| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00023673121537805974, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3673121537805975e-05, | |
| "grad_norm": 1.7583783864974976, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5384, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.3673121537805975e-05, | |
| "eval_loss": 1.7546149492263794, | |
| "eval_runtime": 515.8762, | |
| "eval_samples_per_second": 34.479, | |
| "eval_steps_per_second": 17.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.734624307561195e-05, | |
| "grad_norm": 1.560328722000122, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9956, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.101936461341793e-05, | |
| "grad_norm": 2.629258394241333, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7636, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.101936461341793e-05, | |
| "eval_loss": 1.7382676601409912, | |
| "eval_runtime": 514.9284, | |
| "eval_samples_per_second": 34.543, | |
| "eval_steps_per_second": 17.272, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.46924861512239e-05, | |
| "grad_norm": 2.8225064277648926, | |
| "learning_rate": 8e-05, | |
| "loss": 1.672, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011836560768902987, | |
| "grad_norm": 2.1037559509277344, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5066, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00014203872922683586, | |
| "grad_norm": 2.2576792240142822, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014203872922683586, | |
| "eval_loss": 1.6413675546646118, | |
| "eval_runtime": 1074.9501, | |
| "eval_samples_per_second": 16.547, | |
| "eval_steps_per_second": 8.274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001657118507646418, | |
| "grad_norm": 1.7553894519805908, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7371, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001893849723024478, | |
| "grad_norm": 2.429262638092041, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7913, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00021305809384025378, | |
| "grad_norm": 2.018078327178955, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1738, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00021305809384025378, | |
| "eval_loss": 1.3432157039642334, | |
| "eval_runtime": 1108.4642, | |
| "eval_samples_per_second": 16.047, | |
| "eval_steps_per_second": 8.024, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00023673121537805974, | |
| "grad_norm": 2.38704514503479, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1479, | |
| "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": 1628733135912960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |