| { | |
| "best_metric": 0.1812729686498642, | |
| "best_model_checkpoint": "FlogLlama/checkpoint-20", | |
| "epoch": 0.00045625381399672636, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3971, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018888888888888888, | |
| "loss": 1.2405, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 1.0586, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.871, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.6519, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014444444444444444, | |
| "loss": 0.5204, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.4855, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012222222222222224, | |
| "loss": 0.3206, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.2322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.268, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.124, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.0913, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.1858, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.1198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1833, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1083, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1569, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2545, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 0.1812729686498642, | |
| "eval_runtime": 47728.0562, | |
| "eval_samples_per_second": 1.725, | |
| "eval_steps_per_second": 1.725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "step": 20, | |
| "total_flos": 4403583988776960.0, | |
| "train_loss": 0.4899760320782661, | |
| "train_runtime": 47871.6097, | |
| "train_samples_per_second": 0.002, | |
| "train_steps_per_second": 0.0 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 4403583988776960.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |