| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004642525533890436, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046425255338904364, | |
| "grad_norm": 5.013631343841553, | |
| "learning_rate": 2e-05, | |
| "loss": 22.6464, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00046425255338904364, | |
| "eval_loss": 5.929390907287598, | |
| "eval_runtime": 25.8534, | |
| "eval_samples_per_second": 35.082, | |
| "eval_steps_per_second": 17.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "grad_norm": 4.507352352142334, | |
| "learning_rate": 4e-05, | |
| "loss": 23.9057, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001392757660167131, | |
| "grad_norm": 7.23059606552124, | |
| "learning_rate": 6e-05, | |
| "loss": 24.7785, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001392757660167131, | |
| "eval_loss": 5.926706314086914, | |
| "eval_runtime": 24.9456, | |
| "eval_samples_per_second": 36.359, | |
| "eval_steps_per_second": 18.2, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018570102135561746, | |
| "grad_norm": 4.407309055328369, | |
| "learning_rate": 8e-05, | |
| "loss": 23.2703, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002321262766945218, | |
| "grad_norm": 6.365769386291504, | |
| "learning_rate": 0.0001, | |
| "loss": 25.2618, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "grad_norm": 6.251041889190674, | |
| "learning_rate": 0.00012, | |
| "loss": 21.8259, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "eval_loss": 5.754109859466553, | |
| "eval_runtime": 25.0192, | |
| "eval_samples_per_second": 36.252, | |
| "eval_steps_per_second": 18.146, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032497678737233053, | |
| "grad_norm": 9.705223083496094, | |
| "learning_rate": 0.00014, | |
| "loss": 26.6085, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003714020427112349, | |
| "grad_norm": 11.967326164245605, | |
| "learning_rate": 0.00016, | |
| "loss": 22.8609, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004178272980501393, | |
| "grad_norm": 12.387564659118652, | |
| "learning_rate": 0.00018, | |
| "loss": 17.409, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004178272980501393, | |
| "eval_loss": 4.916599750518799, | |
| "eval_runtime": 25.1347, | |
| "eval_samples_per_second": 36.086, | |
| "eval_steps_per_second": 18.063, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "grad_norm": 13.253218650817871, | |
| "learning_rate": 0.0002, | |
| "loss": 19.0262, | |
| "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": 1632478030725120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |