| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004282960953672639, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001427653651224213, | |
| "eval_loss": 10.38209342956543, | |
| "eval_runtime": 23.8527, | |
| "eval_samples_per_second": 123.676, | |
| "eval_steps_per_second": 61.838, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004282960953672639, | |
| "grad_norm": 0.036336805671453476, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008565921907345278, | |
| "grad_norm": 0.04034361615777016, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3811, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011421229209793704, | |
| "eval_loss": 10.381678581237793, | |
| "eval_runtime": 23.9133, | |
| "eval_samples_per_second": 123.362, | |
| "eval_steps_per_second": 61.681, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012848882861017917, | |
| "grad_norm": 0.03255653753876686, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3806, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017131843814690555, | |
| "grad_norm": 0.0432903878390789, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.381, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021414804768363194, | |
| "grad_norm": 0.028852997347712517, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002284245841958741, | |
| "eval_loss": 10.380470275878906, | |
| "eval_runtime": 23.981, | |
| "eval_samples_per_second": 123.014, | |
| "eval_steps_per_second": 61.507, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0025697765722035833, | |
| "grad_norm": 0.038364723324775696, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002998072667570847, | |
| "grad_norm": 0.03003763221204281, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.379, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003426368762938111, | |
| "grad_norm": 0.02970338612794876, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3791, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003426368762938111, | |
| "eval_loss": 10.379654884338379, | |
| "eval_runtime": 24.1555, | |
| "eval_samples_per_second": 122.125, | |
| "eval_steps_per_second": 61.063, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003854664858305375, | |
| "grad_norm": 0.04011055454611778, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3783, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004282960953672639, | |
| "grad_norm": 0.027406610548496246, | |
| "learning_rate": 0.0, | |
| "loss": 10.3788, | |
| "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": 1516770951168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |