| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01412928293889085, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028258565877781704, | |
| "eval_loss": 9.014374732971191, | |
| "eval_runtime": 45.8636, | |
| "eval_samples_per_second": 32.488, | |
| "eval_steps_per_second": 16.244, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "grad_norm": 31.317241668701172, | |
| "learning_rate": 5e-05, | |
| "loss": 9.2381, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "grad_norm": 30.054075241088867, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "eval_loss": 6.305483341217041, | |
| "eval_runtime": 46.5414, | |
| "eval_samples_per_second": 32.015, | |
| "eval_steps_per_second": 16.007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "grad_norm": 14.453044891357422, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.5007, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": 11.699786186218262, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "eval_loss": 4.397282600402832, | |
| "eval_runtime": 45.8608, | |
| "eval_samples_per_second": 32.49, | |
| "eval_steps_per_second": 16.245, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "grad_norm": 10.621557235717773, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2254, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008477569763334511, | |
| "grad_norm": 8.351560592651367, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6046, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008477569763334511, | |
| "eval_loss": 3.5391788482666016, | |
| "eval_runtime": 45.7633, | |
| "eval_samples_per_second": 32.559, | |
| "eval_steps_per_second": 16.279, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009890498057223597, | |
| "grad_norm": 12.242228507995605, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.3887, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01130342635111268, | |
| "grad_norm": 8.75986385345459, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3271, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01130342635111268, | |
| "eval_loss": 3.2006571292877197, | |
| "eval_runtime": 46.1457, | |
| "eval_samples_per_second": 32.289, | |
| "eval_steps_per_second": 16.145, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012716354645001766, | |
| "grad_norm": 10.265480041503906, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.1251, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01412928293889085, | |
| "grad_norm": 10.496199607849121, | |
| "learning_rate": 0.0, | |
| "loss": 2.9414, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01412928293889085, | |
| "eval_loss": 3.158576011657715, | |
| "eval_runtime": 46.2368, | |
| "eval_samples_per_second": 32.225, | |
| "eval_steps_per_second": 16.113, | |
| "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": 1278959891251200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |