| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006895600606812853, | |
| "eval_steps": 3, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027582402427251415, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027582402427251415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.4827, | |
| "eval_samples_per_second": 13.12, | |
| "eval_steps_per_second": 3.28, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005516480485450283, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008274720728175424, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.565217391304348e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008274720728175424, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.5182, | |
| "eval_samples_per_second": 13.119, | |
| "eval_steps_per_second": 3.28, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011032960970900566, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.130434782608696e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013791201213625708, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.695652173913044e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016549441456350847, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.260869565217392e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016549441456350847, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.4071, | |
| "eval_samples_per_second": 13.122, | |
| "eval_steps_per_second": 3.281, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019307681699075989, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.82608695652174e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022065921941801132, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.391304347826086e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024824162184526274, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.956521739130436e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024824162184526274, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.307, | |
| "eval_samples_per_second": 13.125, | |
| "eval_steps_per_second": 3.282, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027582402427251415, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.521739130434783e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030340642669976557, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.086956521739131e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033098882912701694, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.652173913043478e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033098882912701694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.5583, | |
| "eval_samples_per_second": 13.118, | |
| "eval_steps_per_second": 3.28, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0035857123155426836, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.217391304347826e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0038615363398151977, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.782608695652174e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004137360364087712, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004137360364087712, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.7462, | |
| "eval_samples_per_second": 13.112, | |
| "eval_steps_per_second": 3.279, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0044131843883602265, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.91304347826087e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00468900841263274, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.478260869565218e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004964832436905255, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0434782608695656e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004964832436905255, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.4315, | |
| "eval_samples_per_second": 13.121, | |
| "eval_steps_per_second": 3.281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0052406564611777685, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.608695652173913e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005516480485450283, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005792304509722797, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.739130434782609e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005792304509722797, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.326, | |
| "eval_samples_per_second": 13.124, | |
| "eval_steps_per_second": 3.282, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006068128533995311, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3043478260869566e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006343952558267825, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006619776582540339, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006619776582540339, | |
| "eval_loss": NaN, | |
| "eval_runtime": 465.4109, | |
| "eval_samples_per_second": 13.122, | |
| "eval_steps_per_second": 3.281, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006895600606812853, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 385666252800.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |