| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03762541806020067, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001254180602006689, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.9935, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 3.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003762541806020067, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007525083612040134, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010033444816053512, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.1755, | |
| "eval_samples_per_second": 6.966, | |
| "eval_steps_per_second": 3.483, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0112876254180602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015050167224080268, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018812709030100336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020066889632107024, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.3207, | |
| "eval_samples_per_second": 6.938, | |
| "eval_steps_per_second": 3.469, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0225752508361204, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026337792642140468, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012653483024396533, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030100334448160536, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.030100334448160536, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.3584, | |
| "eval_samples_per_second": 6.931, | |
| "eval_steps_per_second": 3.465, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0338628762541806, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.634902137174483e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03762541806020067, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 1.4376222175789056e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |