| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.791519434628975, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1413427561837456, | |
| "grad_norm": 8.807223320007324, | |
| "learning_rate": 4.9821173158545936e-05, | |
| "loss": 4.4182, | |
| "num_input_tokens_seen": 89360, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2826855123674912, | |
| "grad_norm": 9.933388710021973, | |
| "learning_rate": 4.928725095732169e-05, | |
| "loss": 2.2953, | |
| "num_input_tokens_seen": 173680, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42402826855123676, | |
| "grad_norm": 11.242781639099121, | |
| "learning_rate": 4.813260751184992e-05, | |
| "loss": 2.6132, | |
| "num_input_tokens_seen": 256320, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5653710247349824, | |
| "grad_norm": 18.152969360351562, | |
| "learning_rate": 4.6461219840046654e-05, | |
| "loss": 2.6473, | |
| "num_input_tokens_seen": 354080, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7067137809187279, | |
| "grad_norm": 13.362907409667969, | |
| "learning_rate": 4.431042398061499e-05, | |
| "loss": 1.9798, | |
| "num_input_tokens_seen": 445120, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8480565371024735, | |
| "grad_norm": 11.124238014221191, | |
| "learning_rate": 4.172826515897146e-05, | |
| "loss": 1.6494, | |
| "num_input_tokens_seen": 536160, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9893992932862191, | |
| "grad_norm": 13.07321548461914, | |
| "learning_rate": 3.8772424536302564e-05, | |
| "loss": 1.2652, | |
| "num_input_tokens_seen": 622160, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1130742049469964, | |
| "grad_norm": 10.049528121948242, | |
| "learning_rate": 3.550893070773914e-05, | |
| "loss": 1.1679, | |
| "num_input_tokens_seen": 702992, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.254416961130742, | |
| "grad_norm": 3.1295673847198486, | |
| "learning_rate": 3.201068473265007e-05, | |
| "loss": 0.7785, | |
| "num_input_tokens_seen": 795712, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3957597173144876, | |
| "grad_norm": 13.35985279083252, | |
| "learning_rate": 2.8355831645441388e-05, | |
| "loss": 1.3648, | |
| "num_input_tokens_seen": 880032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5371024734982333, | |
| "grad_norm": 11.210596084594727, | |
| "learning_rate": 2.4626014824618415e-05, | |
| "loss": 1.1121, | |
| "num_input_tokens_seen": 969392, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.6784452296819787, | |
| "grad_norm": 8.436594009399414, | |
| "learning_rate": 2.090455221462156e-05, | |
| "loss": 1.1847, | |
| "num_input_tokens_seen": 1058752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8197879858657244, | |
| "grad_norm": 7.8270649909973145, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.4018, | |
| "num_input_tokens_seen": 1143072, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.96113074204947, | |
| "grad_norm": 18.734634399414062, | |
| "learning_rate": 1.3817171292109183e-05, | |
| "loss": 0.7509, | |
| "num_input_tokens_seen": 1234112, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.0848056537102475, | |
| "grad_norm": 22.8198299407959, | |
| "learning_rate": 1.0609573357858166e-05, | |
| "loss": 0.46, | |
| "num_input_tokens_seen": 1303184, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.2261484098939928, | |
| "grad_norm": 6.278092861175537, | |
| "learning_rate": 7.723433775328384e-06, | |
| "loss": 0.4216, | |
| "num_input_tokens_seen": 1385824, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.3674911660777385, | |
| "grad_norm": 24.357179641723633, | |
| "learning_rate": 5.223224133591476e-06, | |
| "loss": 0.5816, | |
| "num_input_tokens_seen": 1476864, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.508833922261484, | |
| "grad_norm": 8.690754890441895, | |
| "learning_rate": 3.164794984571759e-06, | |
| "loss": 0.4955, | |
| "num_input_tokens_seen": 1569584, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.65017667844523, | |
| "grad_norm": 3.9934189319610596, | |
| "learning_rate": 1.59412823400657e-06, | |
| "loss": 0.2691, | |
| "num_input_tokens_seen": 1657264, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.791519434628975, | |
| "grad_norm": 9.84725284576416, | |
| "learning_rate": 5.463099816548579e-07, | |
| "loss": 1.1078, | |
| "num_input_tokens_seen": 1746624, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 105, | |
| "num_input_tokens_seen": 1746624, | |
| "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": 1.3006890837540864e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |