| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003673516243829641, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009183790609574102, | |
| "grad_norm": 0.5137701034545898, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009183790609574102, | |
| "eval_loss": 1.2702103853225708, | |
| "eval_runtime": 156.6349, | |
| "eval_samples_per_second": 11.709, | |
| "eval_steps_per_second": 5.854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018367581219148204, | |
| "grad_norm": 0.5298815369606018, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018367581219148204, | |
| "eval_loss": 1.2547433376312256, | |
| "eval_runtime": 43.0189, | |
| "eval_samples_per_second": 42.632, | |
| "eval_steps_per_second": 21.316, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027551371828722303, | |
| "grad_norm": 0.5069840550422668, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2306, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003673516243829641, | |
| "grad_norm": 0.5158857107162476, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2945, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003673516243829641, | |
| "eval_loss": 1.2369986772537231, | |
| "eval_runtime": 43.0489, | |
| "eval_samples_per_second": 42.603, | |
| "eval_steps_per_second": 21.301, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2959302797033472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |