| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017543859649122806, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "grad_norm": 1.9267454263172112e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2555, | |
| "eval_samples_per_second": 191.162, | |
| "eval_steps_per_second": 95.581, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035087719298245615, | |
| "grad_norm": 3.091491089435294e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 4.9085520004155114e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2472, | |
| "eval_samples_per_second": 192.427, | |
| "eval_steps_per_second": 96.214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 3.208043926861137e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 1.6017580492189154e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 1.7939628378371708e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2745, | |
| "eval_samples_per_second": 188.312, | |
| "eval_steps_per_second": 94.156, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012280701754385965, | |
| "grad_norm": 2.9179635021137074e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 5.349150887923315e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "grad_norm": 5.942728603258729e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2263, | |
| "eval_samples_per_second": 195.707, | |
| "eval_steps_per_second": 97.853, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 5.0837617891374975e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |