| { | |
| "best_metric": 1.9613432884216309, | |
| "best_model_checkpoint": "./outputs/checkpoint-2100", | |
| "epoch": 2.9829545454545454, | |
| "eval_steps": 100, | |
| "global_step": 2100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5435, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 2.2340614795684814, | |
| "eval_runtime": 54.1619, | |
| "eval_samples_per_second": 27.547, | |
| "eval_steps_per_second": 3.453, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3658, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.193166971206665, | |
| "eval_runtime": 51.9149, | |
| "eval_samples_per_second": 28.739, | |
| "eval_steps_per_second": 3.602, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 2.335, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 2.1651222705841064, | |
| "eval_runtime": 51.9178, | |
| "eval_samples_per_second": 28.738, | |
| "eval_steps_per_second": 3.602, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3016, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 2.1437063217163086, | |
| "eval_runtime": 52.0427, | |
| "eval_samples_per_second": 28.669, | |
| "eval_steps_per_second": 3.593, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2801, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 2.1198127269744873, | |
| "eval_runtime": 51.8718, | |
| "eval_samples_per_second": 28.763, | |
| "eval_steps_per_second": 3.605, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2632, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 2.100426197052002, | |
| "eval_runtime": 51.8813, | |
| "eval_samples_per_second": 28.758, | |
| "eval_steps_per_second": 3.604, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2421, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.0882084369659424, | |
| "eval_runtime": 51.8914, | |
| "eval_samples_per_second": 28.752, | |
| "eval_steps_per_second": 3.604, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 2.207, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 2.07395076751709, | |
| "eval_runtime": 51.9153, | |
| "eval_samples_per_second": 28.739, | |
| "eval_steps_per_second": 3.602, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1805, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 2.0585548877716064, | |
| "eval_runtime": 51.8541, | |
| "eval_samples_per_second": 28.773, | |
| "eval_steps_per_second": 3.606, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1797, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 2.0468482971191406, | |
| "eval_runtime": 51.913, | |
| "eval_samples_per_second": 28.74, | |
| "eval_steps_per_second": 3.602, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1872, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 2.037107467651367, | |
| "eval_runtime": 52.0873, | |
| "eval_samples_per_second": 28.644, | |
| "eval_steps_per_second": 3.59, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1651, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 2.0301010608673096, | |
| "eval_runtime": 51.8485, | |
| "eval_samples_per_second": 28.776, | |
| "eval_steps_per_second": 3.607, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1465, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 2.0145328044891357, | |
| "eval_runtime": 51.9711, | |
| "eval_samples_per_second": 28.708, | |
| "eval_steps_per_second": 3.598, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1501, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.0102152824401855, | |
| "eval_runtime": 51.9656, | |
| "eval_samples_per_second": 28.711, | |
| "eval_steps_per_second": 3.599, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0982, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 2.0040762424468994, | |
| "eval_runtime": 51.9149, | |
| "eval_samples_per_second": 28.739, | |
| "eval_steps_per_second": 3.602, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1027, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.9931957721710205, | |
| "eval_runtime": 51.964, | |
| "eval_samples_per_second": 28.712, | |
| "eval_steps_per_second": 3.599, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0865, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 1.989241123199463, | |
| "eval_runtime": 51.9483, | |
| "eval_samples_per_second": 28.721, | |
| "eval_steps_per_second": 3.6, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0789, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 1.9806030988693237, | |
| "eval_runtime": 52.181, | |
| "eval_samples_per_second": 28.593, | |
| "eval_steps_per_second": 3.584, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0924, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 1.9745317697525024, | |
| "eval_runtime": 52.0357, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.594, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0839, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 1.9676258563995361, | |
| "eval_runtime": 52.0774, | |
| "eval_samples_per_second": 28.65, | |
| "eval_steps_per_second": 3.591, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 2.081, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 1.9613432884216309, | |
| "eval_runtime": 52.027, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.594, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2112, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 6.092531163629568e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |