| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016744668916033858, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.697867566413543e-05, | |
| "grad_norm": 11.202531814575195, | |
| "learning_rate": 0.0001, | |
| "loss": 9.3451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013395735132827087, | |
| "grad_norm": 14.230999946594238, | |
| "learning_rate": 0.0002, | |
| "loss": 9.1198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002009360269924063, | |
| "grad_norm": 9.925089836120605, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.1381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00026791470265654174, | |
| "grad_norm": 9.510652542114258, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 7.5019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033489337832067715, | |
| "grad_norm": 6.61540412902832, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.3718, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004018720539848126, | |
| "grad_norm": 7.274428367614746, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 7.7984, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000468850729648948, | |
| "grad_norm": 7.099924087524414, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.7624, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005358294053130835, | |
| "grad_norm": 5.519874572753906, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 5.4764, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006028080809772189, | |
| "grad_norm": 11.996742248535156, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.9885, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006697867566413543, | |
| "grad_norm": 11.48196792602539, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 9.2482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007367654323054897, | |
| "grad_norm": 5.304096221923828, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.2764, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008037441079696252, | |
| "grad_norm": 9.102093696594238, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.9416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008707227836337606, | |
| "grad_norm": 6.1233696937561035, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 4.4378, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000937701459297896, | |
| "grad_norm": 7.5049052238464355, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.3169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010046801349620316, | |
| "grad_norm": 6.807133674621582, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.1685, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001071658810626167, | |
| "grad_norm": 7.475444316864014, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.9925, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011386374862903024, | |
| "grad_norm": 5.890412330627441, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 8.3801, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012056161619544378, | |
| "grad_norm": 8.594086647033691, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.0054, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012725948376185732, | |
| "grad_norm": 5.71251916885376, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 7.2484, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0013395735132827086, | |
| "grad_norm": 5.218650817871094, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.1231, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001406552188946844, | |
| "grad_norm": 6.071516513824463, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 5.5233, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014735308646109794, | |
| "grad_norm": 10.335101127624512, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.0461, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0015405095402751148, | |
| "grad_norm": 4.438607215881348, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.0407, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0016074882159392504, | |
| "grad_norm": 4.374053478240967, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 5.6196, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016744668916033858, | |
| "grad_norm": 4.783155918121338, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 4.7725, | |
| "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": 3.26729100951552e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |