| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9984, | |
| "eval_steps": 500, | |
| "global_step": 312, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0004987337087656614, | |
| "loss": 1.7079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0004949476630105669, | |
| "loss": 1.5881, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0004886802166271364, | |
| "loss": 1.537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0004799948609147061, | |
| "loss": 1.6139, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.000468979581391722, | |
| "loss": 1.5905, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0004557459664734141, | |
| "loss": 1.5532, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0004404280770443398, | |
| "loss": 1.5624, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00042318108837739987, | |
| "loss": 1.566, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0004041797181571358, | |
| "loss": 1.6084, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00038361645653195025, | |
| "loss": 1.5778, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003616996161254065, | |
| "loss": 1.5952, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003386512217606339, | |
| "loss": 1.526, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00031470476127563017, | |
| "loss": 1.5188, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002901028202144401, | |
| "loss": 1.5547, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00026509462435557154, | |
| "loss": 1.4073, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002399335149726463, | |
| "loss": 1.543, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002148743824037269, | |
| "loss": 1.4798, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00019017108392811063, | |
| "loss": 1.479, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00016607387210834887, | |
| "loss": 1.5438, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00014282685964923643, | |
| "loss": 1.5179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00012066554645558578, | |
| "loss": 1.4537, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.981443394050524e-05, | |
| "loss": 1.5523, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.048475075202727e-05, | |
| "loss": 1.5372, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.28723129572247e-05, | |
| "loss": 1.5376, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.715554036085673e-05, | |
| "loss": 1.5009, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.3493649053890325e-05, | |
| "loss": 1.5572, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.2025038501977485e-05, | |
| "loss": 1.5053, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.286588951321363e-05, | |
| "loss": 1.5444, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.108987288226536e-06, | |
| "loss": 1.5053, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.822781475486507e-06, | |
| "loss": 1.4731, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.069275378746796e-08, | |
| "loss": 1.5291, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 312, | |
| "total_flos": 1.0452011423603098e+17, | |
| "train_loss": 1.5403484671543806, | |
| "train_runtime": 1808.2639, | |
| "train_samples_per_second": 2.765, | |
| "train_steps_per_second": 0.173 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 312, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.0452011423603098e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |