| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.325, |
| "eval_steps": 500, |
| "global_step": 325, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005, |
| "grad_norm": 4.4095964431762695, |
| "learning_rate": 4.9800000000000004e-05, |
| "loss": 5.4329, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.658348798751831, |
| "learning_rate": 4.9550000000000005e-05, |
| "loss": 4.6734, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.015, |
| "grad_norm": 3.4242470264434814, |
| "learning_rate": 4.93e-05, |
| "loss": 4.8327, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 4.363213539123535, |
| "learning_rate": 4.905e-05, |
| "loss": 4.4238, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 2.531619071960449, |
| "learning_rate": 4.88e-05, |
| "loss": 3.9284, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 4.686695098876953, |
| "learning_rate": 4.855e-05, |
| "loss": 4.6794, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.035, |
| "grad_norm": 4.860099792480469, |
| "learning_rate": 4.83e-05, |
| "loss": 5.0624, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 8.296855926513672, |
| "learning_rate": 4.805e-05, |
| "loss": 4.8011, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.045, |
| "grad_norm": 4.80878210067749, |
| "learning_rate": 4.78e-05, |
| "loss": 5.495, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 4.766687393188477, |
| "learning_rate": 4.755e-05, |
| "loss": 4.6778, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.055, |
| "grad_norm": 2.7137186527252197, |
| "learning_rate": 4.73e-05, |
| "loss": 4.5044, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 9.891243934631348, |
| "learning_rate": 4.705e-05, |
| "loss": 4.4744, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.065, |
| "grad_norm": 3.6516237258911133, |
| "learning_rate": 4.6800000000000006e-05, |
| "loss": 4.6576, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 5.687813758850098, |
| "learning_rate": 4.655000000000001e-05, |
| "loss": 5.1204, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 4.273693561553955, |
| "learning_rate": 4.630000000000001e-05, |
| "loss": 5.361, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 6.802962779998779, |
| "learning_rate": 4.605e-05, |
| "loss": 5.5483, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.085, |
| "grad_norm": 2.7016360759735107, |
| "learning_rate": 4.58e-05, |
| "loss": 4.5909, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 8.201666831970215, |
| "learning_rate": 4.555e-05, |
| "loss": 4.2807, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.095, |
| "grad_norm": 3.8271970748901367, |
| "learning_rate": 4.53e-05, |
| "loss": 5.5645, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 3.17282772064209, |
| "learning_rate": 4.5050000000000004e-05, |
| "loss": 4.5845, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.105, |
| "grad_norm": 2.9256932735443115, |
| "learning_rate": 4.4800000000000005e-05, |
| "loss": 4.6003, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.11, |
| "grad_norm": 10.4873046875, |
| "learning_rate": 4.4550000000000005e-05, |
| "loss": 4.6453, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.115, |
| "grad_norm": 2.9158883094787598, |
| "learning_rate": 4.43e-05, |
| "loss": 4.8935, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 3.5588793754577637, |
| "learning_rate": 4.405e-05, |
| "loss": 3.9582, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 2.7040491104125977, |
| "learning_rate": 4.38e-05, |
| "loss": 4.6688, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.13, |
| "grad_norm": 3.1420748233795166, |
| "learning_rate": 4.355e-05, |
| "loss": 4.5591, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.135, |
| "grad_norm": 2.023017168045044, |
| "learning_rate": 4.33e-05, |
| "loss": 4.5944, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 2.902434825897217, |
| "learning_rate": 4.305e-05, |
| "loss": 5.4079, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.145, |
| "grad_norm": 2.4470090866088867, |
| "learning_rate": 4.2800000000000004e-05, |
| "loss": 4.9259, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 4.8970046043396, |
| "learning_rate": 4.2550000000000004e-05, |
| "loss": 4.6465, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.155, |
| "grad_norm": 2.197767734527588, |
| "learning_rate": 4.23e-05, |
| "loss": 4.6841, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 4.577955722808838, |
| "learning_rate": 4.205e-05, |
| "loss": 4.1775, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.165, |
| "grad_norm": 2.3383991718292236, |
| "learning_rate": 4.18e-05, |
