| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.99988665023095, |
| "global_step": 35288, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06, |
| "learning_rate": 2.9589095443210154e-06, |
| "loss": 1.4651, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 2.9178190886420315e-06, |
| "loss": 1.4652, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 2.876728632963047e-06, |
| "loss": 1.4649, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 2.8356381772840626e-06, |
| "loss": 1.4647, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 2.7945477216050783e-06, |
| "loss": 1.4646, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 2.753457265926094e-06, |
| "loss": 1.4648, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 2.7123668102471093e-06, |
| "loss": 1.4643, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 2.6712763545681255e-06, |
| "loss": 1.4643, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 2.6301858988891408e-06, |
| "loss": 1.464, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 2.589095443210156e-06, |
| "loss": 1.4639, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 2.5480049875311722e-06, |
| "loss": 1.4642, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 2.506914531852188e-06, |
| "loss": 1.4637, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 2.4658240761732033e-06, |
| "loss": 1.4639, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 2.424733620494219e-06, |
| "loss": 1.4639, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 2.3836431648152347e-06, |
| "loss": 1.4638, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 2.34255270913625e-06, |
| "loss": 1.4637, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 2.301462253457266e-06, |
| "loss": 1.4629, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.4708495140075684, |
| "eval_runtime": 265.1581, |
| "eval_samples_per_second": 107.54, |
| "eval_steps_per_second": 1.346, |
| "step": 8822 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 2.2603717977782815e-06, |
| "loss": 1.4631, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 2.219281342099297e-06, |
| "loss": 1.4621, |
| "step": 9500 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 2.178190886420313e-06, |
| "loss": 1.4621, |
| "step": 10000 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 2.1371004307413287e-06, |
| "loss": 1.4617, |
| "step": 10500 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 2.096009975062344e-06, |
| "loss": 1.4618, |
| "step": 11000 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 2.0549195193833597e-06, |
| "loss": 1.4622, |
| "step": 11500 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 2.0138290637043754e-06, |
| "loss": 1.4617, |
| "step": 12000 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 1.972738608025391e-06, |
| "loss": 1.4621, |
| "step": 12500 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 1.931648152346407e-06, |
| "loss": 1.4615, |
| "step": 13000 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 1.8905576966674222e-06, |
| "loss": 1.4615, |
| "step": 13500 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 1.8494672409884385e-06, |
| "loss": 1.4616, |
| "step": 14000 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 1.8083767853094543e-06, |
| "loss": 1.4615, |
| "step": 14500 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 1.7672863296304691e-06, |
| "loss": 1.4619, |
| "step": 15000 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 1.7261958739514849e-06, |
| "loss": 1.4613, |
| "step": 15500 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 1.6851054182725004e-06, |
| "loss": 1.4613, |
| "step": 16000 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 1.6440149625935161e-06, |
| "loss": 1.4615, |
| "step": 16500 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 1.6029245069145325e-06, |
| "loss": 1.4612, |
| "step": 17000 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 1.5618340512355474e-06, |
| "loss": 1.4613, |
| "step": 17500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.4701755046844482, |
| "eval_runtime": 263.8925, |
| "eval_samples_per_second": 108.055, |
| "eval_steps_per_second": 1.353, |
| "step": 17644 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 1.520743595556563e-06, |
| "loss": 1.4606, |
| "step": 18000 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 1.479653139877579e-06, |
| "loss": 1.4607, |
| "step": 18500 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 1.4385626841985943e-06, |
| "loss": 1.4602, |
| "step": 19000 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 1.39747222851961e-06, |
| "loss": 1.4603, |
| "step": 19500 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 1.3563817728406258e-06, |
| "loss": 1.4602, |
| "step": 20000 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 1.3152913171616415e-06, |
| "loss": 1.4602, |
| "step": 20500 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 1.2742008614826568e-06, |
| "loss": 1.46, |
| "step": 21000 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 1.233110405803673e-06, |
| "loss": 1.4599, |
| "step": 21500 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 1.1920199501246883e-06, |
| "loss": 1.4602, |
| "step": 22000 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 1.150929494445704e-06, |
| "loss": 1.46, |
| "step": 22500 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 1.1098390387667197e-06, |
| "loss": 1.4601, |
| "step": 23000 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 1.0687485830877354e-06, |
| "loss": 1.46, |
| "step": 23500 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 1.0276581274087507e-06, |
| "loss": 1.4601, |
| "step": 24000 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 9.865676717297667e-07, |
| "loss": 1.46, |
| "step": 24500 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 9.454772160507822e-07, |
| "loss": 1.4601, |
| "step": 25000 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 9.043867603717977e-07, |
| "loss": 1.4598, |
| "step": 25500 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 8.632963046928134e-07, |
| "loss": 1.4607, |
| "step": 26000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.4697959423065186, |
| "eval_runtime": 265.5519, |
| "eval_samples_per_second": 107.38, |
| "eval_steps_per_second": 1.344, |
| "step": 26466 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 8.22205849013829e-07, |
| "loss": 1.4597, |
| "step": 26500 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 7.811153933348447e-07, |
| "loss": 1.4589, |
| "step": 27000 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 7.400249376558603e-07, |
| "loss": 1.4592, |
| "step": 27500 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 6.989344819768761e-07, |
| "loss": 1.4594, |
| "step": 28000 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 6.578440262978915e-07, |
| "loss": 1.4595, |
| "step": 28500 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 6.167535706189074e-07, |
| "loss": 1.4593, |
| "step": 29000 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 5.756631149399229e-07, |
| "loss": 1.4595, |
| "step": 29500 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 5.345726592609387e-07, |
| "loss": 1.4592, |
| "step": 30000 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 4.934822035819541e-07, |
| "loss": 1.4595, |
| "step": 30500 |
| }, |
| { |
| "epoch": 3.51, |
| "learning_rate": 4.5239174790297e-07, |
| "loss": 1.4594, |
| "step": 31000 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 4.113012922239855e-07, |
| "loss": 1.4591, |
| "step": 31500 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 3.70210836545001e-07, |
| "loss": 1.4593, |
| "step": 32000 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 3.2912038086601684e-07, |
| "loss": 1.4595, |
| "step": 32500 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 2.880299251870323e-07, |
| "loss": 1.4595, |
| "step": 33000 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 2.4693946950804813e-07, |
| "loss": 1.4598, |
| "step": 33500 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 2.0584901382906362e-07, |
| "loss": 1.4593, |
| "step": 34000 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 1.6475855815007943e-07, |
| "loss": 1.459, |
| "step": 34500 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 1.2366810247109492e-07, |
| "loss": 1.4596, |
| "step": 35000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 1.4696872234344482, |
| "eval_runtime": 266.0179, |
| "eval_samples_per_second": 107.192, |
| "eval_steps_per_second": 1.342, |
| "step": 35288 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 35288, |
| "total_flos": 1.100521644337791e+18, |
| "train_loss": 1.461335124463566, |
| "train_runtime": 132050.7556, |
| "train_samples_per_second": 85.514, |
| "train_steps_per_second": 0.267 |
| } |
| ], |
| "max_steps": 35288, |
| "num_train_epochs": 4, |
| "total_flos": 1.100521644337791e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
