| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9990680335507922, | |
| "eval_steps": 500, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.6262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9987954562051724e-05, | |
| "loss": 1.6549, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.989176509964781e-05, | |
| "loss": 1.6926, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9700312531945444e-05, | |
| "loss": 1.6159, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.941544065183021e-05, | |
| "loss": 1.3612, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.9039892931234434e-05, | |
| "loss": 1.7452, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.8577286100002723e-05, | |
| "loss": 2.2381, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.803207531480645e-05, | |
| "loss": 3.1504, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.7409511253549592e-05, | |
| "loss": 2.0864, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.6715589548470187e-05, | |
| "loss": 1.5856, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.5956993044924334e-05, | |
| "loss": 1.5722, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.5141027441932217e-05, | |
| "loss": 1.5654, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.4275550934302822e-05, | |
| "loss": 1.5932, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.3368898533922202e-05, | |
| "loss": 1.9197, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.242980179903264e-05, | |
| "loss": 2.3697, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.1467304744553618e-05, | |
| "loss": 2.975, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0490676743274181e-05, | |
| "loss": 2.5185, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.50932325672582e-06, | |
| "loss": 1.9642, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.532695255446384e-06, | |
| "loss": 1.6161, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.570198200967363e-06, | |
| "loss": 1.5248, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.631101466077801e-06, | |
| "loss": 1.4393, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.724449065697182e-06, | |
| "loss": 1.823, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.858972558067784e-06, | |
| "loss": 2.1982, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.043006955075667e-06, | |
| "loss": 3.0005, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.284410451529816e-06, | |
| "loss": 2.8139, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.5904887464504115e-06, | |
| "loss": 1.6601, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.967924685193552e-06, | |
| "loss": 1.4221, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4227138999972801e-06, | |
| "loss": 1.7112, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.601070687655667e-07, | |
| "loss": 1.5428, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.845593481697931e-07, | |
| "loss": 1.5406, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.996874680545603e-07, | |
| "loss": 1.8368, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.0823490035218986e-07, | |
| "loss": 2.6137, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.2045437948275952e-08, | |
| "loss": 1.5788, | |
| "step": 66 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 67, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 4694799827656704.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |