| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008209102252577658, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.2836409010310635e-05, | |
| "grad_norm": 0.039061568677425385, | |
| "learning_rate": 1e-05, | |
| "loss": 10.374, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.2836409010310635e-05, | |
| "eval_loss": 10.37774658203125, | |
| "eval_runtime": 169.5857, | |
| "eval_samples_per_second": 151.227, | |
| "eval_steps_per_second": 18.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.567281802062127e-05, | |
| "grad_norm": 0.04970359802246094, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3808, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.85092270309319e-05, | |
| "grad_norm": 0.051377296447753906, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013134563604124254, | |
| "grad_norm": 0.040986333042383194, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3831, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016418204505155317, | |
| "grad_norm": 0.04276856407523155, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001970184540618638, | |
| "grad_norm": 0.03917916491627693, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022985486307217442, | |
| "grad_norm": 0.054591104388237, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3798, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002626912720824851, | |
| "grad_norm": 0.04181118682026863, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3828, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002955276810927957, | |
| "grad_norm": 0.039910946041345596, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002955276810927957, | |
| "eval_loss": 10.377296447753906, | |
| "eval_runtime": 170.6195, | |
| "eval_samples_per_second": 150.311, | |
| "eval_steps_per_second": 18.79, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032836409010310633, | |
| "grad_norm": 0.057242438197135925, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00036120049911341694, | |
| "grad_norm": 0.06191801652312279, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3803, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0003940369081237276, | |
| "grad_norm": 0.06025468185544014, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3891, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00042687331713403825, | |
| "grad_norm": 0.04083796963095665, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3679, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00045970972614434885, | |
| "grad_norm": 0.04752117395401001, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3791, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0004925461351546594, | |
| "grad_norm": 0.063045933842659, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.383, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005253825441649702, | |
| "grad_norm": 0.03456421196460724, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3785, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005582189531752808, | |
| "grad_norm": 0.04961790144443512, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3833, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005910553621855914, | |
| "grad_norm": 0.05567217618227005, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3881, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005910553621855914, | |
| "eval_loss": 10.37619400024414, | |
| "eval_runtime": 170.4028, | |
| "eval_samples_per_second": 150.502, | |
| "eval_steps_per_second": 18.814, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006238917711959021, | |
| "grad_norm": 0.038412440568208694, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3748, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006567281802062127, | |
| "grad_norm": 0.04399815946817398, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006895645892165233, | |
| "grad_norm": 0.03764853626489639, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3762, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007224009982268339, | |
| "grad_norm": 0.052127059549093246, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3771, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007552374072371446, | |
| "grad_norm": 0.03697521612048149, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007880738162474552, | |
| "grad_norm": 0.04965825751423836, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3714, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008209102252577658, | |
| "grad_norm": 0.038044273853302, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3757, | |
| "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": 1307561164800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |