| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 15.431024551391602, | |
| "learning_rate": 0.0, | |
| "loss": 5.2835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 15.431879043579102, | |
| "learning_rate": 4e-05, | |
| "loss": 5.2835, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 14.52097225189209, | |
| "learning_rate": 8e-05, | |
| "loss": 4.9335, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 7.527328014373779, | |
| "learning_rate": 0.00012, | |
| "loss": 3.6646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 10.276887893676758, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 6.039588451385498, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7373, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 3.487266778945923, | |
| "learning_rate": 0.000192, | |
| "loss": 0.8735, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 2.9169163703918457, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.3411, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 0.7490823864936829, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.0589, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.4124163389205933, | |
| "learning_rate": 0.000168, | |
| "loss": 0.0533, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 1.3603249788284302, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0397, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.7485616207122803, | |
| "learning_rate": 0.000152, | |
| "loss": 0.0232, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 0.3160126805305481, | |
| "learning_rate": 0.000144, | |
| "loss": 0.0114, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 0.39901483058929443, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.0075, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.38916680216789246, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.0051, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.3773799538612366, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0038, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "grad_norm": 0.21171778440475464, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.0021, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 0.12317345291376114, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.0013, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "grad_norm": 0.06952201575040817, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0008, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.05174114927649498, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0006, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 0.03263603150844574, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0005, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 0.022345170378684998, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0003, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "grad_norm": 0.019066136330366135, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0003, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.01889193058013916, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0003, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.013505947776138783, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0002, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 0.011558088473975658, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0002, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.216, | |
| "grad_norm": 0.010295114479959011, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0002, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.009663024917244911, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.232, | |
| "grad_norm": 0.009915046393871307, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.0089695630595088, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0002, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "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": 525137523027840.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |