| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 5972, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.9994976557267246e-05, | |
| "loss": 0.0815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.500167448091092e-05, | |
| "loss": 0.0141, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.01242989394813776, | |
| "eval_runtime": 164.7633, | |
| "eval_samples_per_second": 310.682, | |
| "eval_steps_per_second": 4.855, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0003348961821836e-05, | |
| "loss": 0.0119, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.012703760527074337, | |
| "eval_runtime": 164.7117, | |
| "eval_samples_per_second": 310.779, | |
| "eval_steps_per_second": 4.857, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5005023442732755e-05, | |
| "loss": 0.0112, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.013858836144208908, | |
| "eval_runtime": 164.7925, | |
| "eval_samples_per_second": 310.627, | |
| "eval_steps_per_second": 4.855, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.000669792364367e-05, | |
| "loss": 0.0094, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.012725627049803734, | |
| "eval_runtime": 164.7465, | |
| "eval_samples_per_second": 310.714, | |
| "eval_steps_per_second": 4.856, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.008372404554588e-06, | |
| "loss": 0.0091, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.01414352934807539, | |
| "eval_runtime": 164.7415, | |
| "eval_samples_per_second": 310.723, | |
| "eval_steps_per_second": 4.856, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.0046885465505694e-08, | |
| "loss": 0.0089, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.013257584534585476, | |
| "eval_runtime": 164.7803, | |
| "eval_samples_per_second": 310.65, | |
| "eval_steps_per_second": 4.855, | |
| "step": 5970 | |
| } | |
| ], | |
| "max_steps": 5972, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.01113970314453e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |