| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.176056338028169, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007042253521126761, | |
| "grad_norm": 39.11391067504883, | |
| "learning_rate": 1e-05, | |
| "loss": 10.2157, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007042253521126761, | |
| "eval_loss": 10.0960111618042, | |
| "eval_runtime": 13.1147, | |
| "eval_samples_per_second": 9.15, | |
| "eval_steps_per_second": 1.144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014084507042253521, | |
| "grad_norm": 35.15620040893555, | |
| "learning_rate": 2e-05, | |
| "loss": 10.0954, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02112676056338028, | |
| "grad_norm": 37.665611267089844, | |
| "learning_rate": 3e-05, | |
| "loss": 10.1154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 34.913848876953125, | |
| "learning_rate": 4e-05, | |
| "loss": 9.3856, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.035211267605633804, | |
| "grad_norm": 41.44451141357422, | |
| "learning_rate": 5e-05, | |
| "loss": 8.5514, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04225352112676056, | |
| "grad_norm": 34.1007194519043, | |
| "learning_rate": 6e-05, | |
| "loss": 6.3474, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04929577464788732, | |
| "grad_norm": 21.132896423339844, | |
| "learning_rate": 7e-05, | |
| "loss": 4.1504, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 22.86393165588379, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7505, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06338028169014084, | |
| "grad_norm": 20.914813995361328, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2445, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06338028169014084, | |
| "eval_loss": 0.5339353680610657, | |
| "eval_runtime": 13.1745, | |
| "eval_samples_per_second": 9.109, | |
| "eval_steps_per_second": 1.139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07042253521126761, | |
| "grad_norm": 10.226069450378418, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6835, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07746478873239436, | |
| "grad_norm": 6.849209785461426, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.5162, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 9.03485107421875, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.5481, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09154929577464789, | |
| "grad_norm": 4.938020706176758, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.3335, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09859154929577464, | |
| "grad_norm": 10.797144889831543, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.4465, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1056338028169014, | |
| "grad_norm": 6.949985980987549, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.3258, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 6.018566608428955, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.2399, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11971830985915492, | |
| "grad_norm": 10.206531524658203, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.3624, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "grad_norm": 5.126565456390381, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.2134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "eval_loss": 0.30221232771873474, | |
| "eval_runtime": 13.1693, | |
| "eval_samples_per_second": 9.112, | |
| "eval_steps_per_second": 1.139, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13380281690140844, | |
| "grad_norm": 8.039265632629395, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.5262, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 6.505465984344482, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.3438, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14788732394366197, | |
| "grad_norm": 3.672312021255493, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.3436, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15492957746478872, | |
| "grad_norm": 3.8408946990966797, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.3006, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1619718309859155, | |
| "grad_norm": 6.516692638397217, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.5252, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 7.897261142730713, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6106, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.176056338028169, | |
| "grad_norm": 5.932919025421143, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4199, | |
| "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": 1.85471820890112e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |