| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 4e-05, | |
| "loss": 3.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.65625, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9978, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.1071324348449707, | |
| "eval_runtime": 0.5233, | |
| "eval_samples_per_second": 19.11, | |
| "eval_steps_per_second": 1.911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.5123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.8502731323242188, | |
| "eval_runtime": 0.5332, | |
| "eval_samples_per_second": 18.755, | |
| "eval_steps_per_second": 1.876, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.5, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.2077, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.715447425842285, | |
| "eval_runtime": 0.5429, | |
| "eval_samples_per_second": 18.419, | |
| "eval_steps_per_second": 1.842, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9749, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.6506550312042236, | |
| "eval_runtime": 0.54, | |
| "eval_samples_per_second": 18.517, | |
| "eval_steps_per_second": 1.852, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.8015, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.624201536178589, | |
| "eval_runtime": 0.557, | |
| "eval_samples_per_second": 17.953, | |
| "eval_steps_per_second": 1.795, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.369140625, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.6817, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.610503673553467, | |
| "eval_runtime": 0.5392, | |
| "eval_samples_per_second": 18.546, | |
| "eval_steps_per_second": 1.855, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.365234375, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.6095, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.600292682647705, | |
| "eval_runtime": 0.5472, | |
| "eval_samples_per_second": 18.276, | |
| "eval_steps_per_second": 1.828, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.466796875, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.5701, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.5916552543640137, | |
| "eval_runtime": 0.5514, | |
| "eval_samples_per_second": 18.135, | |
| "eval_steps_per_second": 1.813, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.3046875, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.5524, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.5882315635681152, | |
| "eval_runtime": 0.5445, | |
| "eval_samples_per_second": 18.366, | |
| "eval_steps_per_second": 1.837, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.322265625, | |
| "learning_rate": 0.0, | |
| "loss": 1.5443, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.587819814682007, | |
| "eval_runtime": 0.5585, | |
| "eval_samples_per_second": 17.905, | |
| "eval_steps_per_second": 1.79, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 50, | |
| "total_flos": 2.9368666998964224e+16, | |
| "train_loss": 1.9452767181396484, | |
| "train_runtime": 274.5975, | |
| "train_samples_per_second": 8.012, | |
| "train_steps_per_second": 0.182 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.9368666998964224e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |