| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0009372071227742, | |
| "eval_steps": 67, | |
| "global_step": 267, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037488284910965324, | |
| "eval_loss": 2.361954689025879, | |
| "eval_runtime": 3.5902, | |
| "eval_samples_per_second": 125.342, | |
| "eval_steps_per_second": 15.877, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01874414245548266, | |
| "grad_norm": 0.11034798622131348, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.0049, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03748828491096532, | |
| "grad_norm": 0.24442698061466217, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.3, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.056232427366447985, | |
| "grad_norm": 0.1074686050415039, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2395, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07497656982193064, | |
| "grad_norm": 0.22002893686294556, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.1767, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09372071227741331, | |
| "grad_norm": 0.819185733795166, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.6519, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11246485473289597, | |
| "grad_norm": 0.14553327858448029, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0178, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13120899718837864, | |
| "grad_norm": 0.33844277262687683, | |
| "learning_rate": 9.989021978333995e-05, | |
| "loss": 2.1738, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14995313964386128, | |
| "grad_norm": 0.18579810857772827, | |
| "learning_rate": 9.956136120119858e-05, | |
| "loss": 2.1616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16869728209934395, | |
| "grad_norm": 0.2519240081310272, | |
| "learning_rate": 9.901486834023182e-05, | |
| "loss": 2.0246, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18744142455482662, | |
| "grad_norm": 0.8189491033554077, | |
| "learning_rate": 9.825314096462685e-05, | |
| "loss": 2.3638, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 0.2149842232465744, | |
| "learning_rate": 9.72795239782369e-05, | |
| "loss": 1.9553, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22492970946579194, | |
| "grad_norm": 0.3894648253917694, | |
| "learning_rate": 9.609829273641034e-05, | |
| "loss": 2.152, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2436738519212746, | |
| "grad_norm": 0.20155246555805206, | |
| "learning_rate": 9.47146342720133e-05, | |
| "loss": 2.1133, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2511715089034677, | |
| "eval_loss": 2.1045072078704834, | |
| "eval_runtime": 3.6115, | |
| "eval_samples_per_second": 124.601, | |
| "eval_steps_per_second": 15.783, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2624179943767573, | |
| "grad_norm": 0.2783915400505066, | |
| "learning_rate": 9.3134624518086e-05, | |
| "loss": 1.998, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28116213683223995, | |
| "grad_norm": 1.4236199855804443, | |
| "learning_rate": 9.136520162715287e-05, | |
| "loss": 2.3941, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29990627928772257, | |
| "grad_norm": 0.2663502097129822, | |
| "learning_rate": 8.94141355043471e-05, | |
| "loss": 1.8989, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31865042174320524, | |
| "grad_norm": 0.4793087840080261, | |
| "learning_rate": 8.728999368813591e-05, | |
| "loss": 2.1174, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3373945641986879, | |
| "grad_norm": 0.20656132698059082, | |
| "learning_rate": 8.500210372847127e-05, | |
| "loss": 2.0367, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3561387066541706, | |
| "grad_norm": 0.30166926980018616, | |
| "learning_rate": 8.256051222757188e-05, | |
| "loss": 1.9734, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.37488284910965325, | |
| "grad_norm": 1.0557372570037842, | |
| "learning_rate": 7.997594072319625e-05, | |
| "loss": 2.2227, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3936269915651359, | |
| "grad_norm": 0.2666870355606079, | |
| "learning_rate": 7.725973860813338e-05, | |
| "loss": 1.8634, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 0.47340846061706543, | |
| "learning_rate": 7.442383329265062e-05, | |
| "loss": 2.0263, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4311152764761012, | |
| "grad_norm": 0.23562197387218475, | |
| "learning_rate": 7.14806778287464e-05, | |
| "loss": 2.0062, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.4498594189315839, | |
| "grad_norm": 0.3509786128997803, | |
| "learning_rate": 6.844319622620039e-05, | |
| "loss": 1.9304, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.46860356138706655, | |
| "grad_norm": 1.2238250970840454, | |
| "learning_rate": 6.532472670054974e-05, | |
| "loss": 2.2562, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4873477038425492, | |
| "grad_norm": 0.2801048159599304, | |
| "learning_rate": 6.213896310220139e-05, | |
| "loss": 1.8556, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5023430178069354, | |
| "eval_loss": 2.027282953262329, | |
| "eval_runtime": 3.989, | |
| "eval_samples_per_second": 112.81, | |
| "eval_steps_per_second": 14.289, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5060918462980318, | |
| "grad_norm": 0.6263522505760193, | |
| "learning_rate": 5.889989478387753e-05, | |
| "loss": 2.0187, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5248359887535146, | |
| "grad_norm": 0.2488415390253067, | |
| "learning_rate": 5.5621745170448616e-05, | |
| "loss": 1.9467, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5435801312089972, | |
| "grad_norm": 0.3804314136505127, | |
| "learning_rate": 5.2318909300906926e-05, | |
| "loss": 2.0112, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5623242736644799, | |
| "grad_norm": 1.3460745811462402, | |
| "learning_rate": 4.900589061674649e-05, | |
| "loss": 2.1612, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5810684161199625, | |
| "grad_norm": 0.30925655364990234, | |
| "learning_rate": 4.569723727432517e-05, | |
| "loss": 1.7977, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5998125585754451, | |
| "grad_norm": 0.553766667842865, | |
| "learning_rate": 4.240747826087429e-05, | |
| "loss": 2.0045, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6185567010309279, | |
| "grad_norm": 0.26959770917892456, | |
| "learning_rate": 3.91510595946841e-05, | |
| "loss": 1.948, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6373008434864105, | |
| "grad_norm": 0.42600250244140625, | |
| "learning_rate": 3.5942280889623026e-05, | |
| "loss": 1.9507, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6560449859418932, | |
| "grad_norm": 1.3592358827590942, | |
| "learning_rate": 3.27952325625493e-05, | |
| "loss": 2.1947, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6747891283973758, | |
| "grad_norm": 0.3122025728225708, | |
| "learning_rate": 2.9723733959350307e-05, | |
| "loss": 1.772, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6935332708528584, | |
| "grad_norm": 0.6400068402290344, | |
| "learning_rate": 2.674127267131131e-05, | |
| "loss": 2.0385, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7122774133083412, | |
| "grad_norm": 0.2724437415599823, | |
| "learning_rate": 2.3860945308287552e-05, | |
| "loss": 1.9093, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7310215557638238, | |
| "grad_norm": 0.3942809998989105, | |
| "learning_rate": 2.1095399988757574e-05, | |
| "loss": 1.9067, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7497656982193065, | |
| "grad_norm": 1.2149404287338257, | |
| "learning_rate": 1.8456780799295886e-05, | |
| "loss": 2.1768, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.753514526710403, | |
| "eval_loss": 1.981666922569275, | |
| "eval_runtime": 3.475, | |
| "eval_samples_per_second": 129.496, | |
| "eval_steps_per_second": 16.403, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.7685098406747891, | |
| "grad_norm": 0.31344324350357056, | |
| "learning_rate": 1.5956674467354537e-05, | |
| "loss": 1.7979, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7872539831302718, | |
| "grad_norm": 0.6548614501953125, | |
| "learning_rate": 1.3606059481525296e-05, | |
| "loss": 1.9015, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8059981255857545, | |
| "grad_norm": 0.28455740213394165, | |
| "learning_rate": 1.1415257882705311e-05, | |
| "loss": 1.9196, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8247422680412371, | |
| "grad_norm": 0.42264482378959656, | |
| "learning_rate": 9.393889937861694e-06, | |
| "loss": 1.947, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8434864104967198, | |
| "grad_norm": 1.1509761810302734, | |
| "learning_rate": 7.550831895431798e-06, | |
| "loss": 2.0977, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8622305529522024, | |
| "grad_norm": 0.3231133818626404, | |
| "learning_rate": 5.894177007864271e-06, | |
| "loss": 1.8388, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8809746954076851, | |
| "grad_norm": 0.6163565516471863, | |
| "learning_rate": 4.4311999924586065e-06, | |
| "loss": 1.9681, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8997188378631678, | |
| "grad_norm": 0.27972695231437683, | |
| "learning_rate": 3.1683250865636114e-06, | |
| "loss": 1.9602, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9184629803186504, | |
| "grad_norm": 0.40869590640068054, | |
| "learning_rate": 2.1110978374106192e-06, | |
| "loss": 1.893, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9372071227741331, | |
| "grad_norm": 1.1225160360336304, | |
| "learning_rate": 1.2641607504584928e-06, | |
| "loss": 2.0743, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9559512652296157, | |
| "grad_norm": 0.32928183674812317, | |
| "learning_rate": 6.312329031833319e-07, | |
| "loss": 1.8119, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9746954076850984, | |
| "grad_norm": 0.6379702091217041, | |
| "learning_rate": 2.1509361383330596e-07, | |
| "loss": 1.9946, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.993439550140581, | |
| "grad_norm": 0.35420289635658264, | |
| "learning_rate": 1.7570236862241017e-08, | |
| "loss": 2.0124, | |
| "step": 265 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 267, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 8.53863352458281e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |