| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007778317938745746, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.778317938745747e-05, | |
| "grad_norm": 1.6173714399337769, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5142, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.778317938745747e-05, | |
| "eval_loss": 3.8527331352233887, | |
| "eval_runtime": 164.7874, | |
| "eval_samples_per_second": 32.854, | |
| "eval_steps_per_second": 16.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015556635877491494, | |
| "grad_norm": 2.179248094558716, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0158, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023334953816237238, | |
| "grad_norm": 1.6552778482437134, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7406, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023334953816237238, | |
| "eval_loss": 3.8376524448394775, | |
| "eval_runtime": 164.1279, | |
| "eval_samples_per_second": 32.986, | |
| "eval_steps_per_second": 16.493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00031113271754982987, | |
| "grad_norm": 2.039921283721924, | |
| "learning_rate": 8e-05, | |
| "loss": 3.9739, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003889158969372873, | |
| "grad_norm": 1.9039194583892822, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3947, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00046669907632474475, | |
| "grad_norm": 2.235607624053955, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3443, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00046669907632474475, | |
| "eval_loss": 3.4949259757995605, | |
| "eval_runtime": 164.0829, | |
| "eval_samples_per_second": 32.996, | |
| "eval_steps_per_second": 16.498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005444822557122023, | |
| "grad_norm": 2.643089532852173, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4304, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006222654350996597, | |
| "grad_norm": 2.6849687099456787, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1282, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007000486144871172, | |
| "grad_norm": 3.3133139610290527, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8319, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007000486144871172, | |
| "eval_loss": 2.61970591545105, | |
| "eval_runtime": 164.1071, | |
| "eval_samples_per_second": 32.991, | |
| "eval_steps_per_second": 16.495, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007778317938745746, | |
| "grad_norm": 2.8337090015411377, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6607, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |