| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000646629765661373, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2932595313227458e-05, | |
| "eval_loss": 1.272545576095581, | |
| "eval_runtime": 1902.7416, | |
| "eval_samples_per_second": 17.111, | |
| "eval_steps_per_second": 8.556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.46629765661373e-05, | |
| "grad_norm": 1.095668911933899, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1906, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001293259531322746, | |
| "grad_norm": 1.3296310901641846, | |
| "learning_rate": 0.0001, | |
| "loss": 0.974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001293259531322746, | |
| "eval_loss": 0.6204116940498352, | |
| "eval_runtime": 1901.6146, | |
| "eval_samples_per_second": 17.121, | |
| "eval_steps_per_second": 8.561, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00019398892969841187, | |
| "grad_norm": 0.8761526942253113, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002586519062645492, | |
| "grad_norm": 1.0511103868484497, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1754, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002586519062645492, | |
| "eval_loss": 0.1038876473903656, | |
| "eval_runtime": 1909.3041, | |
| "eval_samples_per_second": 17.052, | |
| "eval_steps_per_second": 8.526, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003233148828306865, | |
| "grad_norm": 0.5521308779716492, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1093, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00038797785939682374, | |
| "grad_norm": 0.43349796533584595, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0608, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00038797785939682374, | |
| "eval_loss": 0.04856891185045242, | |
| "eval_runtime": 1906.6366, | |
| "eval_samples_per_second": 17.076, | |
| "eval_steps_per_second": 8.538, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00045264083596296105, | |
| "grad_norm": 0.19055882096290588, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0445, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0005173038125290984, | |
| "grad_norm": 0.2949741780757904, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0349, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005173038125290984, | |
| "eval_loss": 0.03124900534749031, | |
| "eval_runtime": 1906.0918, | |
| "eval_samples_per_second": 17.081, | |
| "eval_steps_per_second": 8.541, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005819667890952356, | |
| "grad_norm": 0.20197047293186188, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0248, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000646629765661373, | |
| "grad_norm": 0.14738060534000397, | |
| "learning_rate": 0.0, | |
| "loss": 0.021, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.000646629765661373, | |
| "eval_loss": 0.02955532819032669, | |
| "eval_runtime": 1907.2293, | |
| "eval_samples_per_second": 17.071, | |
| "eval_steps_per_second": 8.535, | |
| "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": 8143670712729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |