| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05241090146750524, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010482180293501049, | |
| "eval_loss": 10.35714054107666, | |
| "eval_runtime": 22.2303, | |
| "eval_samples_per_second": 18.083, | |
| "eval_steps_per_second": 9.042, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005241090146750524, | |
| "grad_norm": 10.02385139465332, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010482180293501049, | |
| "grad_norm": 6.39988374710083, | |
| "learning_rate": 0.0001, | |
| "loss": 9.7451, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010482180293501049, | |
| "eval_loss": 9.72470760345459, | |
| "eval_runtime": 23.725, | |
| "eval_samples_per_second": 16.944, | |
| "eval_steps_per_second": 8.472, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015723270440251572, | |
| "grad_norm": 8.908526420593262, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.6638, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "grad_norm": 9.695643424987793, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.6867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "eval_loss": 5.8221917152404785, | |
| "eval_runtime": 22.3228, | |
| "eval_samples_per_second": 18.009, | |
| "eval_steps_per_second": 9.004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02620545073375262, | |
| "grad_norm": 9.570939064025879, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.04, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "grad_norm": 10.328211784362793, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4771, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "eval_loss": 4.2585768699646, | |
| "eval_runtime": 22.3947, | |
| "eval_samples_per_second": 17.951, | |
| "eval_steps_per_second": 8.975, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03668763102725367, | |
| "grad_norm": 9.525994300842285, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.0396, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "grad_norm": 9.37747859954834, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.1277, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "eval_loss": 3.8398115634918213, | |
| "eval_runtime": 22.4732, | |
| "eval_samples_per_second": 17.888, | |
| "eval_steps_per_second": 8.944, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04716981132075472, | |
| "grad_norm": 9.670713424682617, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05241090146750524, | |
| "grad_norm": 8.00166130065918, | |
| "learning_rate": 0.0, | |
| "loss": 3.7131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05241090146750524, | |
| "eval_loss": 3.7832844257354736, | |
| "eval_runtime": 22.3817, | |
| "eval_samples_per_second": 17.961, | |
| "eval_steps_per_second": 8.981, | |
| "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": 5235315918766080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |