| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20110608345902464, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008044243338360985, | |
| "grad_norm": 605.9085693359375, | |
| "learning_rate": 5e-05, | |
| "loss": 119.0301, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008044243338360985, | |
| "eval_loss": 3.8809421062469482, | |
| "eval_runtime": 4.7235, | |
| "eval_samples_per_second": 10.585, | |
| "eval_steps_per_second": 2.752, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01608848667672197, | |
| "grad_norm": 728.4609375, | |
| "learning_rate": 0.0001, | |
| "loss": 118.4882, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024132730015082957, | |
| "grad_norm": 343.075439453125, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 84.1627, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03217697335344394, | |
| "grad_norm": 267.0028991699219, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 60.8765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04022121669180493, | |
| "grad_norm": 227.43841552734375, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 54.7165, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.048265460030165915, | |
| "grad_norm": 141.04962158203125, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 53.5168, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0563097033685269, | |
| "grad_norm": 136.1522979736328, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 46.229, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06435394670688788, | |
| "grad_norm": 103.41104888916016, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 44.856, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 122.4833984375, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 41.9286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08044243338360986, | |
| "grad_norm": 129.08062744140625, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 40.5141, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08848667672197084, | |
| "grad_norm": 131.1678924560547, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 38.5526, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09653092006033183, | |
| "grad_norm": 99.09686279296875, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 41.0654, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 126.01998901367188, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 41.6152, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1126194067370538, | |
| "grad_norm": 141.1000213623047, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 43.2946, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12066365007541478, | |
| "grad_norm": 128.52944946289062, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 43.2944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12870789341377575, | |
| "grad_norm": 164.30210876464844, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 42.1249, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 121.94607543945312, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 44.5202, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 145.65963745117188, | |
| "learning_rate": 7.75e-05, | |
| "loss": 40.5531, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15284062342885874, | |
| "grad_norm": 126.6897964477539, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 41.6405, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16088486676721972, | |
| "grad_norm": 120.6353530883789, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 39.9783, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1689291101055807, | |
| "grad_norm": 147.1504669189453, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 38.0907, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1769733534439417, | |
| "grad_norm": 144.5216064453125, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 45.91, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18501759678230267, | |
| "grad_norm": 177.2615966796875, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 40.3139, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19306184012066366, | |
| "grad_norm": 115.59685516357422, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 38.696, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "grad_norm": 101.69725036621094, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 34.7107, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "eval_loss": 1.1880208253860474, | |
| "eval_runtime": 4.7474, | |
| "eval_samples_per_second": 10.532, | |
| "eval_steps_per_second": 2.738, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.829010669142016e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |