|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 490, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04081632653061224, |
|
"grad_norm": 20286.314453125, |
|
"learning_rate": 1.2244897959183673e-06, |
|
"loss": 2.0797, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.08163265306122448, |
|
"grad_norm": 21226.833984375, |
|
"learning_rate": 2.4489795918367347e-06, |
|
"loss": 2.0794, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12244897959183673, |
|
"grad_norm": 20473.34375, |
|
"learning_rate": 3.673469387755102e-06, |
|
"loss": 2.0791, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.16326530612244897, |
|
"grad_norm": 21295.623046875, |
|
"learning_rate": 4.897959183673469e-06, |
|
"loss": 2.0786, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.20408163265306123, |
|
"grad_norm": 22374.26953125, |
|
"learning_rate": 6.122448979591837e-06, |
|
"loss": 2.0775, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.24489795918367346, |
|
"grad_norm": 27922.837890625, |
|
"learning_rate": 7.346938775510204e-06, |
|
"loss": 2.0762, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.2857142857142857, |
|
"grad_norm": 21962.65625, |
|
"learning_rate": 8.571428571428571e-06, |
|
"loss": 2.0751, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.32653061224489793, |
|
"grad_norm": 25949.669921875, |
|
"learning_rate": 9.795918367346939e-06, |
|
"loss": 2.073, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.3673469387755102, |
|
"grad_norm": 21337.779296875, |
|
"learning_rate": 1.1020408163265306e-05, |
|
"loss": 2.0711, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.40816326530612246, |
|
"grad_norm": 21139.53125, |
|
"learning_rate": 1.2244897959183674e-05, |
|
"loss": 2.068, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.4489795918367347, |
|
"grad_norm": 18687.326171875, |
|
"learning_rate": 1.3469387755102042e-05, |
|
"loss": 2.0621, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.4897959183673469, |
|
"grad_norm": 23997.892578125, |
|
"learning_rate": 1.4693877551020408e-05, |
|
"loss": 2.0557, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.5306122448979592, |
|
"grad_norm": 25094.125, |
|
"learning_rate": 1.5918367346938776e-05, |
|
"loss": 2.0436, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.5714285714285714, |
|
"grad_norm": 35127.62890625, |
|
"learning_rate": 1.7142857142857142e-05, |
|
"loss": 2.0313, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.6122448979591837, |
|
"grad_norm": 38480.73046875, |
|
"learning_rate": 1.836734693877551e-05, |
|
"loss": 2.0124, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.6530612244897959, |
|
"grad_norm": 37025.25390625, |
|
"learning_rate": 1.9591836734693877e-05, |
|
"loss": 1.9832, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.6938775510204082, |
|
"grad_norm": 47326.75390625, |
|
"learning_rate": 2.0816326530612247e-05, |
|
"loss": 1.9503, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.7346938775510204, |
|
"grad_norm": 44386.79296875, |
|
"learning_rate": 2.2040816326530613e-05, |
|
"loss": 1.9033, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.7755102040816326, |
|
"grad_norm": 60427.28515625, |
|
"learning_rate": 2.326530612244898e-05, |
|
"loss": 1.8548, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.8163265306122449, |
|
"grad_norm": 60310.234375, |
|
"learning_rate": 2.448979591836735e-05, |
|
"loss": 1.7809, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.8571428571428571, |
|
"grad_norm": 73581.171875, |
|
"learning_rate": 2.5714285714285714e-05, |
|
"loss": 1.8435, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.8979591836734694, |
|
"grad_norm": 63305.5, |
|
"learning_rate": 2.6938775510204084e-05, |
|
"loss": 1.7222, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.9387755102040817, |
|
"grad_norm": 78695.546875, |
|
"learning_rate": 2.816326530612245e-05, |
|
"loss": 1.7823, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.9795918367346939, |
|
"grad_norm": 118529.84375, |
|
"learning_rate": 2.9387755102040816e-05, |
|
"loss": 1.7203, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.0204081632653061, |
|
"grad_norm": 39453.51953125, |
|
"learning_rate": 2.9931972789115647e-05, |
|
"loss": 1.7304, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.0612244897959184, |
|
"grad_norm": 58271.04296875, |
|
"learning_rate": 2.979591836734694e-05, |
|
"loss": 1.6894, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.1020408163265305, |
|
"grad_norm": 66804.171875, |
|
"learning_rate": 2.9659863945578233e-05, |
|
"loss": 1.7216, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.1428571428571428, |
|
"grad_norm": 85323.1328125, |
|
"learning_rate": 2.9523809523809523e-05, |
|
"loss": 1.6702, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.183673469387755, |
|
"grad_norm": 56704.1484375, |
|
"learning_rate": 2.9387755102040816e-05, |
|
"loss": 1.7761, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.2244897959183674, |
|
"grad_norm": 26519.884765625, |
|
"learning_rate": 2.925170068027211e-05, |
|
"loss": 1.7161, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.2653061224489797, |
|
"grad_norm": 30323.771484375, |
|
"learning_rate": 2.9115646258503402e-05, |
|
"loss": 1.7138, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.306122448979592, |
|
"grad_norm": 88774.5234375, |
|
"learning_rate": 2.8979591836734695e-05, |
|
"loss": 1.7125, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.346938775510204, |
|
"grad_norm": 81892.703125, |
|
"learning_rate": 2.8843537414965988e-05, |
|
"loss": 1.7273, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.3877551020408163, |
|
"grad_norm": 35876.6171875, |
|
"learning_rate": 2.870748299319728e-05, |
|
"loss": 1.7185, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.4285714285714286, |
|
"grad_norm": 91867.0390625, |
|
"learning_rate": 2.857142857142857e-05, |
|
"loss": 1.7057, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.469387755102041, |
|
"grad_norm": 47658.41796875, |
|
"learning_rate": 2.8435374149659864e-05, |
|
"loss": 1.7744, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.510204081632653, |
|
"grad_norm": 105770.484375, |
|
"learning_rate": 2.8299319727891157e-05, |
|
"loss": 1.6898, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.5510204081632653, |
|
"grad_norm": 104692.265625, |
|
"learning_rate": 2.816326530612245e-05, |
|
"loss": 1.7351, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.5918367346938775, |
|
"grad_norm": 45664.515625, |
|
"learning_rate": 2.802721088435374e-05, |
|
"loss": 1.6806, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.6326530612244898, |
|
"grad_norm": 45678.98828125, |
|
"learning_rate": 2.7891156462585036e-05, |
|
"loss": 1.7555, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.6734693877551021, |
|
"grad_norm": 108897.0078125, |
|
"learning_rate": 2.775510204081633e-05, |
|
"loss": 1.6663, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.7142857142857144, |
|
"grad_norm": 46971.11328125, |
|
"learning_rate": 2.761904761904762e-05, |
|
"loss": 1.7053, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.7551020408163265, |
|
"grad_norm": 69147.1171875, |
|
"learning_rate": 2.7482993197278912e-05, |
|
"loss": 1.7412, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.7959183673469388, |
|
"grad_norm": 89437.34375, |
|
"learning_rate": 2.7346938775510205e-05, |
|
"loss": 1.7245, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.836734693877551, |
|
"grad_norm": 40401.5625, |
|
"learning_rate": 2.7210884353741498e-05, |
|
"loss": 1.7614, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.8775510204081631, |
|
"grad_norm": 53271.234375, |
|
"learning_rate": 2.7074829931972787e-05, |
|
"loss": 1.7179, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.9183673469387754, |
|
"grad_norm": 69800.3203125, |
|
"learning_rate": 2.6938775510204084e-05, |
|
"loss": 1.7467, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.9591836734693877, |
|
"grad_norm": 86541.828125, |
|
"learning_rate": 2.6802721088435377e-05, |
|
"loss": 1.6975, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 100622.125, |
|
"learning_rate": 2.6666666666666667e-05, |
|
"loss": 1.6769, |
|
"step": 490 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 2450, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"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": 6.48602219925504e+18, |
|
"train_batch_size": 48, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|