| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1893939393939394, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007575757575757576, | |
| "grad_norm": 0.7533223628997803, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007575757575757576, | |
| "eval_loss": 1.8315911293029785, | |
| "eval_runtime": 20.8027, | |
| "eval_samples_per_second": 5.336, | |
| "eval_steps_per_second": 0.673, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015151515151515152, | |
| "grad_norm": 0.9126298427581787, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9551, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022727272727272728, | |
| "grad_norm": 1.181591272354126, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9402, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 1.1208268404006958, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3827, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03787878787878788, | |
| "grad_norm": 1.2570971250534058, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5976, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 1.388541340827942, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0091, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05303030303030303, | |
| "grad_norm": 1.4139080047607422, | |
| "learning_rate": 7e-05, | |
| "loss": 1.817, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 0.9321380257606506, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7755, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "grad_norm": 0.840682864189148, | |
| "learning_rate": 9e-05, | |
| "loss": 1.0306, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "eval_loss": 1.762389898300171, | |
| "eval_runtime": 19.337, | |
| "eval_samples_per_second": 5.74, | |
| "eval_steps_per_second": 0.724, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07575757575757576, | |
| "grad_norm": 1.8093039989471436, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7722, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 1.243077278137207, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.0837, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.7991745471954346, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.6041, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09848484848484848, | |
| "grad_norm": 0.7331045866012573, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.2589, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10606060606060606, | |
| "grad_norm": 0.8287887573242188, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.1675, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 1.3653068542480469, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.0063, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.5731700658798218, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.5773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12878787878787878, | |
| "grad_norm": 0.9433817863464355, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.3717, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 1.1009303331375122, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.3868, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "eval_loss": 1.5803662538528442, | |
| "eval_runtime": 19.3482, | |
| "eval_samples_per_second": 5.737, | |
| "eval_steps_per_second": 0.724, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14393939393939395, | |
| "grad_norm": 0.6402528882026672, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.1916, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 0.6150195598602295, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.5243, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1590909090909091, | |
| "grad_norm": 0.5555574297904968, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.9703, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.5409879684448242, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.2571, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17424242424242425, | |
| "grad_norm": 0.6518788933753967, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.3489, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.7059927582740784, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6073, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1893939393939394, | |
| "grad_norm": 0.62007737159729, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4875, | |
| "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": 3.412681504378061e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |