| { |
| "best_global_step": 1960, |
| "best_metric": 5.299103260040283, |
| "best_model_checkpoint": null, |
| "epoch": 5.1020408163265305, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002551020408163265, |
| "grad_norm": 15.784777641296387, |
| "learning_rate": 0.0, |
| "loss": 10.3373, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.0758121013641357, |
| "learning_rate": 7.82e-05, |
| "loss": 6.9019, |
| "step": 392 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 5.932833671569824, |
| "eval_runtime": 19.4192, |
| "eval_samples_per_second": 1298.248, |
| "eval_steps_per_second": 5.098, |
| "step": 392 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.8500937223434448, |
| "learning_rate": 9.613387978142077e-05, |
| "loss": 5.6855, |
| "step": 784 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 5.585794448852539, |
| "eval_runtime": 19.3584, |
| "eval_samples_per_second": 1302.326, |
| "eval_steps_per_second": 5.114, |
| "step": 784 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.703319787979126, |
| "learning_rate": 9.077868852459017e-05, |
| "loss": 5.4567, |
| "step": 1176 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 5.44967794418335, |
| "eval_runtime": 19.3703, |
| "eval_samples_per_second": 1301.531, |
| "eval_steps_per_second": 5.111, |
| "step": 1176 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.7449887990951538, |
| "learning_rate": 8.542349726775956e-05, |
| "loss": 5.3291, |
| "step": 1568 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 5.36224889755249, |
| "eval_runtime": 19.3778, |
| "eval_samples_per_second": 1301.028, |
| "eval_steps_per_second": 5.109, |
| "step": 1568 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.7372640371322632, |
| "learning_rate": 8.006830601092896e-05, |
| "loss": 5.2305, |
| "step": 1960 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 5.299103260040283, |
| "eval_runtime": 19.3631, |
| "eval_samples_per_second": 1302.012, |
| "eval_steps_per_second": 5.113, |
| "step": 1960 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 7840, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.341631135744e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
