| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.5616522431373596, | |
| "learning_rate": 4.82e-05, | |
| "loss": 1.1747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.6579018831253052, | |
| "learning_rate": 4.6200000000000005e-05, | |
| "loss": 1.0469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.7981964349746704, | |
| "learning_rate": 4.4200000000000004e-05, | |
| "loss": 1.0567, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.9774985909461975, | |
| "learning_rate": 4.22e-05, | |
| "loss": 0.9834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.6699696779251099, | |
| "learning_rate": 4.02e-05, | |
| "loss": 1.033, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.7246522903442383, | |
| "learning_rate": 3.82e-05, | |
| "loss": 0.9588, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.6503073573112488, | |
| "learning_rate": 3.62e-05, | |
| "loss": 1.1316, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.7243292331695557, | |
| "learning_rate": 3.4200000000000005e-05, | |
| "loss": 1.105, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.6837774515151978, | |
| "learning_rate": 3.2200000000000003e-05, | |
| "loss": 1.0431, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.7276621460914612, | |
| "learning_rate": 3.02e-05, | |
| "loss": 1.0878, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.5852382183074951, | |
| "learning_rate": 2.8199999999999998e-05, | |
| "loss": 1.0713, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.6434891223907471, | |
| "learning_rate": 2.6200000000000003e-05, | |
| "loss": 1.0564, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.8133268356323242, | |
| "learning_rate": 2.4200000000000002e-05, | |
| "loss": 1.0184, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.6674674153327942, | |
| "learning_rate": 2.22e-05, | |
| "loss": 0.9579, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.7289815545082092, | |
| "learning_rate": 2.0200000000000003e-05, | |
| "loss": 1.0709, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.8111977577209473, | |
| "learning_rate": 1.8200000000000002e-05, | |
| "loss": 1.0948, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.822685182094574, | |
| "learning_rate": 1.62e-05, | |
| "loss": 1.0823, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.7154224514961243, | |
| "learning_rate": 1.42e-05, | |
| "loss": 0.9634, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.6793033480644226, | |
| "learning_rate": 1.22e-05, | |
| "loss": 0.9934, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.6630302667617798, | |
| "learning_rate": 1.02e-05, | |
| "loss": 0.9866, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.8769239187240601, | |
| "learning_rate": 8.200000000000001e-06, | |
| "loss": 0.8853, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.7216284275054932, | |
| "learning_rate": 6.2e-06, | |
| "loss": 0.9867, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.9310891032218933, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 0.9694, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.816041111946106, | |
| "learning_rate": 2.2e-06, | |
| "loss": 0.9702, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7796522974967957, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 0.9702, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3181482344448000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |