| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07894736842105263, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002631578947368421, | |
| "eval_loss": 2.1429615020751953, | |
| "eval_runtime": 17.759, | |
| "eval_samples_per_second": 9.01, | |
| "eval_steps_per_second": 4.505, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007894736842105263, | |
| "grad_norm": 7.062963485717773, | |
| "learning_rate": 6e-05, | |
| "loss": 8.3328, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "grad_norm": 7.553915977478027, | |
| "learning_rate": 0.00012, | |
| "loss": 8.4467, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "eval_loss": 1.8446743488311768, | |
| "eval_runtime": 17.6117, | |
| "eval_samples_per_second": 9.085, | |
| "eval_steps_per_second": 4.542, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02368421052631579, | |
| "grad_norm": 6.601487636566162, | |
| "learning_rate": 0.00018, | |
| "loss": 7.217, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "grad_norm": 6.743226528167725, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.2202, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 6.807640552520752, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.4417, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 1.664109468460083, | |
| "eval_runtime": 17.6759, | |
| "eval_samples_per_second": 9.052, | |
| "eval_steps_per_second": 4.526, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04736842105263158, | |
| "grad_norm": 6.45584774017334, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.7004, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05526315789473684, | |
| "grad_norm": 6.424158573150635, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.5881, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "grad_norm": 7.330375671386719, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 6.414, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "eval_loss": 1.5946496725082397, | |
| "eval_runtime": 17.8275, | |
| "eval_samples_per_second": 8.975, | |
| "eval_steps_per_second": 4.487, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07105263157894737, | |
| "grad_norm": 6.634846210479736, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.3574, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 6.49539852142334, | |
| "learning_rate": 0.0, | |
| "loss": 6.3453, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801873028546560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |