| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 615, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 3.4918, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 3.4392, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3662, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 3.23, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0296, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9953, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9222, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7419, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6997, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6147, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6041, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5295, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.1770684719085693, | |
| "eval_runtime": 5.1953, | |
| "eval_samples_per_second": 2.887, | |
| "eval_steps_per_second": 0.385, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5208, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4462, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4549, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5357, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4114, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4352, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4544, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002, | |
| "loss": 2.399, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4452, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3952, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4314, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.0628561973571777, | |
| "eval_runtime": 5.0293, | |
| "eval_samples_per_second": 2.983, | |
| "eval_steps_per_second": 0.398, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4612, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4087, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3681, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3734, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3862, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3411, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3971, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002, | |
| "loss": 2.489, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4349, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0002, | |
| "loss": 2.381, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3873, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 2.403, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.0353705883026123, | |
| "eval_runtime": 4.9843, | |
| "eval_samples_per_second": 3.009, | |
| "eval_steps_per_second": 0.401, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3933, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3991, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3259, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3312, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3381, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2982, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3162, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.362, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4566, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5111, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4077, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3527, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3605, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.0221874713897705, | |
| "eval_runtime": 4.9809, | |
| "eval_samples_per_second": 3.012, | |
| "eval_steps_per_second": 0.402, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3695, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3616, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3368, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2342, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3994, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3202, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 0.0002, | |
| "loss": 2.417, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.0002, | |
| "loss": 2.421, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3507, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3594, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4163, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3647, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.013761281967163, | |
| "eval_runtime": 5.0042, | |
| "eval_samples_per_second": 2.998, | |
| "eval_steps_per_second": 0.4, | |
| "step": 615 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 615, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 6543762259968000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |