| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005689900426742532, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005689900426742532, | |
| "grad_norm": 14.821423530578613, | |
| "learning_rate": 2e-05, | |
| "loss": 4.0971, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005689900426742532, | |
| "eval_loss": 4.759266376495361, | |
| "eval_runtime": 18.7338, | |
| "eval_samples_per_second": 39.501, | |
| "eval_steps_per_second": 19.75, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011379800853485065, | |
| "grad_norm": 20.26717758178711, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017069701280227596, | |
| "grad_norm": 36.814876556396484, | |
| "learning_rate": 6e-05, | |
| "loss": 5.3293, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017069701280227596, | |
| "eval_loss": 4.745490074157715, | |
| "eval_runtime": 17.388, | |
| "eval_samples_per_second": 42.558, | |
| "eval_steps_per_second": 21.279, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002275960170697013, | |
| "grad_norm": 19.0011043548584, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5319, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002844950213371266, | |
| "grad_norm": 13.416031837463379, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0475, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0034139402560455193, | |
| "grad_norm": 18.08382797241211, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7969, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034139402560455193, | |
| "eval_loss": 4.700531482696533, | |
| "eval_runtime": 17.8727, | |
| "eval_samples_per_second": 41.404, | |
| "eval_steps_per_second": 20.702, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003982930298719772, | |
| "grad_norm": 28.20526885986328, | |
| "learning_rate": 0.00014, | |
| "loss": 4.0197, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004551920341394026, | |
| "grad_norm": 20.668590545654297, | |
| "learning_rate": 0.00016, | |
| "loss": 4.0775, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005120910384068279, | |
| "grad_norm": 26.41413116455078, | |
| "learning_rate": 0.00018, | |
| "loss": 4.2394, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005120910384068279, | |
| "eval_loss": 4.500211715698242, | |
| "eval_runtime": 17.5801, | |
| "eval_samples_per_second": 42.093, | |
| "eval_steps_per_second": 21.047, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005689900426742532, | |
| "grad_norm": 19.17963981628418, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1686, | |
| "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": 670167497441280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |