| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.918839153959666, | |
| "eval_steps": 500, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9385145105755044e-05, | |
| "loss": 8.6111, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.8770290211510086e-05, | |
| "loss": 8.9414, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.815543531726513e-05, | |
| "loss": 9.0231, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.754058042302017e-05, | |
| "loss": 8.756, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.692572552877521e-05, | |
| "loss": 8.6571, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.631087063453025e-05, | |
| "loss": 8.5083, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.56960157402853e-05, | |
| "loss": 8.4503, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.5081160846040335e-05, | |
| "loss": 8.3489, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.4466305951795377e-05, | |
| "loss": 8.2406, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.385145105755042e-05, | |
| "loss": 8.2487, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.323659616330546e-05, | |
| "loss": 8.1667, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.262174126906051e-05, | |
| "loss": 8.0874, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.200688637481554e-05, | |
| "loss": 8.0537, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.1392031480570584e-05, | |
| "loss": 8.0119, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.0777176586325626e-05, | |
| "loss": 7.94, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.0162321692080674e-05, | |
| "loss": 7.9435, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.9547466797835716e-05, | |
| "loss": 7.8516, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.893261190359076e-05, | |
| "loss": 7.7969, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.831775700934579e-05, | |
| "loss": 7.7974, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.7702902115100834e-05, | |
| "loss": 7.7728, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.708804722085588e-05, | |
| "loss": 7.6974, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.6473192326610924e-05, | |
| "loss": 7.6804, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.5858337432365965e-05, | |
| "loss": 7.676, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.5243482538121e-05, | |
| "loss": 7.6323, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.462862764387605e-05, | |
| "loss": 7.6116, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.401377274963109e-05, | |
| "loss": 7.574, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.339891785538613e-05, | |
| "loss": 7.5571, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.278406296114117e-05, | |
| "loss": 7.5299, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.2169208066896215e-05, | |
| "loss": 7.4822, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.1554353172651256e-05, | |
| "loss": 7.4693, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.09394982784063e-05, | |
| "loss": 7.4753, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.032464338416134e-05, | |
| "loss": 7.4058, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.9709788489916378e-05, | |
| "loss": 7.4351, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.9094933595671426e-05, | |
| "loss": 7.3385, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.8480078701426464e-05, | |
| "loss": 7.3167, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.7865223807181506e-05, | |
| "loss": 7.3194, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.7250368912936547e-05, | |
| "loss": 7.3105, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.663551401869159e-05, | |
| "loss": 7.2525, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.6020659124446634e-05, | |
| "loss": 7.2848, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.5405804230201675e-05, | |
| "loss": 7.2648, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.4790949335956714e-05, | |
| "loss": 7.2688, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.417609444171176e-05, | |
| "loss": 7.2292, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.35612395474668e-05, | |
| "loss": 7.229, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.294638465322184e-05, | |
| "loss": 7.2068, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.2331529758976883e-05, | |
| "loss": 7.1212, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.171667486473192e-05, | |
| "loss": 7.1578, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.1101819970486966e-05, | |
| "loss": 7.0875, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2.0486965076242008e-05, | |
| "loss": 7.1206, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1.987211018199705e-05, | |
| "loss": 7.1629, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.925725528775209e-05, | |
| "loss": 7.0788, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.8642400393507133e-05, | |
| "loss": 7.0787, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.8027545499262174e-05, | |
| "loss": 7.0581, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.741269060501722e-05, | |
| "loss": 6.9689, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.6797835710772257e-05, | |
| "loss": 7.0185, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.6182980816527302e-05, | |
| "loss": 6.9885, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.5568125922282344e-05, | |
| "loss": 6.9848, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.4953271028037382e-05, | |
| "loss": 6.9358, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.4338416133792425e-05, | |
| "loss": 6.9342, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.3723561239547467e-05, | |
| "loss": 6.94, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.310870634530251e-05, | |
| "loss": 6.9609, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.249385145105755e-05, | |
| "loss": 6.9132, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.1878996556812592e-05, | |
| "loss": 6.8702, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.1264141662567635e-05, | |
| "loss": 6.9124, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.0649286768322676e-05, | |
| "loss": 6.8865, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.0034431874077718e-05, | |
| "loss": 6.8776, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 9.41957697983276e-06, | |
| "loss": 6.8486, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 8.804722085587803e-06, | |
| "loss": 6.8326, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 8.189867191342844e-06, | |
| "loss": 6.8254, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 7.575012297097884e-06, | |
| "loss": 6.82, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 6.960157402852927e-06, | |
| "loss": 6.782, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 6.345302508607968e-06, | |
| "loss": 6.7768, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 5.730447614363011e-06, | |
| "loss": 6.841, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.115592720118052e-06, | |
| "loss": 6.8454, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.500737825873094e-06, | |
| "loss": 6.8015, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 3.885882931628136e-06, | |
| "loss": 6.8061, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 3.2710280373831774e-06, | |
| "loss": 6.8078, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.65617314313822e-06, | |
| "loss": 6.7983, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.0413182488932614e-06, | |
| "loss": 6.792, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 1.426463354648303e-06, | |
| "loss": 6.751, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 8.116084604033448e-07, | |
| "loss": 6.7829, | |
| "step": 40000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 40660, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10000, | |
| "total_flos": 1.0574867779746048e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |