| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003681207436039021, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.362414872078041e-05, | |
| "eval_loss": 4.358658313751221, | |
| "eval_runtime": 245.2881, | |
| "eval_samples_per_second": 23.315, | |
| "eval_steps_per_second": 11.66, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003681207436039021, | |
| "grad_norm": 4.203360080718994, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2873, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007362414872078042, | |
| "grad_norm": 5.499898433685303, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2354, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007362414872078042, | |
| "eval_loss": 3.6313529014587402, | |
| "eval_runtime": 245.3126, | |
| "eval_samples_per_second": 23.313, | |
| "eval_steps_per_second": 11.659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011043622308117063, | |
| "grad_norm": 5.180222034454346, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4088, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014724829744156083, | |
| "grad_norm": 5.636661529541016, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.3155, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014724829744156083, | |
| "eval_loss": 3.170792818069458, | |
| "eval_runtime": 244.3666, | |
| "eval_samples_per_second": 23.403, | |
| "eval_steps_per_second": 11.704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018406037180195105, | |
| "grad_norm": 4.489249229431152, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0083, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022087244616234127, | |
| "grad_norm": 3.8685977458953857, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0143, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022087244616234127, | |
| "eval_loss": 3.04840087890625, | |
| "eval_runtime": 239.3623, | |
| "eval_samples_per_second": 23.893, | |
| "eval_steps_per_second": 11.948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025768452052273147, | |
| "grad_norm": 4.545247554779053, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.0609, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0029449659488312166, | |
| "grad_norm": 3.932966470718384, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6458, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029449659488312166, | |
| "eval_loss": 3.0266425609588623, | |
| "eval_runtime": 236.2487, | |
| "eval_samples_per_second": 24.208, | |
| "eval_steps_per_second": 12.106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033130866924351186, | |
| "grad_norm": 4.188052654266357, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2045, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003681207436039021, | |
| "grad_norm": 5.825687408447266, | |
| "learning_rate": 0.0, | |
| "loss": 3.243, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003681207436039021, | |
| "eval_loss": 3.0219552516937256, | |
| "eval_runtime": 238.5537, | |
| "eval_samples_per_second": 23.974, | |
| "eval_steps_per_second": 11.989, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2512989086810112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |