| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009992366941919368, | |
| "eval_steps": 9, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002775657483866491, | |
| "eval_loss": 0.5042526125907898, | |
| "eval_runtime": 655.4432, | |
| "eval_samples_per_second": 9.258, | |
| "eval_steps_per_second": 1.158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008326972451599472, | |
| "grad_norm": 0.27662014961242676, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.526, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016653944903198944, | |
| "grad_norm": 0.27963921427726746, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4897, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002498091735479842, | |
| "grad_norm": 0.29799002408981323, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.5052, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002498091735479842, | |
| "eval_loss": 0.4782797694206238, | |
| "eval_runtime": 660.6166, | |
| "eval_samples_per_second": 9.185, | |
| "eval_steps_per_second": 1.149, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003330788980639789, | |
| "grad_norm": 0.23466083407402039, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.4373, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004163486225799737, | |
| "grad_norm": 0.20258335769176483, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.4476, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004996183470959684, | |
| "grad_norm": 0.22826525568962097, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 0.4442, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004996183470959684, | |
| "eval_loss": 0.42058902978897095, | |
| "eval_runtime": 660.3378, | |
| "eval_samples_per_second": 9.189, | |
| "eval_steps_per_second": 1.149, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0058288807161196304, | |
| "grad_norm": 0.20002856850624084, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 0.4395, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006661577961279578, | |
| "grad_norm": 0.21906918287277222, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 0.423, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007494275206439525, | |
| "grad_norm": 0.1747865527868271, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 0.4055, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007494275206439525, | |
| "eval_loss": 0.39028802514076233, | |
| "eval_runtime": 660.3218, | |
| "eval_samples_per_second": 9.189, | |
| "eval_steps_per_second": 1.149, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008326972451599473, | |
| "grad_norm": 0.15783219039440155, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.3895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00915966969675942, | |
| "grad_norm": 0.17900213599205017, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 0.4093, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009992366941919368, | |
| "grad_norm": 0.14911402761936188, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 0.3543, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009992366941919368, | |
| "eval_loss": 0.3740505874156952, | |
| "eval_runtime": 660.2612, | |
| "eval_samples_per_second": 9.19, | |
| "eval_steps_per_second": 1.15, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.689425626595328e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |