| { | |
| "best_metric": 0.18780523538589478, | |
| "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-2650", | |
| "epoch": 1.751995879474633, | |
| "eval_steps": 50, | |
| "global_step": 3401, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025753283543651817, | |
| "grad_norm": 21.379672872549193, | |
| "learning_rate": 2.564102564102564e-06, | |
| "loss": 3.0388, | |
| "num_input_tokens_seen": 58496, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0051506567087303634, | |
| "grad_norm": 20.76117223991023, | |
| "learning_rate": 5.128205128205128e-06, | |
| "loss": 2.9831, | |
| "num_input_tokens_seen": 116960, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007725985063095545, | |
| "grad_norm": 22.5213517141881, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 2.8696, | |
| "num_input_tokens_seen": 175448, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010301313417460727, | |
| "grad_norm": 20.673071198727328, | |
| "learning_rate": 1.0256410256410256e-05, | |
| "loss": 2.6316, | |
| "num_input_tokens_seen": 233944, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012876641771825908, | |
| "grad_norm": 18.902291974538457, | |
| "learning_rate": 1.282051282051282e-05, | |
| "loss": 1.9707, | |
| "num_input_tokens_seen": 292416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01545197012619109, | |
| "grad_norm": 8.05718270484028, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.3782, | |
| "num_input_tokens_seen": 350904, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018027298480556272, | |
| "grad_norm": 3.6465275188422344, | |
| "learning_rate": 1.794871794871795e-05, | |
| "loss": 1.0628, | |
| "num_input_tokens_seen": 409384, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020602626834921454, | |
| "grad_norm": 4.842154180410959, | |
| "learning_rate": 2.0512820512820512e-05, | |
| "loss": 0.9789, | |
| "num_input_tokens_seen": 467864, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023177955189286635, | |
| "grad_norm": 2.6799567517341396, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.9327, | |
| "num_input_tokens_seen": 526384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.025753283543651816, | |
| "grad_norm": 2.629272923472648, | |
| "learning_rate": 2.564102564102564e-05, | |
| "loss": 0.9233, | |
| "num_input_tokens_seen": 584856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025753283543651816, | |
| "eval_loss": 0.9281821846961975, | |
| "eval_runtime": 48.2484, | |
| "eval_samples_per_second": 1.244, | |
| "eval_steps_per_second": 0.311, | |
| "num_input_tokens_seen": 584856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028328611898016998, | |
| "grad_norm": 1.2858813899048422, | |
| "learning_rate": 2.8205128205128207e-05, | |
| "loss": 0.897, | |
| "num_input_tokens_seen": 643344, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03090394025238218, | |
| "grad_norm": 1.177678811476692, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.9169, | |
| "num_input_tokens_seen": 701808, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03347926860674736, | |
| "grad_norm": 1.2077065633120996, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.9019, | |
| "num_input_tokens_seen": 760304, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.036054596961112545, | |
| "grad_norm": 1.1560644429967823, | |
| "learning_rate": 3.58974358974359e-05, | |
| "loss": 0.8996, | |
| "num_input_tokens_seen": 818760, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03862992531547772, | |
| "grad_norm": 0.732907212566054, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.9073, | |
| "num_input_tokens_seen": 877256, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04120525366984291, | |
| "grad_norm": 0.9616993870089134, | |
| "learning_rate": 4.1025641025641023e-05, | |
| "loss": 0.9081, | |
| "num_input_tokens_seen": 935752, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.043780582024208085, | |
| "grad_norm": 0.8384067209941525, | |
| "learning_rate": 4.358974358974359e-05, | |
| "loss": 0.906, | |
| "num_input_tokens_seen": 994216, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04635591037857327, | |
| "grad_norm": 0.4045876972188175, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.8952, | |
| "num_input_tokens_seen": 1052704, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04893123873293845, | |
| "grad_norm": 0.6062678622593307, | |
| "learning_rate": 4.871794871794872e-05, | |
| "loss": 0.8996, | |
| "num_input_tokens_seen": 1111176, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05150656708730363, | |
| "grad_norm": 0.5316642041721752, | |
| "learning_rate": 5.128205128205128e-05, | |
| "loss": 0.9024, | |
| "num_input_tokens_seen": 1169664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05150656708730363, | |
| "eval_loss": 0.911374032497406, | |
| "eval_runtime": 19.566, | |
| "eval_samples_per_second": 3.067, | |
| "eval_steps_per_second": 0.767, | |
| "num_input_tokens_seen": 1169664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05408189544166881, | |
| "grad_norm": 0.47189419512253006, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.9142, | |
| "num_input_tokens_seen": 1228112, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "grad_norm": 0.4885000351277984, | |
| "learning_rate": 5.6410256410256414e-05, | |
| "loss": 0.9054, | |
| "num_input_tokens_seen": 1286608, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05923255215039917, | |
| "grad_norm": 1.0232694160031948, | |
| "learning_rate": 5.897435897435898e-05, | |
| "loss": 0.8997, | |
| "num_input_tokens_seen": 1345072, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.06180788050476436, | |
| "grad_norm": 0.6656697152989639, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.8988, | |
| "num_input_tokens_seen": 1403544, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06438320885912954, | |
| "grad_norm": 0.6273175951192728, | |
| "learning_rate": 6.410256410256412e-05, | |
| "loss": 0.9087, | |
| "num_input_tokens_seen": 1462024, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06695853721349472, | |
| "grad_norm": 0.707089894516894, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.8961, | |
| "num_input_tokens_seen": 1520528, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0695338655678599, | |
| "grad_norm": 0.4633668497982238, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.903, | |
| "num_input_tokens_seen": 1579024, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.07210919392222509, | |
| "grad_norm": 0.5052802522069755, | |
| "learning_rate": 7.17948717948718e-05, | |
| "loss": 0.899, | |
| "num_input_tokens_seen": 1637504, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07468452227659027, | |
| "grad_norm": 0.7577940010204668, | |
| "learning_rate": 7.435897435897436e-05, | |
| "loss": 0.9071, | |
| "num_input_tokens_seen": 1696024, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07725985063095545, | |
| "grad_norm": 0.5812587904219971, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.9045, | |
| "num_input_tokens_seen": 1754512, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07725985063095545, | |
| "eval_loss": 0.8934853076934814, | |
| "eval_runtime": 19.8765, | |
| "eval_samples_per_second": 3.019, | |
| "eval_steps_per_second": 0.755, | |
| "num_input_tokens_seen": 1754512, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07983517898532062, | |
| "grad_norm": 0.5167982536583405, | |
| "learning_rate": 7.948717948717948e-05, | |
| "loss": 0.8992, | |
| "num_input_tokens_seen": 1812976, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.08241050733968582, | |
| "grad_norm": 0.4971816797735092, | |
| "learning_rate": 8.205128205128205e-05, | |
| "loss": 0.8965, | |
| "num_input_tokens_seen": 1871464, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08498583569405099, | |
| "grad_norm": 0.6561749633642688, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.9094, | |
| "num_input_tokens_seen": 1929928, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.08756116404841617, | |
| "grad_norm": 0.5010857314708574, | |
| "learning_rate": 8.717948717948718e-05, | |
| "loss": 0.903, | |
| "num_input_tokens_seen": 1988432, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09013649240278135, | |
| "grad_norm": 0.48794512034251364, | |
| "learning_rate": 8.974358974358975e-05, | |
| "loss": 0.902, | |
| "num_input_tokens_seen": 2046920, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09271182075714654, | |
| "grad_norm": 0.4040014684262414, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.9006, | |
| "num_input_tokens_seen": 2105392, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09528714911151172, | |
| "grad_norm": 0.5312840597942438, | |
| "learning_rate": 9.487179487179487e-05, | |
| "loss": 0.9042, | |
| "num_input_tokens_seen": 2163872, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.0978624774658769, | |
| "grad_norm": 0.3535119366494406, | |
| "learning_rate": 9.743589743589744e-05, | |
| "loss": 0.9096, | |
| "num_input_tokens_seen": 2222352, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10043780582024209, | |
| "grad_norm": 0.30590378285024006, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9037, | |
| "num_input_tokens_seen": 2280800, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.10301313417460727, | |
| "grad_norm": 0.3055264226667786, | |
| "learning_rate": 9.999954623308172e-05, | |
| "loss": 0.904, | |
| "num_input_tokens_seen": 2339304, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10301313417460727, | |
| "eval_loss": 0.8980139493942261, | |
| "eval_runtime": 19.316, | |
| "eval_samples_per_second": 3.106, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 2339304, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10558846252897244, | |
| "grad_norm": 0.8828178200664915, | |
| "learning_rate": 9.999818494056303e-05, | |
| "loss": 0.9029, | |
| "num_input_tokens_seen": 2397808, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.10816379088333762, | |
| "grad_norm": 0.4308314655260644, | |
| "learning_rate": 9.99959161471523e-05, | |
| "loss": 0.9005, | |
| "num_input_tokens_seen": 2456288, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11073911923770281, | |
| "grad_norm": 0.4482188659643584, | |
| "learning_rate": 9.99927398940297e-05, | |
| "loss": 0.9096, | |
| "num_input_tokens_seen": 2514784, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.11331444759206799, | |
| "grad_norm": 0.49014741417238206, | |
| "learning_rate": 9.998865623884635e-05, | |
| "loss": 0.9036, | |
| "num_input_tokens_seen": 2573240, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11588977594643317, | |
| "grad_norm": 0.2774850522391394, | |
| "learning_rate": 9.998366525572336e-05, | |
| "loss": 0.901, | |
| "num_input_tokens_seen": 2631672, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.11846510430079835, | |
| "grad_norm": 0.49390873315018263, | |
| "learning_rate": 9.997776703525046e-05, | |
| "loss": 0.9018, | |
| "num_input_tokens_seen": 2690112, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12104043265516354, | |
| "grad_norm": 0.3284306399258997, | |
| "learning_rate": 9.997096168448432e-05, | |
| "loss": 0.8934, | |
| "num_input_tokens_seen": 2748608, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.12361576100952872, | |
| "grad_norm": 0.7182680023403506, | |
| "learning_rate": 9.996324932694668e-05, | |
| "loss": 0.8876, | |
| "num_input_tokens_seen": 2807080, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1261910893638939, | |
| "grad_norm": 0.7305499346526235, | |
| "learning_rate": 9.995463010262206e-05, | |
| "loss": 0.9084, | |
| "num_input_tokens_seen": 2865520, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.12876641771825909, | |
| "grad_norm": 0.5773211522908436, | |
| "learning_rate": 9.994510416795519e-05, | |
| "loss": 0.9106, | |
| "num_input_tokens_seen": 2924016, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.12876641771825909, | |
| "eval_loss": 0.8958488702774048, | |
| "eval_runtime": 19.507, | |
| "eval_samples_per_second": 3.076, | |
| "eval_steps_per_second": 0.769, | |
| "num_input_tokens_seen": 2924016, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13134174607262425, | |
| "grad_norm": 0.44306061088962184, | |
| "learning_rate": 9.993467169584824e-05, | |
| "loss": 0.9012, | |
| "num_input_tokens_seen": 2982520, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.13391707442698944, | |
| "grad_norm": 0.7851687259125024, | |
| "learning_rate": 9.992333287565765e-05, | |
| "loss": 0.9069, | |
| "num_input_tokens_seen": 3041008, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.13649240278135463, | |
| "grad_norm": 0.5705235716557865, | |
| "learning_rate": 9.991108791319066e-05, | |
| "loss": 0.8918, | |
| "num_input_tokens_seen": 3099464, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.1390677311357198, | |
| "grad_norm": 0.6202972137914602, | |
| "learning_rate": 9.989793703070163e-05, | |
| "loss": 0.8996, | |
| "num_input_tokens_seen": 3157944, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.141643059490085, | |
| "grad_norm": 0.7583768377175583, | |
| "learning_rate": 9.988388046688799e-05, | |
| "loss": 0.9009, | |
| "num_input_tokens_seen": 3216448, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.14421838784445018, | |
| "grad_norm": 0.7180540444266581, | |
| "learning_rate": 9.986891847688587e-05, | |
| "loss": 0.9059, | |
| "num_input_tokens_seen": 3274928, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.14679371619881534, | |
| "grad_norm": 0.4173225854654158, | |
| "learning_rate": 9.985305133226553e-05, | |
| "loss": 0.8939, | |
| "num_input_tokens_seen": 3333408, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.14936904455318054, | |
| "grad_norm": 0.7825855108807762, | |
| "learning_rate": 9.983627932102638e-05, | |
| "loss": 0.8899, | |
| "num_input_tokens_seen": 3391896, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1519443729075457, | |
| "grad_norm": 0.4850249272160501, | |
| "learning_rate": 9.981860274759173e-05, | |
| "loss": 0.9092, | |
| "num_input_tokens_seen": 3450392, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.1545197012619109, | |
| "grad_norm": 0.3325682106309916, | |
| "learning_rate": 9.980002193280342e-05, | |
| "loss": 0.8901, | |
| "num_input_tokens_seen": 3508888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1545197012619109, | |
| "eval_loss": 0.8932263255119324, | |
| "eval_runtime": 19.7633, | |
| "eval_samples_per_second": 3.036, | |
| "eval_steps_per_second": 0.759, | |
| "num_input_tokens_seen": 3508888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15709502961627608, | |
| "grad_norm": 0.36562722920113416, | |
| "learning_rate": 9.978053721391578e-05, | |
| "loss": 0.9042, | |
| "num_input_tokens_seen": 3567368, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.15967035797064125, | |
| "grad_norm": 0.3765491511973325, | |
| "learning_rate": 9.976014894458963e-05, | |
| "loss": 0.9007, | |
| "num_input_tokens_seen": 3625848, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.16224568632500644, | |
| "grad_norm": 0.5264420727347517, | |
| "learning_rate": 9.973885749488589e-05, | |
| "loss": 0.9036, | |
| "num_input_tokens_seen": 3684336, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.16482101467937163, | |
| "grad_norm": 0.24680747784235688, | |
| "learning_rate": 9.971666325125874e-05, | |
| "loss": 0.8936, | |
| "num_input_tokens_seen": 3742800, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1673963430337368, | |
| "grad_norm": 0.4982571051665039, | |
| "learning_rate": 9.969356661654876e-05, | |
| "loss": 0.8989, | |
| "num_input_tokens_seen": 3801280, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.16997167138810199, | |
| "grad_norm": 0.49943012602572584, | |
| "learning_rate": 9.966956800997546e-05, | |
| "loss": 0.8983, | |
| "num_input_tokens_seen": 3859792, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.17254699974246718, | |
| "grad_norm": 0.37381050353079964, | |
| "learning_rate": 9.964466786712984e-05, | |
| "loss": 0.9038, | |
| "num_input_tokens_seen": 3918272, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.17512232809683234, | |
| "grad_norm": 0.7501484170811903, | |
| "learning_rate": 9.961886663996629e-05, | |
| "loss": 0.8947, | |
| "num_input_tokens_seen": 3976760, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.17769765645119753, | |
| "grad_norm": 0.5623847203835772, | |
| "learning_rate": 9.959216479679458e-05, | |
| "loss": 0.9179, | |
| "num_input_tokens_seen": 4035240, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.1802729848055627, | |
| "grad_norm": 0.34381878607605765, | |
| "learning_rate": 9.956456282227122e-05, | |
| "loss": 0.9059, | |
| "num_input_tokens_seen": 4093688, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1802729848055627, | |
| "eval_loss": 0.8960411548614502, | |
| "eval_runtime": 20.0734, | |
| "eval_samples_per_second": 2.989, | |
| "eval_steps_per_second": 0.747, | |
| "num_input_tokens_seen": 4093688, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1828483131599279, | |
| "grad_norm": 0.5786050277605497, | |
| "learning_rate": 9.953606121739074e-05, | |
| "loss": 0.8795, | |
| "num_input_tokens_seen": 4152160, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.18542364151429308, | |
| "grad_norm": 1.3309062985901938, | |
| "learning_rate": 9.950666049947653e-05, | |
| "loss": 0.9143, | |
| "num_input_tokens_seen": 4210648, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.18799896986865824, | |
| "grad_norm": 0.5010297124723248, | |
| "learning_rate": 9.947636120217155e-05, | |
| "loss": 0.9164, | |
| "num_input_tokens_seen": 4269136, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.19057429822302344, | |
| "grad_norm": 0.7250841632803818, | |
| "learning_rate": 9.944516387542852e-05, | |
| "loss": 0.9061, | |
| "num_input_tokens_seen": 4327664, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.19314962657738863, | |
| "grad_norm": 0.4506280653909736, | |
| "learning_rate": 9.941306908550005e-05, | |
| "loss": 0.8873, | |
| "num_input_tokens_seen": 4386120, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.1957249549317538, | |
| "grad_norm": 0.6467175538087946, | |
| "learning_rate": 9.938007741492828e-05, | |
| "loss": 0.9038, | |
| "num_input_tokens_seen": 4444560, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.19830028328611898, | |
| "grad_norm": 0.6742654767461002, | |
| "learning_rate": 9.934618946253437e-05, | |
| "loss": 0.9116, | |
| "num_input_tokens_seen": 4503016, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.20087561164048418, | |
| "grad_norm": 0.418516338281364, | |
| "learning_rate": 9.931140584340761e-05, | |
| "loss": 0.9023, | |
| "num_input_tokens_seen": 4561496, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.20345093999484934, | |
| "grad_norm": 0.5738919793445436, | |
| "learning_rate": 9.92757271888942e-05, | |
| "loss": 0.8901, | |
| "num_input_tokens_seen": 4619944, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.20602626834921453, | |
| "grad_norm": 0.3600152815973316, | |
| "learning_rate": 9.923915414658587e-05, | |
| "loss": 0.9033, | |
| "num_input_tokens_seen": 4678384, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.20602626834921453, | |
| "eval_loss": 0.906301736831665, | |
| "eval_runtime": 19.8079, | |
| "eval_samples_per_second": 3.029, | |
| "eval_steps_per_second": 0.757, | |
| "num_input_tokens_seen": 4678384, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2086015967035797, | |
| "grad_norm": 0.4854922483196253, | |
| "learning_rate": 9.920168738030807e-05, | |
| "loss": 0.8951, | |
| "num_input_tokens_seen": 4736904, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.2111769250579449, | |
| "grad_norm": 0.4537032287993717, | |
| "learning_rate": 9.916332757010799e-05, | |
| "loss": 0.9131, | |
| "num_input_tokens_seen": 4795376, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.21375225341231008, | |
| "grad_norm": 0.46655140937482126, | |
| "learning_rate": 9.912407541224213e-05, | |
| "loss": 0.8923, | |
| "num_input_tokens_seen": 4853880, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.21632758176667524, | |
| "grad_norm": 0.3608301258843965, | |
| "learning_rate": 9.908393161916374e-05, | |
| "loss": 0.9026, | |
| "num_input_tokens_seen": 4912360, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.21890291012104043, | |
| "grad_norm": 0.5055648531803498, | |
| "learning_rate": 9.904289691950979e-05, | |
| "loss": 0.905, | |
| "num_input_tokens_seen": 4970872, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.22147823847540563, | |
| "grad_norm": 0.3171606869940592, | |
| "learning_rate": 9.900097205808789e-05, | |
| "loss": 0.8941, | |
| "num_input_tokens_seen": 5029304, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2240535668297708, | |
| "grad_norm": 0.5798722428230844, | |
| "learning_rate": 9.895815779586262e-05, | |
| "loss": 0.9031, | |
| "num_input_tokens_seen": 5087800, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.22662889518413598, | |
| "grad_norm": 0.5751083474979835, | |
| "learning_rate": 9.891445490994182e-05, | |
| "loss": 0.8975, | |
| "num_input_tokens_seen": 5146312, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.22920422353850115, | |
| "grad_norm": 1.2316619525123293, | |
| "learning_rate": 9.886986419356246e-05, | |
| "loss": 0.901, | |
| "num_input_tokens_seen": 5204800, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.23177955189286634, | |
| "grad_norm": 0.5953254293558816, | |
| "learning_rate": 9.88243864560762e-05, | |
| "loss": 0.9062, | |
| "num_input_tokens_seen": 5263304, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.23177955189286634, | |
| "eval_loss": 0.9007609486579895, | |
| "eval_runtime": 20.8827, | |
| "eval_samples_per_second": 2.873, | |
| "eval_steps_per_second": 0.718, | |
| "num_input_tokens_seen": 5263304, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.23435488024723153, | |
| "grad_norm": 0.7549819464827967, | |
| "learning_rate": 9.877802252293474e-05, | |
| "loss": 0.8891, | |
| "num_input_tokens_seen": 5321760, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.2369302086015967, | |
| "grad_norm": 0.9960909370043465, | |
| "learning_rate": 9.873077323567488e-05, | |
| "loss": 0.9026, | |
| "num_input_tokens_seen": 5380224, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.23950553695596188, | |
| "grad_norm": 1.5888386521989892, | |
| "learning_rate": 9.868263945190312e-05, | |
| "loss": 0.8707, | |
| "num_input_tokens_seen": 5438704, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.24208086531032708, | |
| "grad_norm": 3.0542478842411587, | |
| "learning_rate": 9.863362204528024e-05, | |
| "loss": 0.9051, | |
| "num_input_tokens_seen": 5497208, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.24465619366469224, | |
| "grad_norm": 1.2908325061552137, | |
| "learning_rate": 9.858372190550533e-05, | |
| "loss": 0.8711, | |
| "num_input_tokens_seen": 5555704, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.24723152201905743, | |
| "grad_norm": 3.1989324866235744, | |
| "learning_rate": 9.853293993829969e-05, | |
| "loss": 0.885, | |
| "num_input_tokens_seen": 5614160, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.24980685037342262, | |
| "grad_norm": 3.591366302378185, | |
| "learning_rate": 9.848127706539039e-05, | |
| "loss": 0.8615, | |
| "num_input_tokens_seen": 5672640, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.2523821787277878, | |
| "grad_norm": 2.053833335696007, | |
| "learning_rate": 9.842873422449354e-05, | |
| "loss": 0.9057, | |
| "num_input_tokens_seen": 5731072, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.254957507082153, | |
| "grad_norm": 1.4501486574941083, | |
| "learning_rate": 9.837531236929726e-05, | |
| "loss": 0.8818, | |
| "num_input_tokens_seen": 5789544, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.25753283543651817, | |
| "grad_norm": 2.1068404021122866, | |
| "learning_rate": 9.832101246944439e-05, | |
| "loss": 0.8576, | |
| "num_input_tokens_seen": 5848048, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25753283543651817, | |
| "eval_loss": 0.8268976211547852, | |
| "eval_runtime": 19.6346, | |
| "eval_samples_per_second": 3.056, | |
| "eval_steps_per_second": 0.764, | |
| "num_input_tokens_seen": 5848048, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26010816379088336, | |
| "grad_norm": 4.216936754020565, | |
| "learning_rate": 9.826583551051483e-05, | |
| "loss": 0.8566, | |
| "num_input_tokens_seen": 5906512, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.2626834921452485, | |
| "grad_norm": 10.456282683777822, | |
| "learning_rate": 9.820978249400773e-05, | |
| "loss": 0.8365, | |
| "num_input_tokens_seen": 5965024, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.2652588204996137, | |
| "grad_norm": 2.334974931865165, | |
| "learning_rate": 9.81528544373233e-05, | |
| "loss": 0.8882, | |
| "num_input_tokens_seen": 6023496, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.2678341488539789, | |
| "grad_norm": 0.6948827424617825, | |
| "learning_rate": 9.809505237374426e-05, | |
| "loss": 0.8799, | |
| "num_input_tokens_seen": 6082000, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2704094772083441, | |
| "grad_norm": 0.8415524888602947, | |
| "learning_rate": 9.80363773524172e-05, | |
| "loss": 0.8758, | |
| "num_input_tokens_seen": 6140480, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.27298480556270927, | |
| "grad_norm": 1.3536520282199265, | |
| "learning_rate": 9.797683043833345e-05, | |
| "loss": 0.8644, | |
| "num_input_tokens_seen": 6198968, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.2755601339170744, | |
| "grad_norm": 4.556188528469967, | |
| "learning_rate": 9.791641271230982e-05, | |
| "loss": 0.8453, | |
| "num_input_tokens_seen": 6257464, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.2781354622714396, | |
| "grad_norm": 2.890141630286954, | |
| "learning_rate": 9.78551252709689e-05, | |
| "loss": 0.8533, | |
| "num_input_tokens_seen": 6315944, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.2807107906258048, | |
| "grad_norm": 4.471490037342243, | |
| "learning_rate": 9.779296922671923e-05, | |
| "loss": 0.8575, | |
| "num_input_tokens_seen": 6374408, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "grad_norm": 3.174906426420603, | |
| "learning_rate": 9.77299457077351e-05, | |
| "loss": 0.8666, | |
| "num_input_tokens_seen": 6432936, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.28328611898017, | |
| "eval_loss": 0.7909801602363586, | |
| "eval_runtime": 19.8739, | |
| "eval_samples_per_second": 3.019, | |
| "eval_steps_per_second": 0.755, | |
| "num_input_tokens_seen": 6432936, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.28586144733453517, | |
| "grad_norm": 3.529163852540611, | |
| "learning_rate": 9.7666055857936e-05, | |
| "loss": 0.8264, | |
| "num_input_tokens_seen": 6491400, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.28843677568890036, | |
| "grad_norm": 4.044590312854015, | |
| "learning_rate": 9.760130083696595e-05, | |
| "loss": 0.8456, | |
| "num_input_tokens_seen": 6549872, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.2910121040432655, | |
| "grad_norm": 4.650808013267891, | |
| "learning_rate": 9.75356818201724e-05, | |
| "loss": 0.8032, | |
| "num_input_tokens_seen": 6608296, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.2935874323976307, | |
| "grad_norm": 6.577223054225459, | |
| "learning_rate": 9.746919999858492e-05, | |
| "loss": 0.8081, | |
| "num_input_tokens_seen": 6666768, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2961627607519959, | |
| "grad_norm": 7.1732684079932545, | |
| "learning_rate": 9.740185657889357e-05, | |
| "loss": 0.8398, | |
| "num_input_tokens_seen": 6725248, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.29873808910636107, | |
| "grad_norm": 21.451661035438484, | |
| "learning_rate": 9.733365278342696e-05, | |
| "loss": 0.8908, | |
| "num_input_tokens_seen": 6783680, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.30131341746072626, | |
| "grad_norm": 4.031699151478832, | |
| "learning_rate": 9.726458985013017e-05, | |
| "loss": 0.8248, | |
| "num_input_tokens_seen": 6842144, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.3038887458150914, | |
| "grad_norm": 3.45579530759462, | |
| "learning_rate": 9.719466903254215e-05, | |
| "loss": 0.829, | |
| "num_input_tokens_seen": 6900656, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.3064640741694566, | |
| "grad_norm": 4.518719062630672, | |
| "learning_rate": 9.712389159977307e-05, | |
| "loss": 0.8269, | |
| "num_input_tokens_seen": 6959128, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.3090394025238218, | |
| "grad_norm": 12.728221405806083, | |
| "learning_rate": 9.705225883648121e-05, | |
| "loss": 0.7997, | |
| "num_input_tokens_seen": 7017576, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3090394025238218, | |
| "eval_loss": 0.787663459777832, | |
| "eval_runtime": 19.6121, | |
| "eval_samples_per_second": 3.059, | |
| "eval_steps_per_second": 0.765, | |
| "num_input_tokens_seen": 7017576, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.311614730878187, | |
| "grad_norm": 6.69798043480266, | |
| "learning_rate": 9.697977204284973e-05, | |
| "loss": 0.8925, | |
| "num_input_tokens_seen": 7076032, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.31419005923255217, | |
| "grad_norm": 5.067921055882507, | |
| "learning_rate": 9.690643253456297e-05, | |
| "loss": 0.8159, | |
| "num_input_tokens_seen": 7134536, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.31676538758691736, | |
| "grad_norm": 7.400939684061883, | |
| "learning_rate": 9.683224164278264e-05, | |
| "loss": 0.826, | |
| "num_input_tokens_seen": 7193032, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.3193407159412825, | |
| "grad_norm": 5.898525799199162, | |
| "learning_rate": 9.675720071412365e-05, | |
| "loss": 0.8187, | |
| "num_input_tokens_seen": 7251568, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.3219160442956477, | |
| "grad_norm": 11.267105316774332, | |
| "learning_rate": 9.66813111106296e-05, | |
| "loss": 0.8524, | |
| "num_input_tokens_seen": 7310072, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.3244913726500129, | |
| "grad_norm": 6.703970582399643, | |
| "learning_rate": 9.660457420974819e-05, | |
| "loss": 0.7966, | |
| "num_input_tokens_seen": 7368560, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.32706670100437807, | |
| "grad_norm": 6.945445265294353, | |
| "learning_rate": 9.652699140430608e-05, | |
| "loss": 0.799, | |
| "num_input_tokens_seen": 7427040, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.32964202935874326, | |
| "grad_norm": 7.0684293091171595, | |
| "learning_rate": 9.644856410248369e-05, | |
| "loss": 0.8477, | |
| "num_input_tokens_seen": 7485552, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.3322173577131084, | |
| "grad_norm": 7.165086711244158, | |
| "learning_rate": 9.636929372778963e-05, | |
| "loss": 0.7867, | |
| "num_input_tokens_seen": 7544040, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.3347926860674736, | |
| "grad_norm": 9.185933515393563, | |
| "learning_rate": 9.628918171903485e-05, | |
| "loss": 0.8367, | |
| "num_input_tokens_seen": 7602512, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3347926860674736, | |
| "eval_loss": 0.7940558791160583, | |
| "eval_runtime": 19.7641, | |
| "eval_samples_per_second": 3.036, | |
| "eval_steps_per_second": 0.759, | |
| "num_input_tokens_seen": 7602512, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3373680144218388, | |
| "grad_norm": 6.586425160827751, | |
| "learning_rate": 9.620822953030652e-05, | |
| "loss": 0.8131, | |
| "num_input_tokens_seen": 7660968, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.33994334277620397, | |
| "grad_norm": 6.92970378602844, | |
| "learning_rate": 9.612643863094163e-05, | |
| "loss": 0.8348, | |
| "num_input_tokens_seen": 7719448, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.34251867113056916, | |
| "grad_norm": 8.35228285894448, | |
| "learning_rate": 9.604381050550038e-05, | |
| "loss": 0.8289, | |
| "num_input_tokens_seen": 7777928, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.34509399948493436, | |
| "grad_norm": 12.894782157020227, | |
| "learning_rate": 9.596034665373916e-05, | |
| "loss": 0.7758, | |
| "num_input_tokens_seen": 7836424, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.3476693278392995, | |
| "grad_norm": 13.409694970235305, | |
| "learning_rate": 9.587604859058334e-05, | |
| "loss": 0.8189, | |
| "num_input_tokens_seen": 7894904, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.3502446561936647, | |
| "grad_norm": 8.783205826578632, | |
| "learning_rate": 9.579091784609984e-05, | |
| "loss": 0.8221, | |
| "num_input_tokens_seen": 7953432, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.3528199845480299, | |
| "grad_norm": 8.368380903445857, | |
| "learning_rate": 9.570495596546926e-05, | |
| "loss": 0.8378, | |
| "num_input_tokens_seen": 8011888, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.35539531290239507, | |
| "grad_norm": 6.7086179135551145, | |
| "learning_rate": 9.561816450895793e-05, | |
| "loss": 0.7529, | |
| "num_input_tokens_seen": 8070344, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.35797064125676026, | |
| "grad_norm": 8.476897088436242, | |
| "learning_rate": 9.55305450518895e-05, | |
| "loss": 0.7311, | |
| "num_input_tokens_seen": 8128816, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.3605459696111254, | |
| "grad_norm": 10.427785019598666, | |
