| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8, | |
| "eval_steps": 1875, | |
| "global_step": 17500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.330490405117271e-05, | |
| "loss": 4.544, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.965192005389625e-05, | |
| "loss": 3.54, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.684482371434989e-05, | |
| "loss": 3.54, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4256, | |
| "eval_samples_per_second": 54.906, | |
| "eval_steps_per_second": 3.432, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.40377273748035e-05, | |
| "loss": 3.54, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.123063103525713e-05, | |
| "loss": 3.54, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.842353469571077e-05, | |
| "loss": 3.54, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.561643835616438e-05, | |
| "loss": 3.54, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4006, | |
| "eval_samples_per_second": 54.944, | |
| "eval_steps_per_second": 3.434, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.280934201661802e-05, | |
| "loss": 3.54, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.000224567707165e-05, | |
| "loss": 3.54, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.719514933752526e-05, | |
| "loss": 3.54, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.43880529979789e-05, | |
| "loss": 3.54, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4168, | |
| "eval_samples_per_second": 54.92, | |
| "eval_steps_per_second": 3.432, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.158095665843251e-05, | |
| "loss": 3.54, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 6.877386031888615e-05, | |
| "loss": 3.54, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.596676397933978e-05, | |
| "loss": 3.54, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.31596676397934e-05, | |
| "loss": 3.54, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.427, | |
| "eval_samples_per_second": 54.904, | |
| "eval_steps_per_second": 3.432, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.0352571300247026e-05, | |
| "loss": 3.54, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.754547496070065e-05, | |
| "loss": 3.54, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.473837862115428e-05, | |
| "loss": 3.54, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4308, | |
| "eval_samples_per_second": 54.899, | |
| "eval_steps_per_second": 3.431, | |
| "step": 9375 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.193128228160791e-05, | |
| "loss": 3.54, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.912418594206153e-05, | |
| "loss": 3.54, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.631708960251516e-05, | |
| "loss": 3.54, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.350999326296879e-05, | |
| "loss": 3.54, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4709, | |
| "eval_samples_per_second": 54.838, | |
| "eval_steps_per_second": 3.427, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.070289692342241e-05, | |
| "loss": 3.54, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.789580058387604e-05, | |
| "loss": 3.54, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.508870424432967e-05, | |
| "loss": 3.54, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.228160790478329e-05, | |
| "loss": 3.54, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4281, | |
| "eval_samples_per_second": 54.903, | |
| "eval_steps_per_second": 3.431, | |
| "step": 13125 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.9474511565236924e-05, | |
| "loss": 3.54, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.6667415225690546e-05, | |
| "loss": 3.54, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.3860318886144174e-05, | |
| "loss": 3.54, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.10532225465978e-05, | |
| "loss": 3.54, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.434, | |
| "eval_samples_per_second": 54.894, | |
| "eval_steps_per_second": 3.431, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.8246126207051426e-05, | |
| "loss": 3.54, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.5439029867505054e-05, | |
| "loss": 3.54, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.263193352795868e-05, | |
| "loss": 3.54, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 3.5400006771087646, | |
| "eval_runtime": 36.4148, | |
| "eval_samples_per_second": 54.923, | |
| "eval_steps_per_second": 3.433, | |
| "step": 16875 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.824837188412307e-06, | |
| "loss": 3.54, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.017740848865933e-06, | |
| "loss": 3.54, | |
| "step": 17500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 18750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.21532624896e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |