| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026928471248246846, | |
| "eval_steps": 6, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011220196353436186, | |
| "grad_norm": 0.6813791394233704, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1705, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011220196353436186, | |
| "eval_loss": 2.0811240673065186, | |
| "eval_runtime": 12.7097, | |
| "eval_samples_per_second": 29.584, | |
| "eval_steps_per_second": 14.792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002244039270687237, | |
| "grad_norm": 0.4890865683555603, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9746, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033660589060308557, | |
| "grad_norm": 0.8481997847557068, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2087, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004488078541374474, | |
| "grad_norm": 0.40311843156814575, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0627, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005610098176718092, | |
| "grad_norm": 0.5440235733985901, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1454, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006732117812061711, | |
| "grad_norm": 0.3888591229915619, | |
| "learning_rate": 0.00012, | |
| "loss": 2.366, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006732117812061711, | |
| "eval_loss": 2.0609025955200195, | |
| "eval_runtime": 12.7241, | |
| "eval_samples_per_second": 29.55, | |
| "eval_steps_per_second": 14.775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00785413744740533, | |
| "grad_norm": 0.6480532288551331, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008976157082748949, | |
| "grad_norm": 0.6572309136390686, | |
| "learning_rate": 0.00016, | |
| "loss": 2.3367, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010098176718092567, | |
| "grad_norm": 0.4551832973957062, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9394, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011220196353436185, | |
| "grad_norm": 0.6103149652481079, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012342215988779803, | |
| "grad_norm": 0.7382659912109375, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 1.862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013464235624123423, | |
| "grad_norm": 0.4550475478172302, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 2.2914, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013464235624123423, | |
| "eval_loss": 1.8999028205871582, | |
| "eval_runtime": 13.0197, | |
| "eval_samples_per_second": 28.879, | |
| "eval_steps_per_second": 14.44, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014586255259467041, | |
| "grad_norm": 0.44409334659576416, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 1.6056, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01570827489481066, | |
| "grad_norm": 0.7820721864700317, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 1.696, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016830294530154277, | |
| "grad_norm": 0.9811131358146667, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 1.5621, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017952314165497897, | |
| "grad_norm": 0.8004341721534729, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 1.8898, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019074333800841514, | |
| "grad_norm": 0.6704489588737488, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8404, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020196353436185133, | |
| "grad_norm": 0.6039404273033142, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 1.8087, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020196353436185133, | |
| "eval_loss": 1.8163129091262817, | |
| "eval_runtime": 12.9895, | |
| "eval_samples_per_second": 28.946, | |
| "eval_steps_per_second": 14.473, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021318373071528753, | |
| "grad_norm": 0.5095430016517639, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 1.6128, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02244039270687237, | |
| "grad_norm": 0.6485509872436523, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 1.885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02356241234221599, | |
| "grad_norm": 0.6329189538955688, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 1.9701, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024684431977559606, | |
| "grad_norm": 0.5708733201026917, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 2.4112, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025806451612903226, | |
| "grad_norm": 0.7266702055931091, | |
| "learning_rate": 2.5072087818176382e-06, | |
| "loss": 1.5506, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026928471248246846, | |
| "grad_norm": 0.7287759780883789, | |
| "learning_rate": 0.0, | |
| "loss": 2.0879, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026928471248246846, | |
| "eval_loss": 1.8048760890960693, | |
| "eval_runtime": 12.9656, | |
| "eval_samples_per_second": 29.0, | |
| "eval_steps_per_second": 14.5, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 24, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1679736258428928.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |