| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 96, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.7624, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.7445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6133, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001999429490929718, | |
| "loss": 1.4396, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019977186146800707, | |
| "loss": 1.3901, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019948693233918952, | |
| "loss": 1.2958, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019908848681582391, | |
| "loss": 1.2847, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00019857697953148037, | |
| "loss": 1.2663, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019795299412524945, | |
| "loss": 1.2352, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00019721724257579907, | |
| "loss": 1.1587, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001963705643889941, | |
| "loss": 1.2138, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00019541392564000488, | |
| "loss": 1.23, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00019434841787099803, | |
| "loss": 1.1817, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019317525684566685, | |
| "loss": 1.1665, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019189578116202307, | |
| "loss": 1.1024, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00019051145072503215, | |
| "loss": 1.1704, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018902384508083517, | |
| "loss": 1.152, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018743466161445823, | |
| "loss": 1.1639, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001857457136130651, | |
| "loss": 1.1508, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00018395892819696389, | |
| "loss": 1.1354, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018207634412072764, | |
| "loss": 1.1064, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00018010010944693848, | |
| "loss": 1.0968, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001780324790952092, | |
| "loss": 1.1544, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001758758122692791, | |
| "loss": 1.1565, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00017363256976511972, | |
| "loss": 1.1355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00017130531116312203, | |
| "loss": 1.0741, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00016889669190756868, | |
| "loss": 1.0659, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00016640946027672392, | |
| "loss": 1.1374, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00016384645424699835, | |
| "loss": 1.0859, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0001612105982547663, | |
| "loss": 1.1541, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00015850489985953076, | |
| "loss": 1.1597, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00015573244631224365, | |
| "loss": 1.0453, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00015289640103269625, | |
| "loss": 0.9627, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.9099, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001470465480602756, | |
| "loss": 0.888, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00014403941515576344, | |
| "loss": 0.8781, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00014098203247965875, | |
| "loss": 0.9653, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0001378778885610576, | |
| "loss": 0.8979, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013473052528448201, | |
| "loss": 0.8671, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00013154353384852558, | |
| "loss": 0.8808, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00012832055066823038, | |
| "loss": 0.8294, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00012506525322587207, | |
| "loss": 0.84, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00012178135587488515, | |
| "loss": 0.8632, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00011847260560171896, | |
| "loss": 0.8516, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00011514277775045768, | |
| "loss": 0.909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00011179567171508463, | |
| "loss": 0.8472, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00010843510660430447, | |
| "loss": 0.8445, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00010506491688387127, | |
| "loss": 0.8845, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001016889480013931, | |
| "loss": 0.8327, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.83110519986069e-05, | |
| "loss": 0.8393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 9.493508311612874e-05, | |
| "loss": 0.8007, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.156489339569554e-05, | |
| "loss": 0.851, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.820432828491542e-05, | |
| "loss": 0.8675, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.485722224954237e-05, | |
| "loss": 0.8945, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.15273943982811e-05, | |
| "loss": 0.8403, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.821864412511485e-05, | |
| "loss": 0.8358, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.493474677412794e-05, | |
| "loss": 0.8272, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.16794493317696e-05, | |
| "loss": 0.8653, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 6.845646615147445e-05, | |
| "loss": 0.8555, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.526947471551798e-05, | |
| "loss": 0.8192, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 6.21221114389424e-05, | |
| "loss": 0.8457, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 5.901796752034128e-05, | |
| "loss": 0.828, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 5.596058484423656e-05, | |
| "loss": 0.8286, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.2953451939724454e-05, | |
| "loss": 0.7675, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.6688, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.710359896730379e-05, | |
| "loss": 0.688, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.426755368775637e-05, | |
| "loss": 0.665, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.149510014046922e-05, | |
| "loss": 0.6602, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.878940174523371e-05, | |
| "loss": 0.6179, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.615354575300166e-05, | |
| "loss": 0.6359, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.3590539723276083e-05, | |
| "loss": 0.6773, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.110330809243134e-05, | |
| "loss": 0.6421, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.869468883687798e-05, | |
| "loss": 0.6696, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.6367430234880284e-05, | |
| "loss": 0.6332, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.4124187730720917e-05, | |
| "loss": 0.6248, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.1967520904790827e-05, | |
| "loss": 0.6258, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.9899890553061562e-05, | |
| "loss": 0.6268, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.7923655879272393e-05, | |
| "loss": 0.6333, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.60410718030361e-05, | |
| "loss": 0.6232, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.425428638693489e-05, | |
| "loss": 0.6494, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.2565338385541792e-05, | |
| "loss": 0.6526, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.097615491916485e-05, | |
| "loss": 0.6501, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.488549274967872e-06, | |
| "loss": 0.6078, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 8.10421883797694e-06, | |
| "loss": 0.6533, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.824743154333157e-06, | |
| "loss": 0.6292, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.651582129001986e-06, | |
| "loss": 0.6171, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.586074359995119e-06, | |
| "loss": 0.6558, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.6294356110059157e-06, | |
| "loss": 0.6371, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.7827574242009437e-06, | |
| "loss": 0.6505, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 2.0470058747505516e-06, | |
| "loss": 0.6245, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.4230204685196203e-06, | |
| "loss": 0.6499, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.11513184176116e-07, | |
| "loss": 0.6184, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.130676608104845e-07, | |
| "loss": 0.6412, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.2813853199292746e-07, | |
| "loss": 0.5949, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.705090702819993e-08, | |
| "loss": 0.6098, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.5524, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 96, | |
| "total_flos": 6492865167360.0, | |
| "train_loss": 0.9076403665045897, | |
| "train_runtime": 1258.3354, | |
| "train_samples_per_second": 4.768, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 96, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50000, | |
| "total_flos": 6492865167360.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |