| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.849707912904939, | |
| "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": 1.8168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.768841028213501, | |
| "eval_runtime": 215.902, | |
| "eval_samples_per_second": 1.931, | |
| "eval_steps_per_second": 0.195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8426966292134835e-05, | |
| "loss": 1.7432, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.7144243717193604, | |
| "eval_runtime": 215.6923, | |
| "eval_samples_per_second": 1.933, | |
| "eval_steps_per_second": 0.195, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.752808988764045e-05, | |
| "loss": 1.7052, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.678654432296753, | |
| "eval_runtime": 215.6797, | |
| "eval_samples_per_second": 1.933, | |
| "eval_steps_per_second": 0.195, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.662921348314607e-05, | |
| "loss": 1.6851, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.6587953567504883, | |
| "eval_runtime": 215.657, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.5730337078651687e-05, | |
| "loss": 1.6265, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.6458046436309814, | |
| "eval_runtime": 215.6322, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.4831460674157305e-05, | |
| "loss": 1.6617, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.636366844177246, | |
| "eval_runtime": 215.6707, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.3932584269662923e-05, | |
| "loss": 1.651, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.6294023990631104, | |
| "eval_runtime": 215.621, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.303370786516854e-05, | |
| "loss": 1.6218, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6229923963546753, | |
| "eval_runtime": 215.6539, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.213483146067416e-05, | |
| "loss": 1.625, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.6182714700698853, | |
| "eval_runtime": 215.6429, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1235955056179778e-05, | |
| "loss": 1.6358, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.6151902675628662, | |
| "eval_runtime": 215.6354, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0337078651685396e-05, | |
| "loss": 1.6118, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.6117970943450928, | |
| "eval_runtime": 215.6265, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.438202247191012e-06, | |
| "loss": 1.5914, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6088885068893433, | |
| "eval_runtime": 215.6483, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.53932584269663e-06, | |
| "loss": 1.6321, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.6063815355300903, | |
| "eval_runtime": 215.612, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.640449438202247e-06, | |
| "loss": 1.6139, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.6046371459960938, | |
| "eval_runtime": 215.6502, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.741573033707865e-06, | |
| "loss": 1.5742, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6029813289642334, | |
| "eval_runtime": 215.6664, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.842696629213483e-06, | |
| "loss": 1.5757, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.6015688180923462, | |
| "eval_runtime": 215.6424, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.943820224719101e-06, | |
| "loss": 1.577, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.6001653671264648, | |
| "eval_runtime": 215.6467, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.04494382022472e-06, | |
| "loss": 1.6077, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5988893508911133, | |
| "eval_runtime": 215.6429, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.146067415730337e-06, | |
| "loss": 1.6011, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.597815752029419, | |
| "eval_runtime": 215.6307, | |
| "eval_samples_per_second": 1.934, | |
| "eval_steps_per_second": 0.195, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.2471910112359554e-06, | |
| "loss": 1.5982, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.5970968008041382, | |
| "eval_runtime": 215.6746, | |
| "eval_samples_per_second": 1.933, | |
| "eval_steps_per_second": 0.195, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 450, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 2.804385205714944e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |