| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004104507064488121, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031573131265293233, | |
| "grad_norm": 0.6405626535415649, | |
| "learning_rate": 2e-05, | |
| "loss": 6.5486, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031573131265293233, | |
| "eval_loss": 1.742234706878662, | |
| "eval_runtime": 74.1238, | |
| "eval_samples_per_second": 17.997, | |
| "eval_steps_per_second": 8.998, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006314626253058647, | |
| "grad_norm": 0.500285267829895, | |
| "learning_rate": 4e-05, | |
| "loss": 6.1622, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000947193937958797, | |
| "grad_norm": 0.6612991690635681, | |
| "learning_rate": 6e-05, | |
| "loss": 7.4267, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012629252506117293, | |
| "grad_norm": 0.6658630967140198, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6306, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015786565632646618, | |
| "grad_norm": 0.7246699333190918, | |
| "learning_rate": 0.0001, | |
| "loss": 6.792, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001894387875917594, | |
| "grad_norm": 0.6887425780296326, | |
| "learning_rate": 0.00012, | |
| "loss": 6.5042, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022101191885705264, | |
| "grad_norm": 1.1644823551177979, | |
| "learning_rate": 0.00014, | |
| "loss": 6.5081, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025258505012234586, | |
| "grad_norm": 1.0138639211654663, | |
| "learning_rate": 0.00016, | |
| "loss": 6.8784, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028415818138763913, | |
| "grad_norm": 1.9288033246994019, | |
| "learning_rate": 0.00018, | |
| "loss": 7.035, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031573131265293236, | |
| "grad_norm": 2.2389585971832275, | |
| "learning_rate": 0.0002, | |
| "loss": 6.8514, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003473044439182256, | |
| "grad_norm": 1.7787041664123535, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 5.8545, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003788775751835188, | |
| "grad_norm": 1.6030915975570679, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 5.7655, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004104507064488121, | |
| "grad_norm": 1.6597908735275269, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 5.3542, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004104507064488121, | |
| "eval_loss": 1.340001106262207, | |
| "eval_runtime": 73.6832, | |
| "eval_samples_per_second": 18.105, | |
| "eval_steps_per_second": 9.052, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4195247204597760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |