| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008785802143735724, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017571604287471446, | |
| "eval_loss": 1.1193796396255493, | |
| "eval_runtime": 295.9562, | |
| "eval_samples_per_second": 8.099, | |
| "eval_steps_per_second": 4.051, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008785802143735723, | |
| "grad_norm": 0.38145944476127625, | |
| "learning_rate": 5e-05, | |
| "loss": 1.101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017571604287471446, | |
| "grad_norm": 0.43007493019104004, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017571604287471446, | |
| "eval_loss": 1.0578511953353882, | |
| "eval_runtime": 296.8294, | |
| "eval_samples_per_second": 8.075, | |
| "eval_steps_per_second": 4.039, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002635740643120717, | |
| "grad_norm": 0.4852200746536255, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0373, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003514320857494289, | |
| "grad_norm": 0.5584623217582703, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003514320857494289, | |
| "eval_loss": 0.9575603008270264, | |
| "eval_runtime": 296.3108, | |
| "eval_samples_per_second": 8.089, | |
| "eval_steps_per_second": 4.046, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004392901071867862, | |
| "grad_norm": 0.7008752226829529, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005271481286241434, | |
| "grad_norm": 0.6719041466712952, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8862, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005271481286241434, | |
| "eval_loss": 0.9079647660255432, | |
| "eval_runtime": 297.29, | |
| "eval_samples_per_second": 8.063, | |
| "eval_steps_per_second": 4.033, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006150061500615006, | |
| "grad_norm": 0.5712262392044067, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8628, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007028641714988578, | |
| "grad_norm": 0.6111838221549988, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.936, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007028641714988578, | |
| "eval_loss": 0.8869322538375854, | |
| "eval_runtime": 297.012, | |
| "eval_samples_per_second": 8.07, | |
| "eval_steps_per_second": 4.037, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00790722192936215, | |
| "grad_norm": 0.7134804725646973, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8469, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008785802143735724, | |
| "grad_norm": 0.5976589322090149, | |
| "learning_rate": 0.0, | |
| "loss": 0.8012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008785802143735724, | |
| "eval_loss": 0.8830190300941467, | |
| "eval_runtime": 296.6979, | |
| "eval_samples_per_second": 8.079, | |
| "eval_steps_per_second": 4.041, | |
| "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": 1.84956424814592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |