| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013475071118430903, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014972301242701004, | |
| "grad_norm": 5.139781951904297, | |
| "learning_rate": 2e-05, | |
| "loss": 13.9691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014972301242701004, | |
| "eval_loss": 3.1406643390655518, | |
| "eval_runtime": 277.2269, | |
| "eval_samples_per_second": 10.147, | |
| "eval_steps_per_second": 5.075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002994460248540201, | |
| "grad_norm": 3.421827554702759, | |
| "learning_rate": 4e-05, | |
| "loss": 12.1924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004491690372810301, | |
| "grad_norm": 2.9491159915924072, | |
| "learning_rate": 6e-05, | |
| "loss": 10.6957, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004491690372810301, | |
| "eval_loss": 3.1349191665649414, | |
| "eval_runtime": 277.2837, | |
| "eval_samples_per_second": 10.145, | |
| "eval_steps_per_second": 5.074, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005988920497080402, | |
| "grad_norm": 3.7658534049987793, | |
| "learning_rate": 8e-05, | |
| "loss": 13.3329, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007486150621350501, | |
| "grad_norm": 3.601372241973877, | |
| "learning_rate": 0.0001, | |
| "loss": 12.3815, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008983380745620602, | |
| "grad_norm": 4.870517730712891, | |
| "learning_rate": 0.00012, | |
| "loss": 13.1262, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008983380745620602, | |
| "eval_loss": 3.0220553874969482, | |
| "eval_runtime": 277.2274, | |
| "eval_samples_per_second": 10.147, | |
| "eval_steps_per_second": 5.075, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010480610869890701, | |
| "grad_norm": 7.179202079772949, | |
| "learning_rate": 0.00014, | |
| "loss": 13.0076, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011977840994160803, | |
| "grad_norm": 7.2814178466796875, | |
| "learning_rate": 0.00016, | |
| "loss": 11.1482, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013475071118430903, | |
| "grad_norm": 8.782493591308594, | |
| "learning_rate": 0.00018, | |
| "loss": 10.904, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013475071118430903, | |
| "eval_loss": 2.6142091751098633, | |
| "eval_runtime": 209.0104, | |
| "eval_samples_per_second": 13.459, | |
| "eval_steps_per_second": 6.732, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1588030510989312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |