| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993906154783668, | |
| "eval_steps": 100, | |
| "global_step": 615, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0004, | |
| "loss": 1.3292, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.264318823814392, | |
| "eval_runtime": 84.6316, | |
| "eval_samples_per_second": 6.121, | |
| "eval_steps_per_second": 1.536, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00036392754225221053, | |
| "loss": 1.2472, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.2486543655395508, | |
| "eval_runtime": 84.6693, | |
| "eval_samples_per_second": 6.118, | |
| "eval_steps_per_second": 1.535, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00026872239108850267, | |
| "loss": 1.2331, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.2404521703720093, | |
| "eval_runtime": 84.6623, | |
| "eval_samples_per_second": 6.118, | |
| "eval_steps_per_second": 1.536, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00014872738443612402, | |
| "loss": 1.2188, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.2340422868728638, | |
| "eval_runtime": 84.6101, | |
| "eval_samples_per_second": 6.122, | |
| "eval_steps_per_second": 1.536, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.722767036921105e-05, | |
| "loss": 1.2173, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.2294026613235474, | |
| "eval_runtime": 84.6649, | |
| "eval_samples_per_second": 6.118, | |
| "eval_steps_per_second": 1.535, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.366903586781493e-07, | |
| "loss": 1.2025, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.2282078266143799, | |
| "eval_runtime": 84.629, | |
| "eval_samples_per_second": 6.121, | |
| "eval_steps_per_second": 1.536, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 615, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 8.660077507682304e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |