| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013699849986642647, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7399699973285294e-05, | |
| "eval_loss": 2.6317927837371826, | |
| "eval_runtime": 1033.4642, | |
| "eval_samples_per_second": 14.87, | |
| "eval_steps_per_second": 7.435, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013699849986642645, | |
| "grad_norm": 1.359126329421997, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4939, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002739969997328529, | |
| "grad_norm": 1.844275712966919, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002739969997328529, | |
| "eval_loss": 1.8647905588150024, | |
| "eval_runtime": 1036.491, | |
| "eval_samples_per_second": 14.827, | |
| "eval_steps_per_second": 7.413, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00041099549959927936, | |
| "grad_norm": 1.6798439025878906, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3597, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005479939994657058, | |
| "grad_norm": 1.5783166885375977, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8251, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005479939994657058, | |
| "eval_loss": 0.7624468803405762, | |
| "eval_runtime": 1041.0681, | |
| "eval_samples_per_second": 14.762, | |
| "eval_steps_per_second": 7.381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006849924993321323, | |
| "grad_norm": 1.459263563156128, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6941, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008219909991985587, | |
| "grad_norm": 1.2582858800888062, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008219909991985587, | |
| "eval_loss": 0.589572012424469, | |
| "eval_runtime": 1036.876, | |
| "eval_samples_per_second": 14.821, | |
| "eval_steps_per_second": 7.411, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009589894990649852, | |
| "grad_norm": 1.1963167190551758, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6821, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0010959879989314116, | |
| "grad_norm": 1.1443864107131958, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010959879989314116, | |
| "eval_loss": 0.531443178653717, | |
| "eval_runtime": 1040.094, | |
| "eval_samples_per_second": 14.776, | |
| "eval_steps_per_second": 7.388, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0012329864987978383, | |
| "grad_norm": 1.2471452951431274, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4965, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0013699849986642647, | |
| "grad_norm": 0.9611670970916748, | |
| "learning_rate": 0.0, | |
| "loss": 0.4534, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0013699849986642647, | |
| "eval_loss": 0.5210013389587402, | |
| "eval_runtime": 1041.6703, | |
| "eval_samples_per_second": 14.753, | |
| "eval_steps_per_second": 7.377, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9432777665544192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |