| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8560727661851257, | |
| "eval_steps": 20, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9325842696629215e-05, | |
| "loss": 1.8283, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.7597882747650146, | |
| "eval_runtime": 167.9254, | |
| "eval_samples_per_second": 2.65, | |
| "eval_steps_per_second": 0.268, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8426966292134835e-05, | |
| "loss": 1.7181, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.7029485702514648, | |
| "eval_runtime": 168.0408, | |
| "eval_samples_per_second": 2.648, | |
| "eval_steps_per_second": 0.268, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.752808988764045e-05, | |
| "loss": 1.6777, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.6699800491333008, | |
| "eval_runtime": 167.9993, | |
| "eval_samples_per_second": 2.649, | |
| "eval_steps_per_second": 0.268, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.662921348314607e-05, | |
| "loss": 1.6555, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.6510975360870361, | |
| "eval_runtime": 168.0236, | |
| "eval_samples_per_second": 2.648, | |
| "eval_steps_per_second": 0.268, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5730337078651687e-05, | |
| "loss": 1.6371, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.6391140222549438, | |
| "eval_runtime": 167.9874, | |
| "eval_samples_per_second": 2.649, | |
| "eval_steps_per_second": 0.268, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.4831460674157305e-05, | |
| "loss": 1.638, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.6307817697525024, | |
| "eval_runtime": 167.9676, | |
| "eval_samples_per_second": 2.649, | |
| "eval_steps_per_second": 0.268, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.3932584269662923e-05, | |
| "loss": 1.6334, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6237455606460571, | |
| "eval_runtime": 167.9795, | |
| "eval_samples_per_second": 2.649, | |
| "eval_steps_per_second": 0.268, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.303370786516854e-05, | |
| "loss": 1.6568, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6185747385025024, | |
| "eval_runtime": 167.9491, | |
| "eval_samples_per_second": 2.65, | |
| "eval_steps_per_second": 0.268, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.213483146067416e-05, | |
| "loss": 1.6095, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6145987510681152, | |
| "eval_runtime": 167.8883, | |
| "eval_samples_per_second": 2.651, | |
| "eval_steps_per_second": 0.268, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1235955056179778e-05, | |
| "loss": 1.6347, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.6116222143173218, | |
| "eval_runtime": 167.9012, | |
| "eval_samples_per_second": 2.65, | |
| "eval_steps_per_second": 0.268, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0337078651685396e-05, | |
| "loss": 1.6201, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.608642339706421, | |
| "eval_runtime": 168.0086, | |
| "eval_samples_per_second": 2.649, | |
| "eval_steps_per_second": 0.268, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.438202247191012e-06, | |
| "loss": 1.5781, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6063767671585083, | |
| "eval_runtime": 167.9056, | |
| "eval_samples_per_second": 2.65, | |
| "eval_steps_per_second": 0.268, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.53932584269663e-06, | |
| "loss": 1.6158, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.6039100885391235, | |
| "eval_runtime": 286.9359, | |
| "eval_samples_per_second": 1.551, | |
| "eval_steps_per_second": 0.157, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.640449438202247e-06, | |
| "loss": 1.6098, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.602189540863037, | |
| "eval_runtime": 336.0332, | |
| "eval_samples_per_second": 1.324, | |
| "eval_steps_per_second": 0.134, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.741573033707865e-06, | |
| "loss": 1.6083, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6008193492889404, | |
| "eval_runtime": 333.4484, | |
| "eval_samples_per_second": 1.335, | |
| "eval_steps_per_second": 0.135, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.842696629213483e-06, | |
| "loss": 1.596, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.5991967916488647, | |
| "eval_runtime": 333.495, | |
| "eval_samples_per_second": 1.334, | |
| "eval_steps_per_second": 0.135, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.943820224719101e-06, | |
| "loss": 1.6007, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.598080039024353, | |
| "eval_runtime": 333.0437, | |
| "eval_samples_per_second": 1.336, | |
| "eval_steps_per_second": 0.135, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.04494382022472e-06, | |
| "loss": 1.6234, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5969579219818115, | |
| "eval_runtime": 336.627, | |
| "eval_samples_per_second": 1.322, | |
| "eval_steps_per_second": 0.134, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.146067415730337e-06, | |
| "loss": 1.6078, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.5960769653320312, | |
| "eval_runtime": 333.84, | |
| "eval_samples_per_second": 1.333, | |
| "eval_steps_per_second": 0.135, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.2471910112359554e-06, | |
| "loss": 1.5983, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.5955034494400024, | |
| "eval_runtime": 335.6186, | |
| "eval_samples_per_second": 1.326, | |
| "eval_steps_per_second": 0.134, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 2.804385205714944e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |