| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05263157894736842, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "eval_loss": 8.839006423950195, | |
| "eval_runtime": 1.5444, | |
| "eval_samples_per_second": 155.404, | |
| "eval_steps_per_second": 77.702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 1142.3505859375, | |
| "learning_rate": 4e-05, | |
| "loss": 37.9208, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "eval_loss": 8.935256004333496, | |
| "eval_runtime": 1.1351, | |
| "eval_samples_per_second": 211.443, | |
| "eval_steps_per_second": 105.722, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 1164.268798828125, | |
| "learning_rate": 8e-05, | |
| "loss": 33.5556, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "grad_norm": 1055.901611328125, | |
| "learning_rate": 0.00012, | |
| "loss": 35.241, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "eval_loss": 8.801165580749512, | |
| "eval_runtime": 1.1417, | |
| "eval_samples_per_second": 210.215, | |
| "eval_steps_per_second": 105.108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 1153.5133056640625, | |
| "learning_rate": 0.00016, | |
| "loss": 37.0329, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 1203.20703125, | |
| "learning_rate": 0.0002, | |
| "loss": 33.4644, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "eval_loss": 8.627506256103516, | |
| "eval_runtime": 1.1351, | |
| "eval_samples_per_second": 211.427, | |
| "eval_steps_per_second": 105.714, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "grad_norm": 1122.0399169921875, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 33.7543, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "eval_loss": 8.328618049621582, | |
| "eval_runtime": 1.1598, | |
| "eval_samples_per_second": 206.938, | |
| "eval_steps_per_second": 103.469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03684210526315789, | |
| "grad_norm": 1370.0748291015625, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 36.3826, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 1278.0841064453125, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 34.4785, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "eval_loss": 8.307162284851074, | |
| "eval_runtime": 1.1606, | |
| "eval_samples_per_second": 206.792, | |
| "eval_steps_per_second": 103.396, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04736842105263158, | |
| "grad_norm": 1448.9915771484375, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 34.2346, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 1308.057373046875, | |
| "learning_rate": 0.0, | |
| "loss": 30.9553, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "eval_loss": 8.286457061767578, | |
| "eval_runtime": 1.1563, | |
| "eval_samples_per_second": 207.558, | |
| "eval_steps_per_second": 103.779, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 70939739947008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |