| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06474587245063128, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012949174490126255, | |
| "eval_loss": 5.735302448272705, | |
| "eval_runtime": 2.0472, | |
| "eval_samples_per_second": 159.239, | |
| "eval_steps_per_second": 79.619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006474587245063127, | |
| "grad_norm": 5.199829578399658, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8363, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012949174490126255, | |
| "grad_norm": 4.196000576019287, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012949174490126255, | |
| "eval_loss": 5.591858863830566, | |
| "eval_runtime": 2.061, | |
| "eval_samples_per_second": 158.176, | |
| "eval_steps_per_second": 79.088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019423761735189383, | |
| "grad_norm": 5.302495002746582, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.9064, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02589834898025251, | |
| "grad_norm": 5.405220985412598, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.3046, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02589834898025251, | |
| "eval_loss": 4.940808296203613, | |
| "eval_runtime": 2.0626, | |
| "eval_samples_per_second": 158.052, | |
| "eval_steps_per_second": 79.026, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03237293622531564, | |
| "grad_norm": 5.4033002853393555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.5125, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.038847523470378766, | |
| "grad_norm": 6.361747741699219, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7681, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038847523470378766, | |
| "eval_loss": 4.363986015319824, | |
| "eval_runtime": 2.0966, | |
| "eval_samples_per_second": 155.488, | |
| "eval_steps_per_second": 77.744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04532211071544189, | |
| "grad_norm": 5.471643924713135, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9542, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05179669796050502, | |
| "grad_norm": 8.481507301330566, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.2038, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05179669796050502, | |
| "eval_loss": 4.096857070922852, | |
| "eval_runtime": 2.0675, | |
| "eval_samples_per_second": 157.678, | |
| "eval_steps_per_second": 78.839, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.058271285205568145, | |
| "grad_norm": 3.6633269786834717, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.3399, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06474587245063128, | |
| "grad_norm": 5.096242904663086, | |
| "learning_rate": 0.0, | |
| "loss": 3.8004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06474587245063128, | |
| "eval_loss": 4.050339221954346, | |
| "eval_runtime": 2.1017, | |
| "eval_samples_per_second": 155.11, | |
| "eval_steps_per_second": 77.555, | |
| "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": 71210560389120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |