| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000127712289753643, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2771228975364299e-05, | |
| "grad_norm": 0.993276059627533, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.2771228975364299e-05, | |
| "eval_loss": 3.49228572845459, | |
| "eval_runtime": 309.0228, | |
| "eval_samples_per_second": 106.688, | |
| "eval_steps_per_second": 53.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.5542457950728598e-05, | |
| "grad_norm": 1.040056824684143, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.8313686926092896e-05, | |
| "grad_norm": 0.9533179402351379, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4283, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.8313686926092896e-05, | |
| "eval_loss": 3.4902663230895996, | |
| "eval_runtime": 306.0416, | |
| "eval_samples_per_second": 107.727, | |
| "eval_steps_per_second": 53.865, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.1084915901457196e-05, | |
| "grad_norm": 0.9242367148399353, | |
| "learning_rate": 8e-05, | |
| "loss": 3.4517, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.38561448768215e-05, | |
| "grad_norm": 1.0459100008010864, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3989, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.662737385218579e-05, | |
| "grad_norm": 1.0111087560653687, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2861, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.662737385218579e-05, | |
| "eval_loss": 3.456946611404419, | |
| "eval_runtime": 309.2308, | |
| "eval_samples_per_second": 106.616, | |
| "eval_steps_per_second": 53.31, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 8.93986028275501e-05, | |
| "grad_norm": 1.0014288425445557, | |
| "learning_rate": 0.00014, | |
| "loss": 3.6833, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00010216983180291439, | |
| "grad_norm": 1.045379877090454, | |
| "learning_rate": 0.00016, | |
| "loss": 3.5056, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001149410607782787, | |
| "grad_norm": 0.9838472604751587, | |
| "learning_rate": 0.00018, | |
| "loss": 3.4775, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001149410607782787, | |
| "eval_loss": 3.342834711074829, | |
| "eval_runtime": 308.7743, | |
| "eval_samples_per_second": 106.774, | |
| "eval_steps_per_second": 53.389, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000127712289753643, | |
| "grad_norm": 0.944915771484375, | |
| "learning_rate": 0.0002, | |
| "loss": 3.4131, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 34292650475520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |