| { | |
| "best_metric": 0.445181667804718, | |
| "best_model_checkpoint": "mikhail-panzo/fil_b32_le4_s4000/checkpoint-500", | |
| "epoch": 11.11111111111111, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 1.5478250980377197, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.7933, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 2.5992791652679443, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7126, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 4.512153625488281, | |
| "learning_rate": 7.45e-06, | |
| "loss": 0.6643, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 5.529618740081787, | |
| "learning_rate": 9.950000000000001e-06, | |
| "loss": 0.6161, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 1.547269344329834, | |
| "learning_rate": 1.2450000000000001e-05, | |
| "loss": 0.5572, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 1.7310105562210083, | |
| "learning_rate": 1.4950000000000001e-05, | |
| "loss": 0.5307, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 4.040494441986084, | |
| "learning_rate": 1.745e-05, | |
| "loss": 0.5259, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 1.6819641590118408, | |
| "learning_rate": 1.995e-05, | |
| "loss": 0.4981, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 3.428649663925171, | |
| "learning_rate": 2.245e-05, | |
| "loss": 0.5008, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 2.2339069843292236, | |
| "learning_rate": 2.495e-05, | |
| "loss": 0.4923, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "eval_loss": 0.445181667804718, | |
| "eval_runtime": 8.1426, | |
| "eval_samples_per_second": 19.527, | |
| "eval_steps_per_second": 2.456, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 89, | |
| "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": 3444393383785728.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |