| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.30120481927710846, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.924698795180723e-05, | |
| "loss": 1.305, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8493975903614455e-05, | |
| "loss": 1.1432, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.774096385542169e-05, | |
| "loss": 1.0734, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.698795180722892e-05, | |
| "loss": 1.0555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6234939759036145e-05, | |
| "loss": 1.0151, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5481927710843374e-05, | |
| "loss": 1.1434, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4728915662650604e-05, | |
| "loss": 1.0396, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.3975903614457834e-05, | |
| "loss": 1.0922, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3222891566265064e-05, | |
| "loss": 1.047, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2469879518072294e-05, | |
| "loss": 1.0364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1716867469879523e-05, | |
| "loss": 1.0541, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.0963855421686746e-05, | |
| "loss": 0.9778, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0210843373493976e-05, | |
| "loss": 1.0168, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9457831325301206e-05, | |
| "loss": 1.0563, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.8704819277108436e-05, | |
| "loss": 0.9837, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.7951807228915666e-05, | |
| "loss": 0.9251, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7198795180722895e-05, | |
| "loss": 1.0495, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.644578313253012e-05, | |
| "loss": 1.0544, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.569277108433735e-05, | |
| "loss": 1.0473, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.4939759036144585e-05, | |
| "loss": 0.972, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 664, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "total_flos": 2.7583655706624e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |