| { | |
| "best_metric": 2.4054911136627197, | |
| "best_model_checkpoint": "./outputs/checkpoint-900", | |
| "epoch": 0.6557377049180327, | |
| "eval_steps": 100, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7401, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.6427574157714844, | |
| "eval_runtime": 205.0145, | |
| "eval_samples_per_second": 30.603, | |
| "eval_steps_per_second": 3.829, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6057, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.591986656188965, | |
| "eval_runtime": 205.1897, | |
| "eval_samples_per_second": 30.577, | |
| "eval_steps_per_second": 3.826, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5624, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.5554449558258057, | |
| "eval_runtime": 204.8733, | |
| "eval_samples_per_second": 30.624, | |
| "eval_steps_per_second": 3.832, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5354, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.523040533065796, | |
| "eval_runtime": 205.0355, | |
| "eval_samples_per_second": 30.6, | |
| "eval_steps_per_second": 3.829, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4938, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.497437000274658, | |
| "eval_runtime": 204.8026, | |
| "eval_samples_per_second": 30.634, | |
| "eval_steps_per_second": 3.833, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4668, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.4717156887054443, | |
| "eval_runtime": 204.8144, | |
| "eval_samples_per_second": 30.633, | |
| "eval_steps_per_second": 3.833, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4508, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.449354410171509, | |
| "eval_runtime": 204.5211, | |
| "eval_samples_per_second": 30.677, | |
| "eval_steps_per_second": 3.838, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4278, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.4278199672698975, | |
| "eval_runtime": 204.6341, | |
| "eval_samples_per_second": 30.66, | |
| "eval_steps_per_second": 3.836, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3928, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.4054911136627197, | |
| "eval_runtime": 204.5808, | |
| "eval_samples_per_second": 30.668, | |
| "eval_steps_per_second": 3.837, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4116, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2.625477585518592e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |