| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1005, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 3.2636772208309153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 4.198083473691167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7201, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 0.976830869365462, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7097, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 1.0243806020799167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 1.0277760094413817, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6709, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.8438731934295206, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6661, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 0.7599111846557922, | |
| "learning_rate": 5e-06, | |
| "loss": 0.661, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.6979506430052831, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6481, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 0.6344985723138951, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6494, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.9496025763872573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 0.5640696000070055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6292, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.6244500377098101, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6246, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 0.705148467511176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6288, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.5782292155064868, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6208, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.47879907688098855, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6307, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.641221897829538, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6282, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5074626865671642, | |
| "grad_norm": 0.5790307980225682, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6263, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.5896556501658362, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6171, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5671641791044776, | |
| "grad_norm": 0.6678853160055497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6217, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.4932224279411186, | |
| "learning_rate": 5e-06, | |
| "loss": 0.612, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6268656716417911, | |
| "grad_norm": 0.59016513490961, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6207, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 0.6628507303786519, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6205, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6865671641791045, | |
| "grad_norm": 0.5728090788820762, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6198, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.5909920699712947, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6195, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.5403630353274208, | |
| "learning_rate": 5e-06, | |
| "loss": 0.616, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 0.4389359227878181, | |
| "learning_rate": 5e-06, | |
| "loss": 0.615, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8059701492537313, | |
| "grad_norm": 0.5071059932681349, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6119, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 0.5232710694651, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6052, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8656716417910447, | |
| "grad_norm": 0.6304632419292111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6107, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.4513885510016045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6029, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9253731343283582, | |
| "grad_norm": 0.46627673450975804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6224, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.4541172691354782, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6005, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9850746268656716, | |
| "grad_norm": 0.5886900494680195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6102, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6099968552589417, | |
| "eval_runtime": 181.0403, | |
| "eval_samples_per_second": 49.84, | |
| "eval_steps_per_second": 0.392, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.0149253731343284, | |
| "grad_norm": 0.7366116445067696, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5859, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.044776119402985, | |
| "grad_norm": 0.571210239937034, | |
| "learning_rate": 5e-06, | |
| "loss": 0.56, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 0.4668816015405423, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5592, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1044776119402986, | |
| "grad_norm": 0.5628631007519552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5657, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.1343283582089552, | |
| "grad_norm": 0.5929997737908812, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5563, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.164179104477612, | |
| "grad_norm": 0.5658505485409301, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5578, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.7526049702677613, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5615, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2238805970149254, | |
| "grad_norm": 0.5393989822533652, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5673, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2537313432835822, | |
| "grad_norm": 0.5325263654739846, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2835820895522387, | |
| "grad_norm": 0.5064885711552297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5607, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 0.5684568858118794, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5576, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3432835820895521, | |
| "grad_norm": 0.5283953048651826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5561, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.373134328358209, | |
| "grad_norm": 0.46950929831714766, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5602, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.4029850746268657, | |
| "grad_norm": 0.5385565397537747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5581, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 0.5659871694460666, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5617, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.462686567164179, | |
| "grad_norm": 0.546965476854921, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5553, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 0.497538374377084, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5602, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5223880597014925, | |
| "grad_norm": 0.5312343228790736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5618, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 0.5166406423583252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5591, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.582089552238806, | |
| "grad_norm": 0.5255413189150826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5604, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6119402985074627, | |
| "grad_norm": 0.49551565255287583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5618, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6417910447761193, | |
| "grad_norm": 0.49267014615726396, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5585, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 0.5643970187910693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5652, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.7014925373134329, | |
| "grad_norm": 0.5037470018499742, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5625, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7313432835820897, | |
| "grad_norm": 0.48141660593931324, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5568, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.7611940298507462, | |
| "grad_norm": 0.5300295332006951, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5597, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.5373472168427755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5562, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8208955223880596, | |
| "grad_norm": 0.5707503080671126, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5527, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.8507462686567164, | |
| "grad_norm": 0.5730054222686448, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5665, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8805970149253732, | |
| "grad_norm": 0.5072679291608492, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5513, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.5178695559305173, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5583, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9402985074626866, | |
| "grad_norm": 0.5656735937545936, | |
| "learning_rate": 5e-06, | |
| "loss": 0.563, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.9701492537313432, | |
| "grad_norm": 0.4863140367653273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5595, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5328164667475485, | |
| "learning_rate": 5e-06, | |
| "loss": 0.553, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6020517349243164, | |
| "eval_runtime": 181.5231, | |
| "eval_samples_per_second": 49.707, | |
| "eval_steps_per_second": 0.391, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.029850746268657, | |
| "grad_norm": 0.6224628520404539, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5057, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.0597014925373136, | |
| "grad_norm": 0.5148413250898433, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5083, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.08955223880597, | |
| "grad_norm": 0.5438872711269419, | |
| "learning_rate": 5e-06, | |
| "loss": 0.504, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1194029850746268, | |
| "grad_norm": 0.7136622301499072, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5084, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.1492537313432836, | |
| "grad_norm": 0.565521915151828, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5141, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.1791044776119404, | |
| "grad_norm": 0.5319158435460484, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5107, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.208955223880597, | |
| "grad_norm": 0.5565738587496012, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5096, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.2388059701492535, | |
| "grad_norm": 0.4910069126256564, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5154, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.2686567164179103, | |
| "grad_norm": 0.48169824804919137, | |
| "learning_rate": 5e-06, | |
| "loss": 0.515, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.298507462686567, | |
| "grad_norm": 0.5716888321310263, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5059, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.328358208955224, | |
| "grad_norm": 0.5310388379236972, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5065, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.3582089552238807, | |
| "grad_norm": 0.5340384268973276, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5097, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 0.5612588485250506, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5092, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.417910447761194, | |
| "grad_norm": 0.5517492107037403, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5155, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.4477611940298507, | |
| "grad_norm": 0.5868418861130762, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5099, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4776119402985075, | |
| "grad_norm": 0.5335016774082386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4953, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.5074626865671643, | |
| "grad_norm": 0.47262015142721125, | |
| "learning_rate": 5e-06, | |
| "loss": 0.508, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.5373134328358207, | |
| "grad_norm": 0.4852270938780388, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5125, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.5671641791044775, | |
| "grad_norm": 0.5802563395388763, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5095, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.5970149253731343, | |
| "grad_norm": 0.503360426921311, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5189, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.626865671641791, | |
| "grad_norm": 0.49515721551631564, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5158, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.656716417910448, | |
| "grad_norm": 0.48219119082060224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.509, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.6865671641791042, | |
| "grad_norm": 0.4921666373084123, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5099, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.716417910447761, | |
| "grad_norm": 0.547644485149717, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5056, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.746268656716418, | |
| "grad_norm": 0.5561203783171008, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5105, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.7761194029850746, | |
| "grad_norm": 0.5027190076200428, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5101, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.8059701492537314, | |
| "grad_norm": 0.5325189560701381, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5126, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.835820895522388, | |
| "grad_norm": 0.6188498248886457, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5125, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.8656716417910446, | |
| "grad_norm": 0.5315894494034671, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5101, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.8955223880597014, | |
| "grad_norm": 0.5715252097778681, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5138, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.925373134328358, | |
| "grad_norm": 0.4780679784022612, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5108, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.955223880597015, | |
| "grad_norm": 0.48072163191940603, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5103, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "grad_norm": 0.5364386007246811, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5156, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6066075563430786, | |
| "eval_runtime": 181.24, | |
| "eval_samples_per_second": 49.785, | |
| "eval_steps_per_second": 0.392, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1005, | |
| "total_flos": 1682993672355840.0, | |
| "train_loss": 0.5693152133505143, | |
| "train_runtime": 30325.6118, | |
| "train_samples_per_second": 16.959, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1005, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1682993672355840.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |