| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00663858036512192, | |
| "eval_steps": 13, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025533001404315077, | |
| "grad_norm": 0.6356120705604553, | |
| "learning_rate": 5e-06, | |
| "loss": 44.3634, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025533001404315077, | |
| "eval_loss": 11.092207908630371, | |
| "eval_runtime": 4.4694, | |
| "eval_samples_per_second": 368.951, | |
| "eval_steps_per_second": 184.587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005106600280863015, | |
| "grad_norm": 0.5739763975143433, | |
| "learning_rate": 1e-05, | |
| "loss": 44.3397, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007659900421294523, | |
| "grad_norm": 0.5774300694465637, | |
| "learning_rate": 1.5e-05, | |
| "loss": 44.3605, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001021320056172603, | |
| "grad_norm": 0.7528806924819946, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3484, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012766500702157538, | |
| "grad_norm": 0.5565564036369324, | |
| "learning_rate": 2.5e-05, | |
| "loss": 44.3484, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015319800842589046, | |
| "grad_norm": 0.5334393382072449, | |
| "learning_rate": 3e-05, | |
| "loss": 44.3429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017873100983020554, | |
| "grad_norm": 0.5663673281669617, | |
| "learning_rate": 3.5e-05, | |
| "loss": 44.3466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002042640112345206, | |
| "grad_norm": 0.5675923824310303, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3318, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002297970126388357, | |
| "grad_norm": 0.5051159262657166, | |
| "learning_rate": 4.5e-05, | |
| "loss": 44.3295, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025533001404315077, | |
| "grad_norm": 0.5161178112030029, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3284, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028086301544746587, | |
| "grad_norm": 0.4618953764438629, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 44.3585, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003063960168517809, | |
| "grad_norm": 0.6032963991165161, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 44.3768, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00331929018256096, | |
| "grad_norm": 0.5403372645378113, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 44.3579, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00331929018256096, | |
| "eval_loss": 11.091602325439453, | |
| "eval_runtime": 3.5459, | |
| "eval_samples_per_second": 465.044, | |
| "eval_steps_per_second": 232.663, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0035746201966041107, | |
| "grad_norm": 0.593859076499939, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 44.3825, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0038299502106472617, | |
| "grad_norm": 0.6427613496780396, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 44.3755, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004085280224690412, | |
| "grad_norm": 0.6255062222480774, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 44.369, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004340610238733563, | |
| "grad_norm": 0.627750039100647, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 44.3665, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004595940252776714, | |
| "grad_norm": 0.5742212533950806, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 44.3836, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004851270266819864, | |
| "grad_norm": 0.6519846320152283, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 44.3914, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005106600280863015, | |
| "grad_norm": 0.5559941530227661, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 44.3478, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005361930294906166, | |
| "grad_norm": 0.576760470867157, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 44.3521, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005617260308949317, | |
| "grad_norm": 0.8383557200431824, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 44.3474, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005872590322992467, | |
| "grad_norm": 0.5783092379570007, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 44.3559, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006127920337035618, | |
| "grad_norm": 0.5727637410163879, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 44.4125, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006383250351078769, | |
| "grad_norm": 0.610941469669342, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 44.3396, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00663858036512192, | |
| "grad_norm": 0.734337329864502, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 44.3969, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00663858036512192, | |
| "eval_loss": 11.090802192687988, | |
| "eval_runtime": 3.6364, | |
| "eval_samples_per_second": 453.472, | |
| "eval_steps_per_second": 226.873, | |
| "step": 26 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19424870400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |