| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006839433609404221, | |
| "eval_steps": 8, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008549292011755277, | |
| "grad_norm": 16.207183837890625, | |
| "learning_rate": 1e-05, | |
| "loss": 9.2165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008549292011755277, | |
| "eval_loss": 9.122929573059082, | |
| "eval_runtime": 80.1509, | |
| "eval_samples_per_second": 24.579, | |
| "eval_steps_per_second": 12.289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017098584023510553, | |
| "grad_norm": 17.143712997436523, | |
| "learning_rate": 2e-05, | |
| "loss": 8.7316, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002564787603526583, | |
| "grad_norm": 17.279664993286133, | |
| "learning_rate": 3e-05, | |
| "loss": 8.6895, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034197168047021107, | |
| "grad_norm": 16.366716384887695, | |
| "learning_rate": 4e-05, | |
| "loss": 8.8251, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004274646005877639, | |
| "grad_norm": 17.285783767700195, | |
| "learning_rate": 5e-05, | |
| "loss": 8.9384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005129575207053166, | |
| "grad_norm": 15.761588096618652, | |
| "learning_rate": 6e-05, | |
| "loss": 8.3716, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005984504408228694, | |
| "grad_norm": 15.229612350463867, | |
| "learning_rate": 7e-05, | |
| "loss": 7.1605, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006839433609404221, | |
| "grad_norm": 13.926135063171387, | |
| "learning_rate": 8e-05, | |
| "loss": 6.1561, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006839433609404221, | |
| "eval_loss": 5.026383876800537, | |
| "eval_runtime": 69.7028, | |
| "eval_samples_per_second": 28.263, | |
| "eval_steps_per_second": 14.131, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6193424445210624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |