| { | |
| "best_metric": 4.372256755828857, | |
| "best_model_checkpoint": "deta-cd45rb-4ah-4l\\checkpoint-46060", | |
| "epoch": 10.0, | |
| "global_step": 46060, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.00065132435953e-07, | |
| "loss": 4.8838, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.58176851272583, | |
| "eval_runtime": 290.9092, | |
| "eval_samples_per_second": 6.122, | |
| "eval_steps_per_second": 0.767, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.001302648719061e-07, | |
| "loss": 4.3326, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 5.532724857330322, | |
| "eval_runtime": 289.6139, | |
| "eval_samples_per_second": 6.15, | |
| "eval_steps_per_second": 0.77, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.001519756838905e-07, | |
| "loss": 4.3118, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 5.353872776031494, | |
| "eval_runtime": 289.091, | |
| "eval_samples_per_second": 6.161, | |
| "eval_steps_per_second": 0.771, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.001953973078593e-07, | |
| "loss": 4.1978, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 5.155240058898926, | |
| "eval_runtime": 288.8689, | |
| "eval_samples_per_second": 6.165, | |
| "eval_steps_per_second": 0.772, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.002605297438124e-07, | |
| "loss": 4.0235, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 4.9679036140441895, | |
| "eval_runtime": 288.4979, | |
| "eval_samples_per_second": 6.173, | |
| "eval_steps_per_second": 0.773, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.003039513677811e-07, | |
| "loss": 3.9038, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 4.782414436340332, | |
| "eval_runtime": 286.2672, | |
| "eval_samples_per_second": 6.221, | |
| "eval_steps_per_second": 0.779, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.003256621797655e-07, | |
| "loss": 3.8628, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 4.591905117034912, | |
| "eval_runtime": 286.8168, | |
| "eval_samples_per_second": 6.21, | |
| "eval_steps_per_second": 0.777, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0036908380373423e-07, | |
| "loss": 3.7967, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 4.441461563110352, | |
| "eval_runtime": 286.3236, | |
| "eval_samples_per_second": 6.22, | |
| "eval_steps_per_second": 0.779, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0041250542770299e-07, | |
| "loss": 3.7638, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 4.400564670562744, | |
| "eval_runtime": 286.0319, | |
| "eval_samples_per_second": 6.227, | |
| "eval_steps_per_second": 0.78, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.5592705167173247e-10, | |
| "loss": 3.7538, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 4.372256755828857, | |
| "eval_runtime": 285.8571, | |
| "eval_samples_per_second": 6.23, | |
| "eval_steps_per_second": 0.78, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 8.74966392383616e+19, | |
| "train_loss": 4.083041820451585, | |
| "train_runtime": 49819.081, | |
| "train_samples_per_second": 3.698, | |
| "train_steps_per_second": 0.925 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.74966392383616e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |