| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0023181686467690526, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023181686467690525, | |
| "grad_norm": 11.30616283416748, | |
| "learning_rate": 2e-05, | |
| "loss": 6.5095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023181686467690525, | |
| "eval_loss": 1.599483847618103, | |
| "eval_runtime": 65.7503, | |
| "eval_samples_per_second": 27.635, | |
| "eval_steps_per_second": 13.825, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004636337293538105, | |
| "grad_norm": 7.352132797241211, | |
| "learning_rate": 4e-05, | |
| "loss": 6.1124, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006954505940307157, | |
| "grad_norm": 6.156064033508301, | |
| "learning_rate": 6e-05, | |
| "loss": 5.6913, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006954505940307157, | |
| "eval_loss": 1.5879477262496948, | |
| "eval_runtime": 65.5595, | |
| "eval_samples_per_second": 27.715, | |
| "eval_steps_per_second": 13.865, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000927267458707621, | |
| "grad_norm": 9.128706932067871, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6768, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011590843233845263, | |
| "grad_norm": 9.580340385437012, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9169, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013909011880614314, | |
| "grad_norm": 5.978302478790283, | |
| "learning_rate": 0.00012, | |
| "loss": 6.9236, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013909011880614314, | |
| "eval_loss": 1.5002448558807373, | |
| "eval_runtime": 65.2697, | |
| "eval_samples_per_second": 27.838, | |
| "eval_steps_per_second": 13.927, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016227180527383367, | |
| "grad_norm": 6.212968349456787, | |
| "learning_rate": 0.00014, | |
| "loss": 4.9658, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001854534917415242, | |
| "grad_norm": 11.32003402709961, | |
| "learning_rate": 0.00016, | |
| "loss": 6.3171, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0020863517820921473, | |
| "grad_norm": 6.1606831550598145, | |
| "learning_rate": 0.00018, | |
| "loss": 5.7145, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020863517820921473, | |
| "eval_loss": 1.2604190111160278, | |
| "eval_runtime": 65.6497, | |
| "eval_samples_per_second": 27.677, | |
| "eval_steps_per_second": 13.846, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0023181686467690526, | |
| "grad_norm": 10.335721969604492, | |
| "learning_rate": 0.0002, | |
| "loss": 4.6105, | |
| "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": 1628733135912960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |