| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004026129580980564, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.026129580980564e-05, | |
| "grad_norm": 3.8906490802764893, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8591, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.026129580980564e-05, | |
| "eval_loss": 1.138015627861023, | |
| "eval_runtime": 169.9667, | |
| "eval_samples_per_second": 61.536, | |
| "eval_steps_per_second": 30.771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.052259161961128e-05, | |
| "grad_norm": 4.960000514984131, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2235, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012078388742941691, | |
| "grad_norm": 3.729585647583008, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0223, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012078388742941691, | |
| "eval_loss": 1.107124924659729, | |
| "eval_runtime": 169.7375, | |
| "eval_samples_per_second": 61.619, | |
| "eval_steps_per_second": 30.812, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016104518323922256, | |
| "grad_norm": 4.285777568817139, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1406, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002013064790490282, | |
| "grad_norm": 4.24346399307251, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024156777485883382, | |
| "grad_norm": 3.9971883296966553, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8726, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024156777485883382, | |
| "eval_loss": 0.6596404910087585, | |
| "eval_runtime": 170.026, | |
| "eval_samples_per_second": 61.514, | |
| "eval_steps_per_second": 30.76, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002818290706686395, | |
| "grad_norm": 3.6897239685058594, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5946, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003220903664784451, | |
| "grad_norm": 4.003920555114746, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5745, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00036235166228825073, | |
| "grad_norm": 2.6077499389648438, | |
| "learning_rate": 0.00018, | |
| "loss": 0.2364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00036235166228825073, | |
| "eval_loss": 0.16095003485679626, | |
| "eval_runtime": 171.0825, | |
| "eval_samples_per_second": 61.134, | |
| "eval_steps_per_second": 30.57, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004026129580980564, | |
| "grad_norm": 1.9512896537780762, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1299, | |
| "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": 489477793382400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |