| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9726027397260273, | |
| "eval_steps": 2, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0, | |
| "loss": 1.5513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.6200196743011475, | |
| "eval_runtime": 6.6812, | |
| "eval_samples_per_second": 37.418, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.6200196743011475, | |
| "eval_runtime": 6.6725, | |
| "eval_samples_per_second": 37.467, | |
| "eval_steps_per_second": 2.398, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4e-05, | |
| "loss": 1.559, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5558, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.618035078048706, | |
| "eval_runtime": 6.6887, | |
| "eval_samples_per_second": 37.377, | |
| "eval_steps_per_second": 2.392, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5365, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.6109036207199097, | |
| "eval_runtime": 6.677, | |
| "eval_samples_per_second": 37.442, | |
| "eval_steps_per_second": 2.396, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5266, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5358, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.592940092086792, | |
| "eval_runtime": 6.6867, | |
| "eval_samples_per_second": 37.388, | |
| "eval_steps_per_second": 2.393, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4989, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.573974609375, | |
| "eval_runtime": 6.6699, | |
| "eval_samples_per_second": 37.482, | |
| "eval_steps_per_second": 2.399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.502, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 1.4938, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.5591483116149902, | |
| "eval_runtime": 6.6798, | |
| "eval_samples_per_second": 37.427, | |
| "eval_steps_per_second": 2.395, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00018461538461538463, | |
| "loss": 1.5116, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017692307692307693, | |
| "loss": 1.4881, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.5495102405548096, | |
| "eval_runtime": 6.6802, | |
| "eval_samples_per_second": 37.424, | |
| "eval_steps_per_second": 2.395, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00016923076923076923, | |
| "loss": 1.5033, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016153846153846155, | |
| "loss": 1.4639, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.542672872543335, | |
| "eval_runtime": 6.6782, | |
| "eval_samples_per_second": 37.435, | |
| "eval_steps_per_second": 2.396, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.465, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00014615384615384615, | |
| "loss": 1.4824, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.537250280380249, | |
| "eval_runtime": 6.677, | |
| "eval_samples_per_second": 37.442, | |
| "eval_steps_per_second": 2.396, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00013846153846153847, | |
| "loss": 1.4542, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00013076923076923077, | |
| "loss": 1.4752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.5317878723144531, | |
| "eval_runtime": 6.6751, | |
| "eval_samples_per_second": 37.453, | |
| "eval_steps_per_second": 2.397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001230769230769231, | |
| "loss": 1.4691, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00011538461538461538, | |
| "loss": 1.4768, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 1.5277786254882812, | |
| "eval_runtime": 6.6794, | |
| "eval_samples_per_second": 37.428, | |
| "eval_steps_per_second": 2.395, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0001076923076923077, | |
| "loss": 1.4351, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4482, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.5236351490020752, | |
| "eval_runtime": 6.6752, | |
| "eval_samples_per_second": 37.452, | |
| "eval_steps_per_second": 2.397, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 1.4494, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 1.4444, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 1.5209420919418335, | |
| "eval_runtime": 6.6753, | |
| "eval_samples_per_second": 37.452, | |
| "eval_steps_per_second": 2.397, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.4342, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 1.4381, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 1.519213318824768, | |
| "eval_runtime": 6.6725, | |
| "eval_samples_per_second": 37.467, | |
| "eval_steps_per_second": 2.398, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 1.4617, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 1.4415, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.5165919065475464, | |
| "eval_runtime": 6.6901, | |
| "eval_samples_per_second": 37.369, | |
| "eval_steps_per_second": 2.392, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 1.4729, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.4412, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.5150251388549805, | |
| "eval_runtime": 6.6732, | |
| "eval_samples_per_second": 37.463, | |
| "eval_steps_per_second": 2.398, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 1.4786, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 1.4263, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 1.514638900756836, | |
| "eval_runtime": 6.6733, | |
| "eval_samples_per_second": 37.463, | |
| "eval_steps_per_second": 2.398, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.439, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 1.4608, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.5133925676345825, | |
| "eval_runtime": 6.6617, | |
| "eval_samples_per_second": 37.528, | |
| "eval_steps_per_second": 2.402, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 2.9392370233591726e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |