| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009000393767227317, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004500196883613658, | |
| "grad_norm": 0.2620968818664551, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004500196883613658, | |
| "eval_loss": 0.7203913331031799, | |
| "eval_runtime": 1347.4567, | |
| "eval_samples_per_second": 11.11, | |
| "eval_steps_per_second": 2.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009000393767227316, | |
| "grad_norm": 0.2600632607936859, | |
| "learning_rate": 2e-05, | |
| "loss": 0.672, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013500590650840974, | |
| "grad_norm": 0.24837380647659302, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6396, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018000787534454632, | |
| "grad_norm": 0.27130672335624695, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6737, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022500984418068293, | |
| "grad_norm": 0.2528882324695587, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6544, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022500984418068293, | |
| "eval_loss": 0.7098342776298523, | |
| "eval_runtime": 1347.4723, | |
| "eval_samples_per_second": 11.11, | |
| "eval_steps_per_second": 2.778, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002700118130168195, | |
| "grad_norm": 0.23115503787994385, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5711, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003150137818529561, | |
| "grad_norm": 0.25062692165374756, | |
| "learning_rate": 7e-05, | |
| "loss": 0.6868, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0036001575068909265, | |
| "grad_norm": 0.21780619025230408, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6653, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004050177195252292, | |
| "grad_norm": 0.21652354300022125, | |
| "learning_rate": 9e-05, | |
| "loss": 0.606, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0045001968836136585, | |
| "grad_norm": 0.2677552402019501, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0045001968836136585, | |
| "eval_loss": 0.6517220735549927, | |
| "eval_runtime": 1347.593, | |
| "eval_samples_per_second": 11.109, | |
| "eval_steps_per_second": 2.778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004950216571975024, | |
| "grad_norm": 0.26608362793922424, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.6342, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00540023626033639, | |
| "grad_norm": 0.22158242762088776, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.639, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005850255948697755, | |
| "grad_norm": 0.23818451166152954, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.5802, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006300275637059122, | |
| "grad_norm": 0.22042547166347504, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.5583, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006750295325420487, | |
| "grad_norm": 0.19996048510074615, | |
| "learning_rate": 5e-05, | |
| "loss": 0.535, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006750295325420487, | |
| "eval_loss": 0.610110342502594, | |
| "eval_runtime": 1347.8184, | |
| "eval_samples_per_second": 11.107, | |
| "eval_steps_per_second": 2.777, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007200315013781853, | |
| "grad_norm": 0.18081465363502502, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.5724, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0076503347021432185, | |
| "grad_norm": 0.18684270977973938, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.574, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008100354390504584, | |
| "grad_norm": 0.17502309381961823, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.5845, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00855037407886595, | |
| "grad_norm": 0.15463897585868835, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.5625, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009000393767227317, | |
| "grad_norm": 0.13522151112556458, | |
| "learning_rate": 0.0, | |
| "loss": 0.5595, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009000393767227317, | |
| "eval_loss": 0.6022763252258301, | |
| "eval_runtime": 1347.8866, | |
| "eval_samples_per_second": 11.106, | |
| "eval_steps_per_second": 2.777, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.748078614786867e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |