| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16891891891891891, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006756756756756757, | |
| "grad_norm": 1.165550708770752, | |
| "learning_rate": 1e-05, | |
| "loss": 3.626, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006756756756756757, | |
| "eval_loss": 3.7272541522979736, | |
| "eval_runtime": 4.139, | |
| "eval_samples_per_second": 30.2, | |
| "eval_steps_per_second": 3.866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 1.0644617080688477, | |
| "learning_rate": 2e-05, | |
| "loss": 3.8724, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02027027027027027, | |
| "grad_norm": 1.1389989852905273, | |
| "learning_rate": 3e-05, | |
| "loss": 3.5915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 1.0900439023971558, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7253, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.033783783783783786, | |
| "grad_norm": 1.1674542427062988, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6544, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04054054054054054, | |
| "grad_norm": 1.027275800704956, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3359, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0472972972972973, | |
| "grad_norm": 1.348042607307434, | |
| "learning_rate": 7e-05, | |
| "loss": 3.7027, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 1.2195662260055542, | |
| "learning_rate": 8e-05, | |
| "loss": 3.4344, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.060810810810810814, | |
| "grad_norm": 1.1674548387527466, | |
| "learning_rate": 9e-05, | |
| "loss": 3.4253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.060810810810810814, | |
| "eval_loss": 3.543837070465088, | |
| "eval_runtime": 3.5109, | |
| "eval_samples_per_second": 35.603, | |
| "eval_steps_per_second": 4.557, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 1.3922748565673828, | |
| "learning_rate": 0.0001, | |
| "loss": 3.643, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07432432432432433, | |
| "grad_norm": 1.216573715209961, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 3.5204, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08108108108108109, | |
| "grad_norm": 1.1309475898742676, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.113, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08783783783783784, | |
| "grad_norm": 1.4442179203033447, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 3.0735, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0945945945945946, | |
| "grad_norm": 1.3493503332138062, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.2508, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10135135135135136, | |
| "grad_norm": 1.3219938278198242, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.1881, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 1.606813669204712, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.004, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11486486486486487, | |
| "grad_norm": 1.4070640802383423, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.5799, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12162162162162163, | |
| "grad_norm": 1.4162650108337402, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.6839, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12162162162162163, | |
| "eval_loss": 2.5524935722351074, | |
| "eval_runtime": 3.5211, | |
| "eval_samples_per_second": 35.501, | |
| "eval_steps_per_second": 4.544, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12837837837837837, | |
| "grad_norm": 1.2180479764938354, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.632, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 1.2392053604125977, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.543, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14189189189189189, | |
| "grad_norm": 1.225856900215149, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.3457, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14864864864864866, | |
| "grad_norm": 1.4014432430267334, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.4257, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1554054054054054, | |
| "grad_norm": 1.1311300992965698, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.9219, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 1.2671700716018677, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.3732, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16891891891891891, | |
| "grad_norm": 0.9614380598068237, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2316, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2573421930086400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |