| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006395088571976722, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012790177143953444, | |
| "eval_loss": 2.226850748062134, | |
| "eval_runtime": 81.1327, | |
| "eval_samples_per_second": 40.575, | |
| "eval_steps_per_second": 20.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006395088571976722, | |
| "grad_norm": 5.315217971801758, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0454, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012790177143953444, | |
| "grad_norm": 7.136112213134766, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6147, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012790177143953444, | |
| "eval_loss": 2.074836015701294, | |
| "eval_runtime": 82.5022, | |
| "eval_samples_per_second": 39.902, | |
| "eval_steps_per_second": 19.951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019185265715930167, | |
| "grad_norm": 6.462134838104248, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.4957, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002558035428790689, | |
| "grad_norm": 7.336491584777832, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.7107, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002558035428790689, | |
| "eval_loss": 1.8417083024978638, | |
| "eval_runtime": 82.7115, | |
| "eval_samples_per_second": 39.801, | |
| "eval_steps_per_second": 19.9, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003197544285988361, | |
| "grad_norm": 7.918294429779053, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.4426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0038370531431860333, | |
| "grad_norm": 8.098969459533691, | |
| "learning_rate": 5e-05, | |
| "loss": 6.855, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0038370531431860333, | |
| "eval_loss": 1.7846605777740479, | |
| "eval_runtime": 82.8191, | |
| "eval_samples_per_second": 39.749, | |
| "eval_steps_per_second": 19.875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004476562000383705, | |
| "grad_norm": 7.103973865509033, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.1707, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005116070857581378, | |
| "grad_norm": 8.697281837463379, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.0684, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005116070857581378, | |
| "eval_loss": 1.7659326791763306, | |
| "eval_runtime": 83.0156, | |
| "eval_samples_per_second": 39.655, | |
| "eval_steps_per_second": 19.828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00575557971477905, | |
| "grad_norm": 7.536022186279297, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.0319, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006395088571976722, | |
| "grad_norm": 8.265710830688477, | |
| "learning_rate": 0.0, | |
| "loss": 6.9004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006395088571976722, | |
| "eval_loss": 1.761187195777893, | |
| "eval_runtime": 82.7895, | |
| "eval_samples_per_second": 39.763, | |
| "eval_steps_per_second": 19.882, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1492861845504000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |