| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016842105263157894, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "grad_norm": 3.249983072280884, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 3.4262592792510986, | |
| "eval_runtime": 9.0175, | |
| "eval_samples_per_second": 27.724, | |
| "eval_steps_per_second": 13.862, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003368421052631579, | |
| "grad_norm": 3.300755739212036, | |
| "learning_rate": 4e-05, | |
| "loss": 2.131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 3.6411943435668945, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9524, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "eval_loss": 3.3758413791656494, | |
| "eval_runtime": 9.0077, | |
| "eval_samples_per_second": 27.754, | |
| "eval_steps_per_second": 13.877, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006736842105263158, | |
| "grad_norm": 3.872809886932373, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4719, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 3.7300257682800293, | |
| "learning_rate": 0.0001, | |
| "loss": 2.528, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 4.199929714202881, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3181, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "eval_loss": 2.926605463027954, | |
| "eval_runtime": 9.0468, | |
| "eval_samples_per_second": 27.634, | |
| "eval_steps_per_second": 13.817, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011789473684210527, | |
| "grad_norm": 4.478844165802002, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3401, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013473684210526317, | |
| "grad_norm": 7.691252708435059, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8588, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 2.9956653118133545, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "eval_loss": 2.2680604457855225, | |
| "eval_runtime": 9.0829, | |
| "eval_samples_per_second": 27.524, | |
| "eval_steps_per_second": 13.762, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 2.5398459434509277, | |
| "learning_rate": 0.0002, | |
| "loss": 1.902, | |
| "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": 1911091416268800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |