1.021, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 4.88580322265625, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.8711, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029651593773165306, | |
| "grad_norm": 14.325489044189453, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6723, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.031134173461823574, | |
| "grad_norm": 1.8659063577651978, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.3444, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03261675315048184, | |
| "grad_norm": 1.1169908046722412, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.1008, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0340993328391401, | |
| "grad_norm": 3.31902813911438, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.5448, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03558191252779837, | |
| "grad_norm": 2.234715700149536, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.2588, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.037064492216456635, | |
| "grad_norm": 1.7870392799377441, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.219, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.63366161088512e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |