| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010965152744577733, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.386061097831093e-05, | |
| "grad_norm": 0.10043748468160629, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.386061097831093e-05, | |
| "eval_loss": 10.372465133666992, | |
| "eval_runtime": 286.375, | |
| "eval_samples_per_second": 67.045, | |
| "eval_steps_per_second": 8.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.772122195662186e-05, | |
| "grad_norm": 0.07904290407896042, | |
| "learning_rate": 2e-05, | |
| "loss": 10.384, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013158183293493278, | |
| "grad_norm": 0.08990306407213211, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3806, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017544244391324372, | |
| "grad_norm": 0.08300121128559113, | |
| "learning_rate": 4e-05, | |
| "loss": 10.379, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021930305489155464, | |
| "grad_norm": 0.10797716677188873, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3875, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00026316366586986555, | |
| "grad_norm": 0.12022226303815842, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3697, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00030702427684817647, | |
| "grad_norm": 0.11509042233228683, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3746, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00035088488782648744, | |
| "grad_norm": 0.10822642594575882, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3679, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00039474549880479836, | |
| "grad_norm": 0.11744695156812668, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3775, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00039474549880479836, | |
| "eval_loss": 10.371199607849121, | |
| "eval_runtime": 286.4036, | |
| "eval_samples_per_second": 67.038, | |
| "eval_steps_per_second": 8.38, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004386061097831093, | |
| "grad_norm": 0.08792486041784286, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004824667207614202, | |
| "grad_norm": 0.18052351474761963, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3768, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005263273317397311, | |
| "grad_norm": 0.10901749134063721, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3686, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005701879427180421, | |
| "grad_norm": 0.12148555368185043, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3674, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006140485536963529, | |
| "grad_norm": 0.15141719579696655, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3568, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006579091646746639, | |
| "grad_norm": 0.13673336803913116, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.357, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007017697756529749, | |
| "grad_norm": 0.1090550422668457, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3686, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007456303866312857, | |
| "grad_norm": 0.12227842211723328, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.367, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007894909976095967, | |
| "grad_norm": 0.12432891130447388, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3589, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007894909976095967, | |
| "eval_loss": 10.367905616760254, | |
| "eval_runtime": 286.4026, | |
| "eval_samples_per_second": 67.039, | |
| "eval_steps_per_second": 8.38, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008333516085879076, | |
| "grad_norm": 0.09832531958818436, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.373, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008772122195662185, | |
| "grad_norm": 0.1374433934688568, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3661, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009210728305445295, | |
| "grad_norm": 0.12131146341562271, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.365, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009649334415228404, | |
| "grad_norm": 0.14021863043308258, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3637, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0010087940525011514, | |
| "grad_norm": 0.09942276775836945, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3705, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0010526546634794622, | |
| "grad_norm": 0.12141352891921997, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.375, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010965152744577733, | |
| "grad_norm": 0.1361175924539566, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3731, | |
| "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": 2458214989824.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |