| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004210526315789474, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004210526315789474, | |
| "grad_norm": 0.15470190346240997, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004210526315789474, | |
| "eval_loss": 10.831326484680176, | |
| "eval_runtime": 3.6353, | |
| "eval_samples_per_second": 275.08, | |
| "eval_steps_per_second": 137.54, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008421052631578948, | |
| "grad_norm": 0.2425263673067093, | |
| "learning_rate": 4e-05, | |
| "loss": 10.84, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012631578947368421, | |
| "grad_norm": 0.1725035458803177, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8323, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012631578947368421, | |
| "eval_loss": 10.831254959106445, | |
| "eval_runtime": 2.7341, | |
| "eval_samples_per_second": 365.757, | |
| "eval_steps_per_second": 182.878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "grad_norm": 0.25983864068984985, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8106, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002105263157894737, | |
| "grad_norm": 0.18254497647285461, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025263157894736842, | |
| "grad_norm": 0.22616256773471832, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8266, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025263157894736842, | |
| "eval_loss": 10.830709457397461, | |
| "eval_runtime": 2.7824, | |
| "eval_samples_per_second": 359.402, | |
| "eval_steps_per_second": 179.701, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029473684210526317, | |
| "grad_norm": 0.2730276882648468, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8315, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003368421052631579, | |
| "grad_norm": 0.18166963756084442, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8321, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003789473684210526, | |
| "grad_norm": 0.1957683563232422, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8402, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003789473684210526, | |
| "eval_loss": 10.829776763916016, | |
| "eval_runtime": 2.7633, | |
| "eval_samples_per_second": 361.882, | |
| "eval_steps_per_second": 180.941, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004210526315789474, | |
| "grad_norm": 0.3295745551586151, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8424, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 820295761920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |