| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.05, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005, |
| "grad_norm": 7.283497333526611, |
| "learning_rate": 2.7e-06, |
| "loss": 9.9652685546875, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 2.230577230453491, |
| "learning_rate": 5.34e-06, |
| "loss": 7.3708349609375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.015, |
| "grad_norm": 2.9674696922302246, |
| "learning_rate": 8.040000000000001e-06, |
| "loss": 6.394255981445313, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 5.306502819061279, |
| "learning_rate": 1.074e-05, |
| "loss": 6.023402709960937, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 4.985537528991699, |
| "learning_rate": 1.3500000000000001e-05, |
| "loss": 6.261904907226563, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 3.5350327491760254, |
| "learning_rate": 1.65e-05, |
| "loss": 5.984814453125, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.035, |
| "grad_norm": 2.3650736808776855, |
| "learning_rate": 1.95e-05, |
| "loss": 5.866536865234375, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 2.358975410461426, |
| "learning_rate": 2.25e-05, |
| "loss": 6.0157708740234375, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.045, |
| "grad_norm": 2.671454429626465, |
| "learning_rate": 2.55e-05, |
| "loss": 6.32117919921875, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 2.476318359375, |
| "learning_rate": 2.8499999999999998e-05, |
| "loss": 6.613551025390625, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 10000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "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": 4.072103585483981e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
