| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06134969325153374, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00245398773006135, | |
| "grad_norm": 1.2490895986557007, | |
| "learning_rate": 1e-05, | |
| "loss": 0.377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00245398773006135, | |
| "eval_loss": 0.3467381000518799, | |
| "eval_runtime": 73.3044, | |
| "eval_samples_per_second": 4.679, | |
| "eval_steps_per_second": 0.587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0049079754601227, | |
| "grad_norm": 0.9828861951828003, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007361963190184049, | |
| "grad_norm": 1.7154072523117065, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4348, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0098159509202454, | |
| "grad_norm": 1.0366357564926147, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4483, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012269938650306749, | |
| "grad_norm": 0.5755931735038757, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014723926380368098, | |
| "grad_norm": 0.538214921951294, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2947, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01717791411042945, | |
| "grad_norm": 0.6407910585403442, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3255, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0196319018404908, | |
| "grad_norm": 0.5397402048110962, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2128, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022085889570552148, | |
| "grad_norm": 0.4955255091190338, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2757, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022085889570552148, | |
| "eval_loss": 0.19442740082740784, | |
| "eval_runtime": 72.614, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 0.592, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024539877300613498, | |
| "grad_norm": 0.6418875455856323, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026993865030674847, | |
| "grad_norm": 0.49799808859825134, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.1871, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029447852760736196, | |
| "grad_norm": 0.38547053933143616, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.1577, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03190184049079755, | |
| "grad_norm": 0.4232013523578644, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.1357, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0343558282208589, | |
| "grad_norm": 0.26138433814048767, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.102, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03680981595092025, | |
| "grad_norm": 0.2390362024307251, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.1143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0392638036809816, | |
| "grad_norm": 0.3332692086696625, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.1448, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04171779141104295, | |
| "grad_norm": 0.24300773441791534, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.1121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044171779141104296, | |
| "grad_norm": 0.36635148525238037, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.1723, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044171779141104296, | |
| "eval_loss": 0.11410464346408844, | |
| "eval_runtime": 72.6128, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 0.592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.046625766871165646, | |
| "grad_norm": 0.2136872410774231, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0939, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.049079754601226995, | |
| "grad_norm": 0.2869775593280792, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.051533742331288344, | |
| "grad_norm": 0.21182110905647278, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0954, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.053987730061349694, | |
| "grad_norm": 0.4248709976673126, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0941, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05644171779141104, | |
| "grad_norm": 0.16834016144275665, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0836, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05889570552147239, | |
| "grad_norm": 0.25709477066993713, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06134969325153374, | |
| "grad_norm": 0.3403218686580658, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1511, | |
| "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": 3.264304047665971e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |