| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06622516556291391, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006622516556291391, | |
| "grad_norm": 0.36483386158943176, | |
| "learning_rate": 2e-05, | |
| "loss": 10.37, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006622516556291391, | |
| "eval_loss": 10.372517585754395, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 367.668, | |
| "eval_steps_per_second": 183.834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013245033112582781, | |
| "grad_norm": 0.42666858434677124, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3088, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019867549668874173, | |
| "grad_norm": 0.3792109191417694, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3156, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019867549668874173, | |
| "eval_loss": 10.372127532958984, | |
| "eval_runtime": 0.1752, | |
| "eval_samples_per_second": 365.292, | |
| "eval_steps_per_second": 182.646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026490066225165563, | |
| "grad_norm": 0.29022088646888733, | |
| "learning_rate": 8e-05, | |
| "loss": 10.373, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.033112582781456956, | |
| "grad_norm": 0.3271644115447998, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3709, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.039735099337748346, | |
| "grad_norm": 0.35579004883766174, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3604, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.039735099337748346, | |
| "eval_loss": 10.370521545410156, | |
| "eval_runtime": 0.1826, | |
| "eval_samples_per_second": 350.463, | |
| "eval_steps_per_second": 175.232, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.046357615894039736, | |
| "grad_norm": 0.3526122272014618, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3609, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 0.34618157148361206, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3934, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.059602649006622516, | |
| "grad_norm": 0.4153050184249878, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3299, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.059602649006622516, | |
| "eval_loss": 10.367629051208496, | |
| "eval_runtime": 0.1857, | |
| "eval_samples_per_second": 344.673, | |
| "eval_steps_per_second": 172.336, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06622516556291391, | |
| "grad_norm": 0.3620421588420868, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3303, | |
| "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": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |