| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.046620046620046623, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004662004662004662, | |
| "grad_norm": 7.565432071685791, | |
| "learning_rate": 2e-05, | |
| "loss": 10.114, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004662004662004662, | |
| "eval_loss": 9.789741516113281, | |
| "eval_runtime": 0.6865, | |
| "eval_samples_per_second": 132.55, | |
| "eval_steps_per_second": 67.003, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009324009324009324, | |
| "grad_norm": 8.629670143127441, | |
| "learning_rate": 4e-05, | |
| "loss": 9.945, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013986013986013986, | |
| "grad_norm": 6.395711898803711, | |
| "learning_rate": 6e-05, | |
| "loss": 10.2802, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013986013986013986, | |
| "eval_loss": 9.781152725219727, | |
| "eval_runtime": 0.6971, | |
| "eval_samples_per_second": 130.534, | |
| "eval_steps_per_second": 65.984, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018648018648018648, | |
| "grad_norm": 6.709271430969238, | |
| "learning_rate": 8e-05, | |
| "loss": 9.7886, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023310023310023312, | |
| "grad_norm": 4.035851001739502, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4621, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027972027972027972, | |
| "grad_norm": 7.662912845611572, | |
| "learning_rate": 0.00012, | |
| "loss": 10.1554, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027972027972027972, | |
| "eval_loss": 9.638227462768555, | |
| "eval_runtime": 0.7434, | |
| "eval_samples_per_second": 122.414, | |
| "eval_steps_per_second": 61.88, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03263403263403263, | |
| "grad_norm": 7.706947326660156, | |
| "learning_rate": 0.00014, | |
| "loss": 9.685, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037296037296037296, | |
| "grad_norm": 10.190275192260742, | |
| "learning_rate": 0.00016, | |
| "loss": 9.6822, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04195804195804196, | |
| "grad_norm": 9.342390060424805, | |
| "learning_rate": 0.00018, | |
| "loss": 9.8531, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04195804195804196, | |
| "eval_loss": 9.292366981506348, | |
| "eval_runtime": 0.7236, | |
| "eval_samples_per_second": 125.766, | |
| "eval_steps_per_second": 63.574, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.046620046620046623, | |
| "grad_norm": 8.551138877868652, | |
| "learning_rate": 0.0002, | |
| "loss": 9.2544, | |
| "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": 1081715982336.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |