| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9591836734693877, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0326530612244898, | |
| "grad_norm": 0.3159657120704651, | |
| "learning_rate": 4.9985361990992455e-05, | |
| "loss": 0.1654, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653061224489796, | |
| "grad_norm": 0.32706642150878906, | |
| "learning_rate": 4.9941465105674435e-05, | |
| "loss": 0.1369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09795918367346938, | |
| "grad_norm": 0.33407843112945557, | |
| "learning_rate": 4.986836074908616e-05, | |
| "loss": 0.1259, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1306122448979592, | |
| "grad_norm": 0.3189881443977356, | |
| "learning_rate": 4.976613452940604e-05, | |
| "loss": 0.1041, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.3424989581108093, | |
| "learning_rate": 4.9634906157700036e-05, | |
| "loss": 0.1004, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19591836734693877, | |
| "grad_norm": 0.3253389298915863, | |
| "learning_rate": 4.9474829307735115e-05, | |
| "loss": 0.0941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.26078635454177856, | |
| "learning_rate": 4.9286091436021015e-05, | |
| "loss": 0.0867, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2612244897959184, | |
| "grad_norm": 0.252139687538147, | |
| "learning_rate": 4.906891356229103e-05, | |
| "loss": 0.0853, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2938775510204082, | |
| "grad_norm": 0.3403972387313843, | |
| "learning_rate": 4.882355001067892e-05, | |
| "loss": 0.0863, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.4710679352283478, | |
| "learning_rate": 4.855028811189496e-05, | |
| "loss": 0.0874, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35918367346938773, | |
| "grad_norm": 0.3147217929363251, | |
| "learning_rate": 4.8249447866750025e-05, | |
| "loss": 0.0733, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.39183673469387753, | |
| "grad_norm": 0.3265310823917389, | |
| "learning_rate": 4.792138157142158e-05, | |
| "loss": 0.0719, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42448979591836733, | |
| "grad_norm": 0.35432252287864685, | |
| "learning_rate": 4.75664734049005e-05, | |
| "loss": 0.0824, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.3701626658439636, | |
| "learning_rate": 4.7185138979101864e-05, | |
| "loss": 0.0731, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.35868266224861145, | |
| "learning_rate": 4.677782485216644e-05, | |
| "loss": 0.0725, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5224489795918368, | |
| "grad_norm": 0.32440632581710815, | |
| "learning_rate": 4.6345008005522966e-05, | |
| "loss": 0.0694, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5551020408163265, | |
| "grad_norm": 0.3003002405166626, | |
| "learning_rate": 4.588719528532342e-05, | |
| "loss": 0.072, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5877551020408164, | |
| "grad_norm": 0.34989920258522034, | |
| "learning_rate": 4.540492280890555e-05, | |
| "loss": 0.0646, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6204081632653061, | |
| "grad_norm": 0.473254919052124, | |
| "learning_rate": 4.4898755336977673e-05, | |
| "loss": 0.0732, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.30768489837646484, | |
| "learning_rate": 4.436928561226087e-05, | |
| "loss": 0.068, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.31777673959732056, | |
| "learning_rate": 4.381713366536311e-05, | |
| "loss": 0.0749, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7183673469387755, | |
| "grad_norm": 0.40202295780181885, | |
| "learning_rate": 4.324294608869817e-05, | |
| "loss": 0.0652, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7510204081632653, | |
| "grad_norm": 0.4353463053703308, | |
| "learning_rate": 4.264739527929959e-05, | |
| "loss": 0.0562, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7836734693877551, | |
| "grad_norm": 0.4079282879829407, | |
| "learning_rate": 4.203117865141635e-05, | |
| "loss": 0.0602, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.40490931272506714, | |
| "learning_rate": 4.1395017819812445e-05, | |
| "loss": 0.0639, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8489795918367347, | |
| "grad_norm": 0.423981636762619, | |
| "learning_rate": 4.07396577547265e-05, | |
| "loss": 0.0651, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8816326530612245, | |
| "grad_norm": 0.3315489590167999, | |
| "learning_rate": 4.0065865909481417e-05, | |
| "loss": 0.0676, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.560667097568512, | |
| "learning_rate": 3.937443132176517e-05, | |
| "loss": 0.0669, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9469387755102041, | |
| "grad_norm": 0.4202517569065094, | |
| "learning_rate": 3.8666163689635616e-05, | |
| "loss": 0.0631, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.4563729465007782, | |
| "learning_rate": 3.794189242333106e-05, | |
| "loss": 0.0649, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0122448979591836, | |
| "grad_norm": 0.3522864580154419, | |
| "learning_rate": 3.720246567399712e-05, | |
| "loss": 0.059, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.0448979591836736, | |
| "grad_norm": 0.38459908962249756, | |
| "learning_rate": 3.644874934046716e-05, | |
| "loss": 0.062, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0775510204081633, | |
| "grad_norm": 0.37406954169273376, | |
| "learning_rate": 3.568162605525953e-05, | |
| "loss": 0.0565, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.110204081632653, | |
| "grad_norm": 0.3395706117153168, | |
| "learning_rate": 3.490199415097892e-05, | |
| "loss": 0.0575, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.31273558735847473, | |
| "learning_rate": 3.4110766608332347e-05, | |
| "loss": 0.0589, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.1755102040816325, | |
| "grad_norm": 0.44675061106681824, | |
| "learning_rate": 3.330886998699149e-05, | |
| "loss": 0.0611, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2081632653061225, | |
| "grad_norm": 0.34769827127456665, | |
| "learning_rate": 3.249724334055367e-05, | |
| "loss": 0.062, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.2408163265306122, | |
| "grad_norm": 0.31832146644592285, | |
| "learning_rate": 3.167683711687179e-05, | |
| "loss": 0.0616, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.273469387755102, | |
| "grad_norm": 0.4153653085231781, | |
| "learning_rate": 3.084861204504122e-05, | |
| "loss": 0.0586, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "grad_norm": 0.36249643564224243, | |
| "learning_rate": 3.001353801034688e-05, | |
| "loss": 0.0578, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3387755102040817, | |
| "grad_norm": 0.43447113037109375, | |
| "learning_rate": 2.917259291848814e-05, | |
| "loss": 0.0547, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 0.3350294530391693, | |
| "learning_rate": 2.8326761550411345e-05, | |
| "loss": 0.0581, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4040816326530612, | |
| "grad_norm": 0.34255513548851013, | |
| "learning_rate": 2.747703440909128e-05, | |
| "loss": 0.0535, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.436734693877551, | |
| "grad_norm": 0.6323994398117065, | |
| "learning_rate": 2.662440655961183e-05, | |
| "loss": 0.0666, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 0.3421262502670288, | |
| "learning_rate": 2.5769876463904265e-05, | |
| "loss": 0.053, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.5020408163265306, | |
| "grad_norm": 0.4133753478527069, | |
| "learning_rate": 2.491444481150763e-05, | |
| "loss": 0.0602, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.5346938775510204, | |
| "grad_norm": 0.37677302956581116, | |
| "learning_rate": 2.4059113347720574e-05, | |
| "loss": 0.0573, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.5673469387755103, | |
| "grad_norm": 0.3683429956436157, | |
| "learning_rate": 2.3204883700516812e-05, | |
| "loss": 0.0544, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.34340280294418335, | |
| "learning_rate": 2.235275620759797e-05, | |
| "loss": 0.0552, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 0.39541885256767273, | |
| "learning_rate": 2.150372874495739e-05, | |
| "loss": 0.0543, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.6653061224489796, | |
| "grad_norm": 0.384330689907074, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0481, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.6979591836734693, | |
| "grad_norm": 0.4634612798690796, | |
| "learning_rate": 1.9818946098873766e-05, | |
| "loss": 0.052, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.730612244897959, | |
| "grad_norm": 0.4186592400074005, | |
| "learning_rate": 1.8985163864514645e-05, | |
| "loss": 0.0516, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.763265306122449, | |
| "grad_norm": 0.4726428985595703, | |
| "learning_rate": 1.815842524819793e-05, | |
| "loss": 0.0559, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 0.38660183548927307, | |
| "learning_rate": 1.733969839450863e-05, | |
| "loss": 0.0554, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 0.40636590123176575, | |
| "learning_rate": 1.6529942065931477e-05, | |
| "loss": 0.0576, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.8612244897959185, | |
| "grad_norm": 0.3667762875556946, | |
| "learning_rate": 1.5730104520100982e-05, | |
| "loss": 0.0546, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.8938775510204082, | |
| "grad_norm": 0.38867512345314026, | |
| "learning_rate": 1.4941122399353185e-05, | |
| "loss": 0.0539, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.926530612244898, | |
| "grad_norm": 0.37944862246513367, | |
| "learning_rate": 1.4163919633879324e-05, | |
| "loss": 0.0537, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": 0.394191175699234, | |
| "learning_rate": 1.339940635976592e-05, | |
| "loss": 0.0493, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 459, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.8642398036380877e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |