| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000811187903565982, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.244751614263928e-05, | |
| "grad_norm": 0.699952244758606, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.244751614263928e-05, | |
| "eval_loss": 1.2364516258239746, | |
| "eval_runtime": 410.7977, | |
| "eval_samples_per_second": 63.177, | |
| "eval_steps_per_second": 7.899, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.489503228527856e-05, | |
| "grad_norm": 0.5059106945991516, | |
| "learning_rate": 2e-05, | |
| "loss": 1.173, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.734254842791784e-05, | |
| "grad_norm": 0.721911609172821, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2592, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012979006457055711, | |
| "grad_norm": 0.7691875696182251, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2255, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016223758071319641, | |
| "grad_norm": 0.6363957524299622, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2921, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00019468509685583569, | |
| "grad_norm": 0.8589330315589905, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022713261299847496, | |
| "grad_norm": 0.7455472350120544, | |
| "learning_rate": 7e-05, | |
| "loss": 1.3303, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00025958012914111423, | |
| "grad_norm": 0.6809628009796143, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1682, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002920276452837535, | |
| "grad_norm": 0.5815722346305847, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2131, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002920276452837535, | |
| "eval_loss": 1.2085680961608887, | |
| "eval_runtime": 409.6889, | |
| "eval_samples_per_second": 63.348, | |
| "eval_steps_per_second": 7.921, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032447516142639283, | |
| "grad_norm": 0.48401424288749695, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003569226775690321, | |
| "grad_norm": 0.7972922325134277, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.3705, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00038937019371167137, | |
| "grad_norm": 0.7923889756202698, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.187, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00042181770985431064, | |
| "grad_norm": 0.7378607988357544, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.1752, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0004542652259969499, | |
| "grad_norm": 0.6670899987220764, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.2382, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0004867127421395892, | |
| "grad_norm": 0.5493435859680176, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.0741, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005191602582822285, | |
| "grad_norm": 0.6642765402793884, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005516077744248677, | |
| "grad_norm": 0.7158033847808838, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.0416, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.000584055290567507, | |
| "grad_norm": 0.6141757965087891, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.1888, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000584055290567507, | |
| "eval_loss": 1.1528652906417847, | |
| "eval_runtime": 409.6904, | |
| "eval_samples_per_second": 63.348, | |
| "eval_steps_per_second": 7.921, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006165028067101464, | |
| "grad_norm": 0.7109853029251099, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.09, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006489503228527857, | |
| "grad_norm": 0.6954298615455627, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.0063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006813978389954249, | |
| "grad_norm": 0.7887369990348816, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.0689, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007138453551380642, | |
| "grad_norm": 0.9078826308250427, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.0223, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007462928712807035, | |
| "grad_norm": 0.8368735313415527, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.2175, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007787403874233427, | |
| "grad_norm": 0.6735103726387024, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.2283, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000811187903565982, | |
| "grad_norm": 0.6207486391067505, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0345, | |
| "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": 2727827245891584.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |