| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.42000654339790344, | |
| "learning_rate": 0.00019, | |
| "loss": 2.3405, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3462536931037903, | |
| "learning_rate": 0.00039000000000000005, | |
| "loss": 2.0338, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3165397346019745, | |
| "learning_rate": 0.0004995066821070679, | |
| "loss": 1.9899, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3208169937133789, | |
| "learning_rate": 0.000494893812399836, | |
| "loss": 1.9271, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3150009214878082, | |
| "learning_rate": 0.00048551436319682417, | |
| "loss": 1.9116, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.3124900758266449, | |
| "learning_rate": 0.00047155089480780364, | |
| "loss": 1.8997, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.3002833127975464, | |
| "learning_rate": 0.0004532751902617569, | |
| "loss": 1.8786, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.31171324849128723, | |
| "learning_rate": 0.00043104296535936696, | |
| "loss": 1.8725, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.29542508721351624, | |
| "learning_rate": 0.0004052869450695776, | |
| "loss": 1.8492, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.2971261143684387, | |
| "learning_rate": 0.0003765084410302909, | |
| "loss": 1.8369, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.30833086371421814, | |
| "learning_rate": 0.0003452675940875686, | |
| "loss": 1.8455, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.29420724511146545, | |
| "learning_rate": 0.0003121724717912138, | |
| "loss": 1.8386, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.3092733919620514, | |
| "learning_rate": 0.00027786723305158134, | |
| "loss": 1.8389, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.30236175656318665, | |
| "learning_rate": 0.00024301959031910783, | |
| "loss": 1.8244, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.31684431433677673, | |
| "learning_rate": 0.00020830781332097445, | |
| "loss": 1.8188, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.3082987666130066, | |
| "learning_rate": 0.00017440752731238892, | |
| "loss": 1.8117, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.28097477555274963, | |
| "learning_rate": 0.0001419785627995044, | |
| "loss": 1.8093, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.30032917857170105, | |
| "learning_rate": 0.000111652112689164, | |
| "loss": 1.8271, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.30186182260513306, | |
| "learning_rate": 8.40184468369396e-05, | |
| "loss": 1.7926, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.30022040009498596, | |
| "learning_rate": 5.961542311581586e-05, | |
| "loss": 1.797, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.31262123584747314, | |
| "learning_rate": 3.891801862449629e-05, | |
| "loss": 1.8048, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.2855285704135895, | |
| "learning_rate": 2.2329084798455746e-05, | |
| "loss": 1.8056, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.3000660240650177, | |
| "learning_rate": 1.0171506364985622e-05, | |
| "loss": 1.7877, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.2893758714199066, | |
| "learning_rate": 2.681916759252917e-06, | |
| "loss": 1.7942, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2988986372947693, | |
| "learning_rate": 6.092323651313292e-09, | |
| "loss": 1.7917, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.4071568135757824e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |