| { | |
| "best_metric": 0.27965888381004333, | |
| "best_model_checkpoint": "pythia-XYZCompany-1000-steps\\checkpoint-450", | |
| "epoch": 2.848101265822785, | |
| "eval_steps": 50, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.75975975975976e-06, | |
| "loss": 1.497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.50950950950951e-06, | |
| "loss": 0.3452, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.32888519763946533, | |
| "eval_runtime": 6.4693, | |
| "eval_samples_per_second": 21.641, | |
| "eval_steps_per_second": 5.41, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.318, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 0.3598, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.3072541356086731, | |
| "eval_runtime": 6.5211, | |
| "eval_samples_per_second": 21.469, | |
| "eval_steps_per_second": 5.367, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.75875875875876e-06, | |
| "loss": 0.2963, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.50850850850851e-06, | |
| "loss": 0.3045, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.2949899435043335, | |
| "eval_runtime": 6.7431, | |
| "eval_samples_per_second": 20.762, | |
| "eval_steps_per_second": 5.19, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 8.258258258258259e-06, | |
| "loss": 0.2857, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 8.00800800800801e-06, | |
| "loss": 0.252, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.2895931303501129, | |
| "eval_runtime": 6.5147, | |
| "eval_samples_per_second": 21.49, | |
| "eval_steps_per_second": 5.372, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 7.757757757757758e-06, | |
| "loss": 0.2613, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.507507507507507e-06, | |
| "loss": 0.2541, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.2829298973083496, | |
| "eval_runtime": 6.7922, | |
| "eval_samples_per_second": 20.612, | |
| "eval_steps_per_second": 5.153, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 7.257257257257258e-06, | |
| "loss": 0.2388, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.007007007007007e-06, | |
| "loss": 0.2455, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 0.28180426359176636, | |
| "eval_runtime": 6.7633, | |
| "eval_samples_per_second": 20.7, | |
| "eval_steps_per_second": 5.175, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 0.2336, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 6.506506506506507e-06, | |
| "loss": 0.2067, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.28442302346229553, | |
| "eval_runtime": 6.758, | |
| "eval_samples_per_second": 20.716, | |
| "eval_steps_per_second": 5.179, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 6.2562562562562565e-06, | |
| "loss": 0.2049, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.006006006006007e-06, | |
| "loss": 0.2169, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.28421658277511597, | |
| "eval_runtime": 6.7687, | |
| "eval_samples_per_second": 20.683, | |
| "eval_steps_per_second": 5.171, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.755755755755756e-06, | |
| "loss": 0.1923, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.505505505505506e-06, | |
| "loss": 0.2112, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.27965888381004333, | |
| "eval_runtime": 6.7745, | |
| "eval_samples_per_second": 20.666, | |
| "eval_steps_per_second": 5.166, | |
| "step": 450 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1000, | |
| "num_train_epochs": 7, | |
| "save_steps": 50, | |
| "total_flos": 1364866816278528.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |