| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 145, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.9595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.0078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.7643, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4478, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001992708874098054, | |
| "loss": 1.3356, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.4178, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001935016242685415, | |
| "loss": 1.2849, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 1.271, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018229838658936564, | |
| "loss": 1.3692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.2819, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00016631226582407952, | |
| "loss": 1.3848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00015680647467311557, | |
| "loss": 1.332, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00014647231720437686, | |
| "loss": 1.2716, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 1.2611, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001239315664287558, | |
| "loss": 1.2658, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001120536680255323, | |
| "loss": 1.3735, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3004, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 1.2043, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.606843357124426e-05, | |
| "loss": 1.1837, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.453951129574644e-05, | |
| "loss": 1.1508, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.3527682795623146e-05, | |
| "loss": 1.2025, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 1.2575, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.36877341759205e-05, | |
| "loss": 1.2624, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.514892518288988e-05, | |
| "loss": 1.2505, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7701613410634365e-05, | |
| "loss": 1.2264, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 1.1638, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.498375731458528e-06, | |
| "loss": 1.1018, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.905818257394799e-06, | |
| "loss": 1.2153, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.291125901946027e-07, | |
| "loss": 1.1638, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2691, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1793650388717651, | |
| "eval_runtime": 24.4695, | |
| "eval_samples_per_second": 11.811, | |
| "eval_steps_per_second": 1.512, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 145, | |
| "total_flos": 2.153195061955789e+16, | |
| "train_loss": 1.310744782151847, | |
| "train_runtime": 268.5316, | |
| "train_samples_per_second": 4.309, | |
| "train_steps_per_second": 0.54 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 145, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 2.153195061955789e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |