| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.48136910969944, | |
| "eval_steps": 50000, | |
| "global_step": 400000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.940766331658292e-05, | |
| "loss": 1.1651, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.026120662689209, | |
| "eval_runtime": 1432.5553, | |
| "eval_samples_per_second": 104.708, | |
| "eval_steps_per_second": 1.636, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 4.940763961316014e-05, | |
| "loss": 1.0237, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.9803563356399536, | |
| "eval_runtime": 1376.4724, | |
| "eval_samples_per_second": 108.974, | |
| "eval_steps_per_second": 1.703, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 4.940766331658292e-05, | |
| "loss": 0.9833, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_loss": 0.9588034152984619, | |
| "eval_runtime": 1376.5573, | |
| "eval_samples_per_second": 108.967, | |
| "eval_steps_per_second": 1.703, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.9407651464871526e-05, | |
| "loss": 0.9592, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 0.944024384021759, | |
| "eval_runtime": 1372.4075, | |
| "eval_samples_per_second": 109.297, | |
| "eval_steps_per_second": 1.708, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 4.94076751682943e-05, | |
| "loss": 0.9411, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 0.9341336488723755, | |
| "eval_runtime": 1371.037, | |
| "eval_samples_per_second": 109.406, | |
| "eval_steps_per_second": 1.71, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 4.940766331658292e-05, | |
| "loss": 0.9263, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 0.9277684092521667, | |
| "eval_runtime": 1370.7524, | |
| "eval_samples_per_second": 109.429, | |
| "eval_steps_per_second": 1.71, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.9407651464871526e-05, | |
| "loss": 0.9129, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "eval_loss": 0.9227856993675232, | |
| "eval_runtime": 1365.4307, | |
| "eval_samples_per_second": 109.855, | |
| "eval_steps_per_second": 1.717, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 4.940766331658292e-05, | |
| "loss": 0.9026, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "eval_loss": 0.9180548787117004, | |
| "eval_runtime": 1373.3191, | |
| "eval_samples_per_second": 109.224, | |
| "eval_steps_per_second": 1.707, | |
| "step": 400000 | |
| } | |
| ], | |
| "logging_steps": 50000, | |
| "max_steps": 4218800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 50000, | |
| "total_flos": 8.36125095886848e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |