| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005285179475886369, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001761726491962123, | |
| "eval_loss": 1.258076548576355, | |
| "eval_runtime": 351.7517, | |
| "eval_samples_per_second": 6.797, | |
| "eval_steps_per_second": 3.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005285179475886368, | |
| "grad_norm": 1.8236202001571655, | |
| "learning_rate": 6e-05, | |
| "loss": 4.8041, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010570358951772737, | |
| "grad_norm": 2.2088983058929443, | |
| "learning_rate": 0.00012, | |
| "loss": 5.2211, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014093811935696984, | |
| "eval_loss": 1.0344609022140503, | |
| "eval_runtime": 353.8305, | |
| "eval_samples_per_second": 6.757, | |
| "eval_steps_per_second": 3.38, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015855538427659106, | |
| "grad_norm": 1.4011439085006714, | |
| "learning_rate": 0.00018, | |
| "loss": 4.4971, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021140717903545474, | |
| "grad_norm": 2.4960269927978516, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.7786, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0026425897379431843, | |
| "grad_norm": 1.7385677099227905, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.3206, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0028187623871393968, | |
| "eval_loss": 0.7006307244300842, | |
| "eval_runtime": 354.0153, | |
| "eval_samples_per_second": 6.754, | |
| "eval_steps_per_second": 3.378, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0031711076855318212, | |
| "grad_norm": 1.7371435165405273, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.6688, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003699625633120458, | |
| "grad_norm": 1.4975641965866089, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.3158, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004228143580709095, | |
| "grad_norm": 1.9014939069747925, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.6375, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004228143580709095, | |
| "eval_loss": 0.5634551048278809, | |
| "eval_runtime": 354.047, | |
| "eval_samples_per_second": 6.753, | |
| "eval_steps_per_second": 3.378, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004756661528297732, | |
| "grad_norm": 1.679165244102478, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.4099, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005285179475886369, | |
| "grad_norm": 1.5690745115280151, | |
| "learning_rate": 0.0, | |
| "loss": 2.2271, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.515571136528384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |