| { | |
| "best_metric": 2.507997512817383, | |
| "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": 2.8181, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.7240540981292725, | |
| "eval_runtime": 204.8489, | |
| "eval_samples_per_second": 30.627, | |
| "eval_steps_per_second": 3.832, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6957, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.6725997924804688, | |
| "eval_runtime": 204.875, | |
| "eval_samples_per_second": 30.624, | |
| "eval_steps_per_second": 3.832, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6509, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.6377696990966797, | |
| "eval_runtime": 204.8779, | |
| "eval_samples_per_second": 30.623, | |
| "eval_steps_per_second": 3.832, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6248, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.6048855781555176, | |
| "eval_runtime": 204.7551, | |
| "eval_samples_per_second": 30.641, | |
| "eval_steps_per_second": 3.834, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5822, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.5791709423065186, | |
| "eval_runtime": 204.976, | |
| "eval_samples_per_second": 30.608, | |
| "eval_steps_per_second": 3.83, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5557, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.5526647567749023, | |
| "eval_runtime": 208.5751, | |
| "eval_samples_per_second": 30.08, | |
| "eval_steps_per_second": 3.764, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5397, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.5280492305755615, | |
| "eval_runtime": 204.8306, | |
| "eval_samples_per_second": 30.63, | |
| "eval_steps_per_second": 3.832, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5165, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.507997512817383, | |
| "eval_runtime": 204.6726, | |
| "eval_samples_per_second": 30.654, | |
| "eval_steps_per_second": 3.835, | |
| "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 | |
| } | |