| "loss": 4.0309, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.17, |
| "grad_norm": 3.794187307357788, |
| "learning_rate": 4.155e-05, |
| "loss": 4.5336, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 4.427373886108398, |
| "learning_rate": 4.13e-05, |
| "loss": 4.241, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 2.8116564750671387, |
| "learning_rate": 4.105e-05, |
| "loss": 4.7562, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.185, |
| "grad_norm": 5.841445446014404, |
| "learning_rate": 4.08e-05, |
| "loss": 3.7034, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 20.96999740600586, |
| "learning_rate": 4.055e-05, |
| "loss": 5.1727, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.195, |
| "grad_norm": 11.743700981140137, |
| "learning_rate": 4.0300000000000004e-05, |
| "loss": 5.1553, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 10.230498313903809, |
| "learning_rate": 4.0050000000000004e-05, |
| "loss": 4.8657, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.205, |
| "grad_norm": 5.706521987915039, |
| "learning_rate": 3.9800000000000005e-05, |
| "loss": 4.3638, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 5.781250476837158, |
| "learning_rate": 3.9550000000000006e-05, |
| "loss": 4.3452, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.215, |
| "grad_norm": 2.371096611022949, |
| "learning_rate": 3.9300000000000007e-05, |
| "loss": 4.6681, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 4.352181911468506, |
| "learning_rate": 3.905e-05, |
| "loss": 4.2025, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.225, |
| "grad_norm": 4.531359672546387, |
| "learning_rate": 3.88e-05, |
| "loss": 4.5391, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.23, |
| "grad_norm": 6.948793411254883, |
| "learning_rate": 3.855e-05, |
| "loss": 4.0233, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.235, |
| "grad_norm": 4.765657424926758, |
| "learning_rate": 3.83e-05, |
| "loss": 4.1225, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 3.838766574859619, |
| "learning_rate": 3.805e-05, |
| "loss": 4.9202, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.245, |
| "grad_norm": 6.471155643463135, |
| "learning_rate": 3.7800000000000004e-05, |
| "loss": 4.7561, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 5.748368740081787, |
| "learning_rate": 3.7550000000000005e-05, |
| "loss": 3.7783, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.255, |
| "grad_norm": 2.663558006286621, |
| "learning_rate": 3.73e-05, |
| "loss": 4.1553, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 3.4103472232818604, |
| "learning_rate": 3.705e-05, |
| "loss": 4.9314, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.265, |
| "grad_norm": 6.4364824295043945, |
| "learning_rate": 3.68e-05, |
| "loss": 4.4708, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.27, |
| "grad_norm": 4.145668983459473, |
| "learning_rate": 3.655e-05, |
| "loss": 4.5879, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.275, |
| "grad_norm": 3.4401297569274902, |
| "learning_rate": 3.63e-05, |
| "loss": 4.7668, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 9.18470287322998, |
| "learning_rate": 3.605e-05, |
| "loss": 4.619, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.285, |
| "grad_norm": 4.180783748626709, |
| "learning_rate": 3.58e-05, |
| "loss": 3.8878, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 7.336719036102295, |
| "learning_rate": 3.555e-05, |
| "loss": 4.5864, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.295, |
| "grad_norm": 4.498530864715576, |
| "learning_rate": 3.53e-05, |
| "loss": 3.8987, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 3.3154962062835693, |
| "learning_rate": 3.505e-05, |
| "loss": 4.5049, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.305, |
| "grad_norm": 5.832047462463379, |
| "learning_rate": 3.48e-05, |
| "loss": 5.0849, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.31, |
| "grad_norm": 17.935897827148438, |
| "learning_rate": 3.455e-05, |
| "loss": 4.8395, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.315, |
| "grad_norm": 8.821608543395996, |
| "learning_rate": 3.430000000000001e-05, |
| "loss": 4.9111, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 4.014020919799805, |
| "learning_rate": 3.405e-05, |
| "loss": 3.6753, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.325, |
| "grad_norm": 7.319735050201416, |
| "learning_rate": 3.38e-05, |
| "loss": 4.6448, |
| "step": 325 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 110513199513600.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
