| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0019767729182110206, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.589243060703402e-05, | |
| "eval_loss": 2.3003780841827393, | |
| "eval_runtime": 1187.7558, | |
| "eval_samples_per_second": 5.38, | |
| "eval_steps_per_second": 2.69, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019767729182110206, | |
| "grad_norm": 0.8546552658081055, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4369, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003953545836422041, | |
| "grad_norm": 1.0584559440612793, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3481, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005271394448562722, | |
| "eval_loss": 2.0888173580169678, | |
| "eval_runtime": 1194.0411, | |
| "eval_samples_per_second": 5.352, | |
| "eval_steps_per_second": 2.676, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005930318754633062, | |
| "grad_norm": 0.9050226807594299, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007907091672844082, | |
| "grad_norm": 0.9661085605621338, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7741, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009883864591055103, | |
| "grad_norm": 0.6132097840309143, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0345, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010542788897125444, | |
| "eval_loss": 1.9907269477844238, | |
| "eval_runtime": 1195.1028, | |
| "eval_samples_per_second": 5.347, | |
| "eval_steps_per_second": 2.673, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011860637509266123, | |
| "grad_norm": 0.5894842147827148, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1804, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013837410427477144, | |
| "grad_norm": 0.6730942130088806, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.0049, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015814183345688165, | |
| "grad_norm": 0.5569067001342773, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.9578, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015814183345688165, | |
| "eval_loss": 1.9681271314620972, | |
| "eval_runtime": 1194.7544, | |
| "eval_samples_per_second": 5.348, | |
| "eval_steps_per_second": 2.674, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017790956263899185, | |
| "grad_norm": 0.6647498607635498, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.9623, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0019767729182110206, | |
| "grad_norm": 0.5334838032722473, | |
| "learning_rate": 0.0, | |
| "loss": 2.2075, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5579903537709056e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |