| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018501387604070305, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006167129201356768, | |
| "eval_loss": 3.5650603771209717, | |
| "eval_runtime": 92.818, | |
| "eval_samples_per_second": 7.358, | |
| "eval_steps_per_second": 3.685, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "grad_norm": 1.1820497512817383, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5986, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037002775208140612, | |
| "grad_norm": 1.860599160194397, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3325, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004933703361085414, | |
| "eval_loss": 3.097452163696289, | |
| "eval_runtime": 93.1595, | |
| "eval_samples_per_second": 7.332, | |
| "eval_steps_per_second": 3.671, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005550416281221091, | |
| "grad_norm": 0.8140160441398621, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1377, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0074005550416281225, | |
| "grad_norm": 0.894902765750885, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.0202, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009250693802035153, | |
| "grad_norm": 0.5678002834320068, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.8962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009867406722170829, | |
| "eval_loss": 2.8576066493988037, | |
| "eval_runtime": 93.4677, | |
| "eval_samples_per_second": 7.307, | |
| "eval_steps_per_second": 3.659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011100832562442183, | |
| "grad_norm": 0.9780793190002441, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.8131, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012950971322849213, | |
| "grad_norm": 0.4450037479400635, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.6101, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014801110083256245, | |
| "grad_norm": 0.4622777998447418, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.7151, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014801110083256245, | |
| "eval_loss": 2.810142993927002, | |
| "eval_runtime": 94.2087, | |
| "eval_samples_per_second": 7.25, | |
| "eval_steps_per_second": 3.63, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016651248843663275, | |
| "grad_norm": 0.5054405331611633, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.6541, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018501387604070305, | |
| "grad_norm": 0.3172176778316498, | |
| "learning_rate": 0.0, | |
| "loss": 2.6418, | |
| "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": 1.1272153982828544e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |