| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.7597626604112047, | |
| "eval_steps": 500, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.942504944574767e-05, | |
| "loss": 3.2985, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8850098891495336e-05, | |
| "loss": 3.1395, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8275148337242996e-05, | |
| "loss": 3.0915, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.770019778299066e-05, | |
| "loss": 3.0514, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.712524722873833e-05, | |
| "loss": 2.9975, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6550296674485996e-05, | |
| "loss": 2.9986, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.597534612023366e-05, | |
| "loss": 2.9464, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.540039556598133e-05, | |
| "loss": 2.9419, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4825445011728997e-05, | |
| "loss": 2.9467, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.425049445747666e-05, | |
| "loss": 2.9477, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.367554390322432e-05, | |
| "loss": 2.9098, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.310059334897199e-05, | |
| "loss": 2.9206, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.252564279471966e-05, | |
| "loss": 2.908, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.1950692240467324e-05, | |
| "loss": 2.8956, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1375741686214984e-05, | |
| "loss": 2.9077, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.080079113196265e-05, | |
| "loss": 2.8966, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.022584057771032e-05, | |
| "loss": 2.8607, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9650890023457984e-05, | |
| "loss": 2.8856, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.907593946920565e-05, | |
| "loss": 2.8774, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.850098891495332e-05, | |
| "loss": 2.8594, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.7926038360700984e-05, | |
| "loss": 2.8541, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.735108780644865e-05, | |
| "loss": 2.8643, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.677613725219631e-05, | |
| "loss": 2.8425, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.620118669794398e-05, | |
| "loss": 2.8535, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.5626236143691645e-05, | |
| "loss": 2.8506, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.505128558943931e-05, | |
| "loss": 2.8514, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.447633503518697e-05, | |
| "loss": 2.8401, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.390138448093464e-05, | |
| "loss": 2.8293, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3326433926682305e-05, | |
| "loss": 2.8031, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.275148337242998e-05, | |
| "loss": 2.704, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.217653281817764e-05, | |
| "loss": 2.7216, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1601582263925305e-05, | |
| "loss": 2.6997, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.102663170967297e-05, | |
| "loss": 2.6923, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.0451681155420635e-05, | |
| "loss": 2.7136, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9876730601168302e-05, | |
| "loss": 2.6984, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9301780046915966e-05, | |
| "loss": 2.7133, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8726829492663632e-05, | |
| "loss": 2.6969, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8151878938411296e-05, | |
| "loss": 2.6954, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7576928384158962e-05, | |
| "loss": 2.7024, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7001977829906626e-05, | |
| "loss": 2.7208, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.6427027275654293e-05, | |
| "loss": 2.683, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.5852076721401963e-05, | |
| "loss": 2.6896, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.527712616714963e-05, | |
| "loss": 2.7004, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.470217561289729e-05, | |
| "loss": 2.7053, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.412722505864496e-05, | |
| "loss": 2.6863, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.3552274504392623e-05, | |
| "loss": 2.6896, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.297732395014029e-05, | |
| "loss": 2.6897, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.2402373395887953e-05, | |
| "loss": 2.6733, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.182742284163562e-05, | |
| "loss": 2.684, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.1252472287383283e-05, | |
| "loss": 2.6966, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.0677521733130954e-05, | |
| "loss": 2.6691, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.0102571178878617e-05, | |
| "loss": 2.6901, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.9527620624626284e-05, | |
| "loss": 2.6852, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8952670070373947e-05, | |
| "loss": 2.679, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.8377719516121614e-05, | |
| "loss": 2.6777, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7802768961869277e-05, | |
| "loss": 2.6864, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7227818407616947e-05, | |
| "loss": 2.6714, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.665286785336461e-05, | |
| "loss": 2.681, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.6077917299112278e-05, | |
| "loss": 2.6028, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.550296674485994e-05, | |
| "loss": 2.5981, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.4928016190607608e-05, | |
| "loss": 2.5976, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.4353065636355273e-05, | |
| "loss": 2.5921, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3778115082102941e-05, | |
| "loss": 2.588, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3203164527850606e-05, | |
| "loss": 2.5888, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2628213973598271e-05, | |
| "loss": 2.6143, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.2053263419345937e-05, | |
| "loss": 2.5874, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1478312865093603e-05, | |
| "loss": 2.5905, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.0903362310841268e-05, | |
| "loss": 2.6078, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0328411756588933e-05, | |
| "loss": 2.5793, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.7534612023366e-06, | |
| "loss": 2.5968, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.178510648084265e-06, | |
| "loss": 2.595, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.60356009383193e-06, | |
| "loss": 2.5673, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.028609539579597e-06, | |
| "loss": 2.5954, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.453658985327262e-06, | |
| "loss": 2.5939, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 6.878708431074927e-06, | |
| "loss": 2.6008, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.303757876822594e-06, | |
| "loss": 2.6016, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 5.728807322570259e-06, | |
| "loss": 2.5827, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.153856768317925e-06, | |
| "loss": 2.5904, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.57890621406559e-06, | |
| "loss": 2.5745, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.003955659813256e-06, | |
| "loss": 2.5777, | |
| "step": 40000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 43482, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10000, | |
| "total_flos": 1.0451289341952e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |