| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.465855307640297, | |
| "global_step": 14000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.9993238674780257e-05, | |
| "loss": 1.9928, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.9986477349560515e-05, | |
| "loss": 1.5804, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5350453853607178, | |
| "eval_runtime": 0.0909, | |
| "eval_samples_per_second": 43.998, | |
| "eval_steps_per_second": 11.0, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.997971602434077e-05, | |
| "loss": 1.4417, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.997295469912103e-05, | |
| "loss": 1.2966, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.9966193373901284e-05, | |
| "loss": 1.2455, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.411128044128418, | |
| "eval_runtime": 0.0866, | |
| "eval_samples_per_second": 46.21, | |
| "eval_steps_per_second": 11.552, | |
| "step": 2958 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.9959432048681543e-05, | |
| "loss": 1.1971, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.99526707234618e-05, | |
| "loss": 1.1112, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.9945909398242057e-05, | |
| "loss": 1.0734, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.3451578617095947, | |
| "eval_runtime": 0.0858, | |
| "eval_samples_per_second": 46.634, | |
| "eval_steps_per_second": 11.659, | |
| "step": 4437 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.9939148073022316e-05, | |
| "loss": 1.0531, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.993238674780257e-05, | |
| "loss": 0.9843, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.992562542258283e-05, | |
| "loss": 0.9622, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.2762081623077393, | |
| "eval_runtime": 0.0884, | |
| "eval_samples_per_second": 45.25, | |
| "eval_steps_per_second": 11.312, | |
| "step": 5916 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.9918864097363085e-05, | |
| "loss": 0.9453, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 1.9912102772143343e-05, | |
| "loss": 0.8873, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.99053414469236e-05, | |
| "loss": 0.8723, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.2012463808059692, | |
| "eval_runtime": 0.0849, | |
| "eval_samples_per_second": 47.093, | |
| "eval_steps_per_second": 11.773, | |
| "step": 7395 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.9898580121703857e-05, | |
| "loss": 0.8676, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 1.9891818796484112e-05, | |
| "loss": 0.7985, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 1.9885057471264367e-05, | |
| "loss": 0.8085, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.1576131582260132, | |
| "eval_runtime": 0.0879, | |
| "eval_samples_per_second": 45.526, | |
| "eval_steps_per_second": 11.381, | |
| "step": 8874 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 1.9878296146044626e-05, | |
| "loss": 0.7917, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.987153482082488e-05, | |
| "loss": 0.7452, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.986477349560514e-05, | |
| "loss": 0.7447, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.1027594804763794, | |
| "eval_runtime": 0.0838, | |
| "eval_samples_per_second": 47.724, | |
| "eval_steps_per_second": 11.931, | |
| "step": 10353 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.9858012170385395e-05, | |
| "loss": 0.7298, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.9851250845165654e-05, | |
| "loss": 0.681, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 1.9844489519945912e-05, | |
| "loss": 0.7038, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0498589277267456, | |
| "eval_runtime": 0.086, | |
| "eval_samples_per_second": 46.519, | |
| "eval_steps_per_second": 11.63, | |
| "step": 11832 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 1.9837728194726168e-05, | |
| "loss": 0.6726, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 1.9830966869506426e-05, | |
| "loss": 0.6405, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 1.982420554428668e-05, | |
| "loss": 0.6458, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.9868650436401367, | |
| "eval_runtime": 0.0904, | |
| "eval_samples_per_second": 44.229, | |
| "eval_steps_per_second": 11.057, | |
| "step": 13311 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 1.981744421906694e-05, | |
| "loss": 0.6234, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 1.9810682893847195e-05, | |
| "loss": 0.5984, | |
| "step": 14000 | |
| } | |
| ], | |
| "max_steps": 1479000, | |
| "num_train_epochs": 1000, | |
| "total_flos": 3.051556454321357e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |