| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6397952655150352, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06397952655150352, | |
| "grad_norm": 5.188015460968018, | |
| "learning_rate": 4.8944337811900195e-05, | |
| "loss": 0.5162, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12795905310300704, | |
| "grad_norm": 8.62886905670166, | |
| "learning_rate": 4.7878012369375135e-05, | |
| "loss": 0.4123, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19193857965451055, | |
| "grad_norm": 6.661285877227783, | |
| "learning_rate": 4.681168692685008e-05, | |
| "loss": 0.4106, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2559181062060141, | |
| "grad_norm": 7.992310523986816, | |
| "learning_rate": 4.5745361484325014e-05, | |
| "loss": 0.3619, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3198976327575176, | |
| "grad_norm": 8.48903751373291, | |
| "learning_rate": 4.467903604179996e-05, | |
| "loss": 0.3724, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3838771593090211, | |
| "grad_norm": 7.3620219230651855, | |
| "learning_rate": 4.3612710599274906e-05, | |
| "loss": 0.3582, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44785668586052463, | |
| "grad_norm": 7.127757549285889, | |
| "learning_rate": 4.254638515674984e-05, | |
| "loss": 0.351, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5118362124120281, | |
| "grad_norm": 8.284778594970703, | |
| "learning_rate": 4.1480059714224785e-05, | |
| "loss": 0.3517, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5758157389635317, | |
| "grad_norm": 6.389641284942627, | |
| "learning_rate": 4.0413734271699725e-05, | |
| "loss": 0.3197, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6397952655150352, | |
| "grad_norm": 8.652924537658691, | |
| "learning_rate": 3.9347408829174664e-05, | |
| "loss": 0.3457, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4689, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1052444221440000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |