| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4756242568370987, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023781212841854936, | |
| "grad_norm": 11.536224365234375, | |
| "learning_rate": 3e-05, | |
| "loss": 5.0938, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04756242568370987, | |
| "grad_norm": 3.4980711936950684, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 3.1992, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0713436385255648, | |
| "grad_norm": 2.206911325454712, | |
| "learning_rate": 0.00019951729686242962, | |
| "loss": 2.0348, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09512485136741974, | |
| "grad_norm": 1.7694568634033203, | |
| "learning_rate": 0.00019790828640386162, | |
| "loss": 1.9145, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11890606420927467, | |
| "grad_norm": 1.6293410062789917, | |
| "learning_rate": 0.00019629927594529365, | |
| "loss": 1.7651, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1426872770511296, | |
| "grad_norm": 1.8220889568328857, | |
| "learning_rate": 0.00019469026548672567, | |
| "loss": 1.8897, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16646848989298454, | |
| "grad_norm": 1.842227578163147, | |
| "learning_rate": 0.0001930812550281577, | |
| "loss": 1.8391, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1902497027348395, | |
| "grad_norm": 1.6302684545516968, | |
| "learning_rate": 0.00019147224456958972, | |
| "loss": 1.7881, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2140309155766944, | |
| "grad_norm": 1.7633960247039795, | |
| "learning_rate": 0.00018986323411102174, | |
| "loss": 1.7444, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23781212841854935, | |
| "grad_norm": 1.9522314071655273, | |
| "learning_rate": 0.00018825422365245377, | |
| "loss": 1.6647, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2615933412604043, | |
| "grad_norm": 1.5591909885406494, | |
| "learning_rate": 0.00018664521319388576, | |
| "loss": 1.6839, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2853745541022592, | |
| "grad_norm": 1.9646824598312378, | |
| "learning_rate": 0.00018503620273531779, | |
| "loss": 1.7177, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3091557669441142, | |
| "grad_norm": 2.0045852661132812, | |
| "learning_rate": 0.0001834271922767498, | |
| "loss": 1.7352, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3329369797859691, | |
| "grad_norm": 1.6761493682861328, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 1.5562, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.356718192627824, | |
| "grad_norm": 1.720191478729248, | |
| "learning_rate": 0.00018020917135961383, | |
| "loss": 1.8305, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.380499405469679, | |
| "grad_norm": 1.689537763595581, | |
| "learning_rate": 0.00017860016090104586, | |
| "loss": 1.6121, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4042806183115339, | |
| "grad_norm": 1.6469579935073853, | |
| "learning_rate": 0.0001769911504424779, | |
| "loss": 1.5827, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4280618311533888, | |
| "grad_norm": 1.637831449508667, | |
| "learning_rate": 0.0001753821399839099, | |
| "loss": 1.6039, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4518430439952438, | |
| "grad_norm": 2.1786320209503174, | |
| "learning_rate": 0.00017377312952534193, | |
| "loss": 1.7008, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4756242568370987, | |
| "grad_norm": 1.634881615638733, | |
| "learning_rate": 0.00017216411906677395, | |
| "loss": 1.5673, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1263, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.30437162755072e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |