| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.146131805157593, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05730659025787966, | |
| "grad_norm": 13.615523112232149, | |
| "learning_rate": 5e-07, | |
| "loss": 1.2695, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11461318051575932, | |
| "grad_norm": 8.507104558172857, | |
| "learning_rate": 1e-06, | |
| "loss": 1.1722, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17191977077363896, | |
| "grad_norm": 5.216528499988659, | |
| "learning_rate": 9.990212076323586e-07, | |
| "loss": 1.067, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22922636103151864, | |
| "grad_norm": 3.9965836016587044, | |
| "learning_rate": 9.9608866266743e-07, | |
| "loss": 1.0137, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28653295128939826, | |
| "grad_norm": 3.90312687677931, | |
| "learning_rate": 9.912138465157323e-07, | |
| "loss": 1.0128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3438395415472779, | |
| "grad_norm": 3.5852669105149593, | |
| "learning_rate": 9.84415844908637e-07, | |
| "loss": 0.9835, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40114613180515757, | |
| "grad_norm": 3.544317847930178, | |
| "learning_rate": 9.757212731744973e-07, | |
| "loss": 0.967, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4584527220630373, | |
| "grad_norm": 3.581414511816451, | |
| "learning_rate": 9.65164172035126e-07, | |
| "loss": 0.9694, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5157593123209169, | |
| "grad_norm": 3.4337266155445634, | |
| "learning_rate": 9.527858743306018e-07, | |
| "loss": 0.9532, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "grad_norm": 3.4769930108810807, | |
| "learning_rate": 9.386348431941952e-07, | |
| "loss": 0.9472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "eval_loss": 0.9284669160842896, | |
| "eval_runtime": 42.918, | |
| "eval_samples_per_second": 57.761, | |
| "eval_steps_per_second": 0.909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6303724928366762, | |
| "grad_norm": 3.550987444482616, | |
| "learning_rate": 9.227664823109882e-07, | |
| "loss": 0.9391, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6876790830945558, | |
| "grad_norm": 3.4297326670171917, | |
| "learning_rate": 9.052429190030588e-07, | |
| "loss": 0.9422, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7449856733524355, | |
| "grad_norm": 3.507501066789746, | |
| "learning_rate": 8.861327609904857e-07, | |
| "loss": 0.9428, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8022922636103151, | |
| "grad_norm": 3.5906687662141117, | |
| "learning_rate": 8.655108277804975e-07, | |
| "loss": 0.9253, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8595988538681948, | |
| "grad_norm": 3.500303702885294, | |
| "learning_rate": 8.434578577364217e-07, | |
| "loss": 0.9285, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9169054441260746, | |
| "grad_norm": 3.9526314008449996, | |
| "learning_rate": 8.200601919733105e-07, | |
| "loss": 0.8996, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9742120343839542, | |
| "grad_norm": 3.516323615141867, | |
| "learning_rate": 7.954094363178421e-07, | |
| "loss": 0.895, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0315186246418337, | |
| "grad_norm": 4.35173055618085, | |
| "learning_rate": 7.696021026559849e-07, | |
| "loss": 0.8505, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0888252148997135, | |
| "grad_norm": 4.085589351210672, | |
| "learning_rate": 7.427392310726087e-07, | |
| "loss": 0.7964, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "grad_norm": 3.9343561192796934, | |
| "learning_rate": 7.149259942624286e-07, | |
| "loss": 0.7918, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "eval_loss": 0.8878653049468994, | |
| "eval_runtime": 42.3514, | |
| "eval_samples_per_second": 58.534, | |
| "eval_steps_per_second": 0.921, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 261, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 589411381149696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |