| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005671506352087115, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.2686025408348456e-05, | |
| "grad_norm": 1.6416054964065552, | |
| "learning_rate": 1e-05, | |
| "loss": 3.1299, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.2686025408348456e-05, | |
| "eval_loss": 3.1315808296203613, | |
| "eval_runtime": 1113.4778, | |
| "eval_samples_per_second": 33.337, | |
| "eval_steps_per_second": 4.167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.537205081669691e-05, | |
| "grad_norm": 1.6501107215881348, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0943, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.805807622504538e-05, | |
| "grad_norm": 1.723808765411377, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1309, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.074410163339382e-05, | |
| "grad_norm": 1.7017780542373657, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1083, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011343012704174228, | |
| "grad_norm": 1.7527612447738647, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0895, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00013611615245009076, | |
| "grad_norm": 1.946850061416626, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0412, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001588021778584392, | |
| "grad_norm": 1.6056472063064575, | |
| "learning_rate": 7e-05, | |
| "loss": 2.8686, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00018148820326678765, | |
| "grad_norm": 1.555307388305664, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7655, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00020417422867513612, | |
| "grad_norm": 1.6594849824905396, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7033, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020417422867513612, | |
| "eval_loss": 2.648374319076538, | |
| "eval_runtime": 1114.7953, | |
| "eval_samples_per_second": 33.298, | |
| "eval_steps_per_second": 4.162, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022686025408348456, | |
| "grad_norm": 1.9916863441467285, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6444, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000249546279491833, | |
| "grad_norm": 2.3508129119873047, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.665, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0002722323049001815, | |
| "grad_norm": 2.1137266159057617, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.5167, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00029491833030852996, | |
| "grad_norm": 1.6255558729171753, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.4863, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003176043557168784, | |
| "grad_norm": 1.564011573791504, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.3751, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00034029038112522685, | |
| "grad_norm": 1.4088207483291626, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.3232, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003629764065335753, | |
| "grad_norm": 1.549394130706787, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.287, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003856624319419238, | |
| "grad_norm": 1.0880142450332642, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.244, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00040834845735027224, | |
| "grad_norm": 1.453312635421753, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.2197, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00040834845735027224, | |
| "eval_loss": 2.2361209392547607, | |
| "eval_runtime": 1116.9114, | |
| "eval_samples_per_second": 33.235, | |
| "eval_steps_per_second": 4.154, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004310344827586207, | |
| "grad_norm": 1.3305575847625732, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.2363, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00045372050816696913, | |
| "grad_norm": 1.5530980825424194, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.1967, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00047640653357531763, | |
| "grad_norm": 1.5624852180480957, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.2401, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000499092558983666, | |
| "grad_norm": 1.6178418397903442, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.1992, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0005217785843920145, | |
| "grad_norm": 1.6604396104812622, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.2365, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000544464609800363, | |
| "grad_norm": 1.4351677894592285, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.1485, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005671506352087115, | |
| "grad_norm": 1.5888997316360474, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1908, | |
| "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": 2419306423910400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |