| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006197764466356985, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.479105786542794e-05, | |
| "grad_norm": 7.298285007476807, | |
| "learning_rate": 0.0001, | |
| "loss": 8.3458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.958211573085588e-05, | |
| "grad_norm": 8.879791259765625, | |
| "learning_rate": 0.0002, | |
| "loss": 8.3615, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.437317359628382e-05, | |
| "grad_norm": 8.794269561767578, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 7.5151, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.916423146171176e-05, | |
| "grad_norm": 9.012420654296875, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 5.6806, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001239552893271397, | |
| "grad_norm": 7.061407566070557, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.9168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00014874634719256764, | |
| "grad_norm": 6.04531717300415, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.518, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017353740505799558, | |
| "grad_norm": 5.078192234039307, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 1.6634, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00019832846292342353, | |
| "grad_norm": 5.033928871154785, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.907, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00022311952078885147, | |
| "grad_norm": 3.0206494331359863, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.6279, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002479105786542794, | |
| "grad_norm": 2.810877799987793, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.419, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00027270163651970736, | |
| "grad_norm": 3.125711441040039, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.7372, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0002974926943851353, | |
| "grad_norm": 3.9015979766845703, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.312, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003222837522505632, | |
| "grad_norm": 1.802170753479004, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.1449, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00034707481011599117, | |
| "grad_norm": 1.4817924499511719, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0737, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0003718658679814191, | |
| "grad_norm": 0.31127655506134033, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0081, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00039665692584684706, | |
| "grad_norm": 1.7345539331436157, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.1763, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000421447983712275, | |
| "grad_norm": 0.861487865447998, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0059, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00044623904157770294, | |
| "grad_norm": 0.014484393410384655, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0003, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00047103009944313086, | |
| "grad_norm": 0.020801691338419914, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0003, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0004958211573085588, | |
| "grad_norm": 0.035404324531555176, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005206122151739868, | |
| "grad_norm": 15.371546745300293, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.1066, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0005454032730394147, | |
| "grad_norm": 0.01011655479669571, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0002, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0005701943309048426, | |
| "grad_norm": 0.09178952872753143, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0005949853887702706, | |
| "grad_norm": 0.00701731164008379, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0001, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006197764466356985, | |
| "grad_norm": 0.014851056970655918, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0003, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 3.3054705844224e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |