| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01156570767673847, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002313141535347694, | |
| "grad_norm": 177.47068786621094, | |
| "learning_rate": 1e-05, | |
| "loss": 124.5555, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002313141535347694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 56.7108, | |
| "eval_samples_per_second": 12.855, | |
| "eval_steps_per_second": 6.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004626283070695388, | |
| "grad_norm": 191.83155822753906, | |
| "learning_rate": 2e-05, | |
| "loss": 112.9062, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004626283070695388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.6197, | |
| "eval_samples_per_second": 22.348, | |
| "eval_steps_per_second": 11.19, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0069394246060430825, | |
| "grad_norm": 192.53724670410156, | |
| "learning_rate": 3e-05, | |
| "loss": 113.4672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009252566141390776, | |
| "grad_norm": 172.92764282226562, | |
| "learning_rate": 4e-05, | |
| "loss": 113.4296, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009252566141390776, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.623, | |
| "eval_samples_per_second": 21.682, | |
| "eval_steps_per_second": 10.856, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01156570767673847, | |
| "grad_norm": 199.4036865234375, | |
| "learning_rate": 5e-05, | |
| "loss": 114.6384, | |
| "step": 5 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3505339571896320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |