| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004276702662247407, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004276702662247407, | |
| "grad_norm": 0.8259687423706055, | |
| "learning_rate": 2e-05, | |
| "loss": 3.688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004276702662247407, | |
| "eval_loss": 3.4796206951141357, | |
| "eval_runtime": 9.7562, | |
| "eval_samples_per_second": 100.962, | |
| "eval_steps_per_second": 50.532, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008553405324494814, | |
| "grad_norm": 0.6826836466789246, | |
| "learning_rate": 4e-05, | |
| "loss": 3.5816, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012830107986742223, | |
| "grad_norm": 0.738509476184845, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012830107986742223, | |
| "eval_loss": 3.477968454360962, | |
| "eval_runtime": 8.7542, | |
| "eval_samples_per_second": 112.518, | |
| "eval_steps_per_second": 56.316, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017106810648989629, | |
| "grad_norm": 0.8007542490959167, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8971, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021383513311237037, | |
| "grad_norm": 0.7359699010848999, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5116, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025660215973484445, | |
| "grad_norm": 0.7051669955253601, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4093, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025660215973484445, | |
| "eval_loss": 3.4572508335113525, | |
| "eval_runtime": 8.9288, | |
| "eval_samples_per_second": 110.317, | |
| "eval_steps_per_second": 55.215, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002993691863573185, | |
| "grad_norm": 0.7064687013626099, | |
| "learning_rate": 0.00014, | |
| "loss": 3.2339, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034213621297979257, | |
| "grad_norm": 0.7325624823570251, | |
| "learning_rate": 0.00016, | |
| "loss": 3.5549, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0038490323960226665, | |
| "grad_norm": 0.75117427110672, | |
| "learning_rate": 0.00018, | |
| "loss": 3.3433, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0038490323960226665, | |
| "eval_loss": 3.3985917568206787, | |
| "eval_runtime": 8.923, | |
| "eval_samples_per_second": 110.389, | |
| "eval_steps_per_second": 55.25, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004276702662247407, | |
| "grad_norm": 1.1726967096328735, | |
| "learning_rate": 0.0002, | |
| "loss": 3.6287, | |
| "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": 34292650475520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |