| { | |
| "best_metric": 2.506849527359009, | |
| "best_model_checkpoint": "./outputs/checkpoint-800", | |
| "epoch": 0.5828779599271403, | |
| "eval_steps": 100, | |
| "global_step": 800, | |
| "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": 2.8176, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.7248005867004395, | |
| "eval_runtime": 204.526, | |
| "eval_samples_per_second": 30.676, | |
| "eval_steps_per_second": 3.838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6959, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.6743462085723877, | |
| "eval_runtime": 205.6888, | |
| "eval_samples_per_second": 30.502, | |
| "eval_steps_per_second": 3.816, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6512, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.6400036811828613, | |
| "eval_runtime": 204.5763, | |
| "eval_samples_per_second": 30.668, | |
| "eval_steps_per_second": 3.837, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6241, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.6055357456207275, | |
| "eval_runtime": 204.4295, | |
| "eval_samples_per_second": 30.69, | |
| "eval_steps_per_second": 3.84, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5812, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.5787856578826904, | |
| "eval_runtime": 204.1968, | |
| "eval_samples_per_second": 30.725, | |
| "eval_steps_per_second": 3.844, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 2.553, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.552586555480957, | |
| "eval_runtime": 204.5367, | |
| "eval_samples_per_second": 30.674, | |
| "eval_steps_per_second": 3.838, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5368, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.527393341064453, | |
| "eval_runtime": 204.8117, | |
| "eval_samples_per_second": 30.633, | |
| "eval_steps_per_second": 3.833, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5124, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.506849527359009, | |
| "eval_runtime": 204.0454, | |
| "eval_samples_per_second": 30.748, | |
| "eval_steps_per_second": 3.847, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4116, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2.277701378039808e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |