| { | |
| "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": 0.0561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.500167448091092e-05, | |
| "loss": 0.0111, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.010945957154035568, | |
| "eval_runtime": 164.8351, | |
| "eval_samples_per_second": 310.547, | |
| "eval_steps_per_second": 4.853, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.0003348961821836e-05, | |
| "loss": 0.0096, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.011111176572740078, | |
| "eval_runtime": 164.6974, | |
| "eval_samples_per_second": 310.806, | |
| "eval_steps_per_second": 4.857, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5005023442732755e-05, | |
| "loss": 0.0091, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.011091501452028751, | |
| "eval_runtime": 164.8189, | |
| "eval_samples_per_second": 310.577, | |
| "eval_steps_per_second": 4.854, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.000669792364367e-05, | |
| "loss": 0.0078, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.010855572298169136, | |
| "eval_runtime": 164.7068, | |
| "eval_samples_per_second": 310.789, | |
| "eval_steps_per_second": 4.857, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.008372404554588e-06, | |
| "loss": 0.0076, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.012394336052238941, | |
| "eval_runtime": 164.7631, | |
| "eval_samples_per_second": 310.682, | |
| "eval_steps_per_second": 4.855, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.0046885465505694e-08, | |
| "loss": 0.0074, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.011221092194318771, | |
| "eval_runtime": 164.746, | |
| "eval_samples_per_second": 310.715, | |
| "eval_steps_per_second": 4.856, | |
| "step": 5970 | |
| } | |
| ], | |
| "max_steps": 5972, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.01113970314453e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |