| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.909090909090909, | |
| "eval_steps": 2, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9523, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.953429730181653e-05, | |
| "loss": 0.9586, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.8882376551628113, | |
| "eval_runtime": 199.3091, | |
| "eval_samples_per_second": 1.962, | |
| "eval_steps_per_second": 1.962, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.814586436738998e-05, | |
| "loss": 0.9663, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.586056507527266e-05, | |
| "loss": 0.9093, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.8382185697555542, | |
| "eval_runtime": 197.5958, | |
| "eval_samples_per_second": 1.979, | |
| "eval_steps_per_second": 1.979, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.272097022732443e-05, | |
| "loss": 0.8951, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.8785564535221e-05, | |
| "loss": 0.802, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.8089605569839478, | |
| "eval_runtime": 197.4382, | |
| "eval_samples_per_second": 1.98, | |
| "eval_steps_per_second": 1.98, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.412765716093272e-05, | |
| "loss": 0.839, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.883401610574336e-05, | |
| "loss": 0.839, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.778209924697876, | |
| "eval_runtime": 197.4012, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 1.981, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.300325188655761e-05, | |
| "loss": 0.7963, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.674398060854931e-05, | |
| "loss": 0.7654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.7569797039031982, | |
| "eval_runtime": 198.9934, | |
| "eval_samples_per_second": 1.965, | |
| "eval_steps_per_second": 1.965, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.01728006526317e-05, | |
| "loss": 0.8633, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.341212066823355e-05, | |
| "loss": 0.7767, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.7437096238136292, | |
| "eval_runtime": 198.5519, | |
| "eval_samples_per_second": 1.969, | |
| "eval_steps_per_second": 1.969, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.658787933176646e-05, | |
| "loss": 0.773, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.982719934736832e-05, | |
| "loss": 0.7392, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.7332723140716553, | |
| "eval_runtime": 197.6582, | |
| "eval_samples_per_second": 1.978, | |
| "eval_steps_per_second": 1.978, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.325601939145069e-05, | |
| "loss": 0.8132, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.6996748113442394e-05, | |
| "loss": 0.7252, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.7241747975349426, | |
| "eval_runtime": 197.3839, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 1.981, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.1165983894256647e-05, | |
| "loss": 0.7055, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.5872342839067306e-05, | |
| "loss": 0.7293, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.7176232933998108, | |
| "eval_runtime": 196.8785, | |
| "eval_samples_per_second": 1.986, | |
| "eval_steps_per_second": 1.986, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.1214435464779006e-05, | |
| "loss": 0.7933, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.2790297726755716e-06, | |
| "loss": 0.7216, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.7138686180114746, | |
| "eval_runtime": 197.4955, | |
| "eval_samples_per_second": 1.98, | |
| "eval_steps_per_second": 1.98, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 4.139434924727359e-06, | |
| "loss": 0.7214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.8541356326100433e-06, | |
| "loss": 0.8073, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 0.7127791047096252, | |
| "eval_runtime": 197.4244, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 1.981, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 4.6570269818346224e-07, | |
| "loss": 0.6509, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0, | |
| "loss": 0.7432, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.7129585146903992, | |
| "eval_runtime": 198.2692, | |
| "eval_samples_per_second": 1.972, | |
| "eval_steps_per_second": 1.972, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "step": 24, | |
| "total_flos": 6.417806722282291e+16, | |
| "train_loss": 0.8036013916134834, | |
| "train_runtime": 3665.0764, | |
| "train_samples_per_second": 0.32, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 24, | |
| "num_train_epochs": 3, | |
| "save_steps": 3, | |
| "total_flos": 6.417806722282291e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |