| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2294455066921606, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0076481835564053535, | |
| "eval_loss": 5.045347690582275, | |
| "eval_runtime": 3.0639, | |
| "eval_samples_per_second": 17.951, | |
| "eval_steps_per_second": 9.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022944550669216062, | |
| "grad_norm": 17.803730010986328, | |
| "learning_rate": 3e-05, | |
| "loss": 19.7081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045889101338432124, | |
| "grad_norm": 18.587099075317383, | |
| "learning_rate": 6e-05, | |
| "loss": 19.3411, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06118546845124283, | |
| "eval_loss": 4.587184429168701, | |
| "eval_runtime": 1.9392, | |
| "eval_samples_per_second": 28.362, | |
| "eval_steps_per_second": 14.439, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06883365200764818, | |
| "grad_norm": 14.857477188110352, | |
| "learning_rate": 9e-05, | |
| "loss": 17.4632, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09177820267686425, | |
| "grad_norm": 15.489852905273438, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 17.1185, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1147227533460803, | |
| "grad_norm": 12.425662994384766, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 14.8632, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12237093690248566, | |
| "eval_loss": 3.3697333335876465, | |
| "eval_runtime": 1.9488, | |
| "eval_samples_per_second": 28.223, | |
| "eval_steps_per_second": 14.368, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13766730401529637, | |
| "grad_norm": 13.362841606140137, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 13.0895, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16061185468451242, | |
| "grad_norm": 13.389608383178711, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 11.9513, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1835564053537285, | |
| "grad_norm": 14.42936897277832, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 11.6374, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1835564053537285, | |
| "eval_loss": 2.773041248321533, | |
| "eval_runtime": 1.948, | |
| "eval_samples_per_second": 28.234, | |
| "eval_steps_per_second": 14.374, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20650095602294455, | |
| "grad_norm": 13.830270767211914, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 11.0541, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2294455066921606, | |
| "grad_norm": 12.206254005432129, | |
| "learning_rate": 0.0, | |
| "loss": 10.2184, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1803030626304000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |