| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009405125793557489, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047025628967787447, | |
| "eval_loss": 1.3333030939102173, | |
| "eval_runtime": 72.5334, | |
| "eval_samples_per_second": 49.384, | |
| "eval_steps_per_second": 6.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014107688690336232, | |
| "grad_norm": 1.7957247495651245, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3816, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023512814483893723, | |
| "eval_loss": 1.252621054649353, | |
| "eval_runtime": 72.4361, | |
| "eval_samples_per_second": 49.451, | |
| "eval_steps_per_second": 6.185, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028215377380672465, | |
| "grad_norm": 0.8181892037391663, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2521, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00423230660710087, | |
| "grad_norm": 0.6588422060012817, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2152, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0047025628967787446, | |
| "eval_loss": 1.1770787239074707, | |
| "eval_runtime": 72.7257, | |
| "eval_samples_per_second": 49.254, | |
| "eval_steps_per_second": 6.16, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005643075476134493, | |
| "grad_norm": 0.6331816911697388, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.1578, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007053844345168116, | |
| "grad_norm": 0.5597560405731201, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2228, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007053844345168116, | |
| "eval_loss": 1.157048225402832, | |
| "eval_runtime": 72.6624, | |
| "eval_samples_per_second": 49.296, | |
| "eval_steps_per_second": 6.166, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00846461321420174, | |
| "grad_norm": 0.6084182262420654, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.2561, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009405125793557489, | |
| "eval_loss": 1.14651358127594, | |
| "eval_runtime": 72.6867, | |
| "eval_samples_per_second": 49.28, | |
| "eval_steps_per_second": 6.163, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4266295704944640.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |