| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0678466076696165, | |
| "eval_steps": 3, | |
| "global_step": 11, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0943952802359882, | |
| "grad_norm": 0.1971358209848404, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6567, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0943952802359882, | |
| "eval_loss": 0.85373455286026, | |
| "eval_runtime": 5.3495, | |
| "eval_samples_per_second": 13.459, | |
| "eval_steps_per_second": 3.365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1887905604719764, | |
| "grad_norm": 0.18910476565361023, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6616, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 0.18931685388088226, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6363, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "eval_loss": 0.8524961471557617, | |
| "eval_runtime": 4.6731, | |
| "eval_samples_per_second": 15.407, | |
| "eval_steps_per_second": 3.852, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3775811209439528, | |
| "grad_norm": 0.18228459358215332, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6263, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.471976401179941, | |
| "grad_norm": 0.18348485231399536, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6098, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 0.1853514462709427, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6469, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "eval_loss": 0.8376555442810059, | |
| "eval_runtime": 4.6732, | |
| "eval_samples_per_second": 15.407, | |
| "eval_steps_per_second": 3.852, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6607669616519174, | |
| "grad_norm": 0.1833762377500534, | |
| "learning_rate": 7e-05, | |
| "loss": 0.7417, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7551622418879056, | |
| "grad_norm": 0.2062716782093048, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6748, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 0.17450149357318878, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "eval_loss": 0.7961457371711731, | |
| "eval_runtime": 4.6683, | |
| "eval_samples_per_second": 15.423, | |
| "eval_steps_per_second": 3.856, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.943952802359882, | |
| "grad_norm": 0.15376947820186615, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5393, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0678466076696165, | |
| "grad_norm": 0.3497083783149719, | |
| "learning_rate": 0.0, | |
| "loss": 1.117, | |
| "step": 11 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 11, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 9.705131010844262e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |