| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.125, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9980725906018074e-05, | |
| "loss": 0.7547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.566, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.982671142387316e-05, | |
| "loss": 0.5632, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.5385, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 0.5242, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.4853, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.906138091134118e-05, | |
| "loss": 0.5078, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.519, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.8454783398062106e-05, | |
| "loss": 0.5759, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.5073, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.7703579345627035e-05, | |
| "loss": 0.4996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.498, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.681240017681993e-05, | |
| "loss": 0.5313, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.51, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.5786740307563636e-05, | |
| "loss": 0.5182, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.5222, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.463292327201862e-05, | |
| "loss": 0.3137, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.2685, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.335806273589214e-05, | |
| "loss": 0.2834, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.2713, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.197001863832355e-05, | |
| "loss": 0.2705, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.2517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.047734873274586e-05, | |
| "loss": 0.2626, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.2754, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.888925582549006e-05, | |
| "loss": 0.2645, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.2405, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.721553103742388e-05, | |
| "loss": 0.2412, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.2519, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.54664934384357e-05, | |
| "loss": 0.27, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.2511, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 3.365292642693732e-05, | |
| "loss": 0.2409, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.2486, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.178601124662686e-05, | |
| "loss": 0.1282, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.1339, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.9877258050403212e-05, | |
| "loss": 0.1175, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.109, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.7938434936445945e-05, | |
| "loss": 0.12, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.1263, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.598149539397672e-05, | |
| "loss": 0.1206, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1147, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.4018504606023293e-05, | |
| "loss": 0.1148, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.1162, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.2061565063554064e-05, | |
| "loss": 0.1083, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.117, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 2.0122741949596797e-05, | |
| "loss": 0.0933, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.1052, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.8213988753373146e-05, | |
| "loss": 0.1112, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.1048, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.6347073573062672e-05, | |
| "loss": 0.0463, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0518, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 160, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 20, | |
| "total_flos": 1.0844211055626813e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |