| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007894736842105263, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008771929824561404, | |
| "grad_norm": 0.9405450224876404, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008771929824561404, | |
| "eval_loss": 1.4270412921905518, | |
| "eval_runtime": 29.2451, | |
| "eval_samples_per_second": 16.447, | |
| "eval_steps_per_second": 8.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "grad_norm": 0.729203999042511, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4651, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002631578947368421, | |
| "grad_norm": 0.8438076376914978, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3636, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002631578947368421, | |
| "eval_loss": 1.4241745471954346, | |
| "eval_runtime": 27.6691, | |
| "eval_samples_per_second": 17.384, | |
| "eval_steps_per_second": 8.71, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0035087719298245615, | |
| "grad_norm": 0.7597953081130981, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6102, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0043859649122807015, | |
| "grad_norm": 0.6878741979598999, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3306, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 0.8477479815483093, | |
| "learning_rate": 0.00012, | |
| "loss": 1.388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "eval_loss": 1.3872567415237427, | |
| "eval_runtime": 27.6998, | |
| "eval_samples_per_second": 17.365, | |
| "eval_steps_per_second": 8.7, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0061403508771929825, | |
| "grad_norm": 1.0238683223724365, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5472, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 0.802706241607666, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3701, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007894736842105263, | |
| "grad_norm": 0.8171374201774597, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3579, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007894736842105263, | |
| "eval_loss": 1.2911149263381958, | |
| "eval_runtime": 27.6998, | |
| "eval_samples_per_second": 17.365, | |
| "eval_steps_per_second": 8.7, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2904251223244800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |