| { | |
| "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": 1.7265625, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9969, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.1170578002929688, | |
| "eval_runtime": 0.4884, | |
| "eval_samples_per_second": 20.475, | |
| "eval_steps_per_second": 2.047, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.390625, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.5079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.849125862121582, | |
| "eval_runtime": 0.5022, | |
| "eval_samples_per_second": 19.912, | |
| "eval_steps_per_second": 1.991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.2109375, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.1709, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.725147247314453, | |
| "eval_runtime": 0.5172, | |
| "eval_samples_per_second": 19.335, | |
| "eval_steps_per_second": 1.934, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.6266896724700928, | |
| "eval_runtime": 0.5348, | |
| "eval_samples_per_second": 18.699, | |
| "eval_steps_per_second": 1.87, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.7591, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.5900256633758545, | |
| "eval_runtime": 0.5346, | |
| "eval_samples_per_second": 18.707, | |
| "eval_steps_per_second": 1.871, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.6527, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.590770721435547, | |
| "eval_runtime": 0.5433, | |
| "eval_samples_per_second": 18.406, | |
| "eval_steps_per_second": 1.841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.341796875, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5938, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.5816967487335205, | |
| "eval_runtime": 0.5475, | |
| "eval_samples_per_second": 18.265, | |
| "eval_steps_per_second": 1.826, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.322265625, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.5589, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.5729336738586426, | |
| "eval_runtime": 0.5448, | |
| "eval_samples_per_second": 18.356, | |
| "eval_steps_per_second": 1.836, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.287109375, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.5434, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.5688018798828125, | |
| "eval_runtime": 0.5464, | |
| "eval_samples_per_second": 18.302, | |
| "eval_steps_per_second": 1.83, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.310546875, | |
| "learning_rate": 0.0, | |
| "loss": 1.5362, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.5693273544311523, | |
| "eval_runtime": 0.5446, | |
| "eval_samples_per_second": 18.363, | |
| "eval_steps_per_second": 1.836, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 50, | |
| "total_flos": 2.9368666998964224e+16, | |
| "train_loss": 1.9250271797180176, | |
| "train_runtime": 273.2217, | |
| "train_samples_per_second": 8.052, | |
| "train_steps_per_second": 0.183 | |
| } | |
| ], | |
| "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 | |
| } | |