| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.18248175182481752, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0036496350364963502, |
| "eval_loss": 8.032208442687988, |
| "eval_runtime": 6.3647, |
| "eval_samples_per_second": 18.225, |
| "eval_steps_per_second": 9.113, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.01824817518248175, |
| "grad_norm": 11.895684242248535, |
| "learning_rate": 5e-05, |
| "loss": 7.7326, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0364963503649635, |
| "grad_norm": 12.489108085632324, |
| "learning_rate": 0.0001, |
| "loss": 6.1782, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0364963503649635, |
| "eval_loss": 4.179005146026611, |
| "eval_runtime": 6.3854, |
| "eval_samples_per_second": 18.166, |
| "eval_steps_per_second": 9.083, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05474452554744526, |
| "grad_norm": 12.432720184326172, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.7055, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.072992700729927, |
| "grad_norm": 14.823360443115234, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.7577, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.072992700729927, |
| "eval_loss": 1.3997901678085327, |
| "eval_runtime": 6.3225, |
| "eval_samples_per_second": 18.347, |
| "eval_steps_per_second": 9.174, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09124087591240876, |
| "grad_norm": 6.508552551269531, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.757, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.10948905109489052, |
| "grad_norm": 7.162863731384277, |
| "learning_rate": 5e-05, |
| "loss": 1.5102, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.10948905109489052, |
| "eval_loss": 1.1935330629348755, |
| "eval_runtime": 6.4101, |
| "eval_samples_per_second": 18.097, |
| "eval_steps_per_second": 9.048, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.12773722627737227, |
| "grad_norm": 8.839790344238281, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.461, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.145985401459854, |
| "grad_norm": 8.390496253967285, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.4076, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.145985401459854, |
| "eval_loss": 1.140897274017334, |
| "eval_runtime": 6.4822, |
| "eval_samples_per_second": 17.895, |
| "eval_steps_per_second": 8.948, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.16423357664233576, |
| "grad_norm": 10.96522331237793, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.2903, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.18248175182481752, |
| "grad_norm": 9.890042304992676, |
| "learning_rate": 0.0, |
| "loss": 1.5304, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.18248175182481752, |
| "eval_loss": 1.1241391897201538, |
| "eval_runtime": 6.3738, |
| "eval_samples_per_second": 18.199, |
| "eval_steps_per_second": 9.1, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2512989086810112.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