| "learning_rate": 9.544209918461642e-05, | |
| "loss": 0.774, | |
| "num_input_tokens_seen": 8187320, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3605459696111254, | |
| "eval_loss": 0.7318872809410095, | |
| "eval_runtime": 19.6917, | |
| "eval_samples_per_second": 3.047, | |
| "eval_steps_per_second": 0.762, | |
| "num_input_tokens_seen": 8187320, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3631212979654906, | |
| "grad_norm": 14.492396688166755, | |
| "learning_rate": 9.535282851249103e-05, | |
| "loss": 0.765, | |
| "num_input_tokens_seen": 8245776, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.3656966263198558, | |
| "grad_norm": 16.054951836007135, | |
| "learning_rate": 9.526273465583646e-05, | |
| "loss": 0.7287, | |
| "num_input_tokens_seen": 8304280, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.36827195467422097, | |
| "grad_norm": 21.4994447839661, | |
| "learning_rate": 9.517181924991716e-05, | |
| "loss": 0.758, | |
| "num_input_tokens_seen": 8362728, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.37084728302858616, | |
| "grad_norm": 10.676012702912917, | |
| "learning_rate": 9.508008394490926e-05, | |
| "loss": 0.795, | |
| "num_input_tokens_seen": 8421224, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.37342261138295135, | |
| "grad_norm": 9.802559177691224, | |
| "learning_rate": 9.498753040587066e-05, | |
| "loss": 0.6901, | |
| "num_input_tokens_seen": 8479720, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.3759979397373165, | |
| "grad_norm": 12.345047855457121, | |
| "learning_rate": 9.48941603127107e-05, | |
| "loss": 0.7618, | |
| "num_input_tokens_seen": 8538192, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.3785732680916817, | |
| "grad_norm": 9.115843124142248, | |
| "learning_rate": 9.479997536015977e-05, | |
| "loss": 0.7481, | |
| "num_input_tokens_seen": 8596664, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.3811485964460469, | |
| "grad_norm": 13.754407712653018, | |
| "learning_rate": 9.47049772577385e-05, | |
| "loss": 0.746, | |
| "num_input_tokens_seen": 8655128, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.38372392480041206, | |
| "grad_norm": 11.612003816357428, | |
| "learning_rate": 9.460916772972672e-05, | |
| "loss": 0.812, | |
| "num_input_tokens_seen": 8713624, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.38629925315477726, | |
| "grad_norm": 27.606819697848053, | |
| "learning_rate": 9.451254851513222e-05, | |
| "loss": 0.6751, | |
| "num_input_tokens_seen": 8772104, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.38629925315477726, | |
| "eval_loss": 0.732211709022522, | |
| "eval_runtime": 19.8828, | |
| "eval_samples_per_second": 3.018, | |
| "eval_steps_per_second": 0.754, | |
| "num_input_tokens_seen": 8772104, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3888745815091424, | |
| "grad_norm": 14.96041133173447, | |
| "learning_rate": 9.441512136765911e-05, | |
| "loss": 0.7772, | |
| "num_input_tokens_seen": 8830568, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.3914499098635076, | |
| "grad_norm": 11.503685090619637, | |
| "learning_rate": 9.431688805567607e-05, | |
| "loss": 0.7114, | |
| "num_input_tokens_seen": 8889072, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.3940252382178728, | |
| "grad_norm": 10.096502565612639, | |
| "learning_rate": 9.421785036218417e-05, | |
| "loss": 0.8463, | |
| "num_input_tokens_seen": 8947568, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.39660056657223797, | |
| "grad_norm": 10.03630613489591, | |
| "learning_rate": 9.411801008478459e-05, | |
| "loss": 0.7822, | |
| "num_input_tokens_seen": 9006056, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.39917589492660316, | |
| "grad_norm": 9.513127486957377, | |
| "learning_rate": 9.401736903564592e-05, | |
| "loss": 0.7628, | |
| "num_input_tokens_seen": 9064592, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.40175122328096835, | |
| "grad_norm": 6.959520401923045, | |
| "learning_rate": 9.39159290414713e-05, | |
| "loss": 0.7589, | |
| "num_input_tokens_seen": 9123096, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.4043265516353335, | |
| "grad_norm": 11.121102798997068, | |
| "learning_rate": 9.381369194346527e-05, | |
| "loss": 0.7564, | |
| "num_input_tokens_seen": 9181576, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.4069018799896987, | |
| "grad_norm": 8.968142728241798, | |
| "learning_rate": 9.371065959730039e-05, | |
| "loss": 0.6934, | |
| "num_input_tokens_seen": 9240048, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.40947720834406387, | |
| "grad_norm": 12.849518629503493, | |
| "learning_rate": 9.36068338730834e-05, | |
| "loss": 0.7314, | |
| "num_input_tokens_seen": 9298528, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.41205253669842906, | |
| "grad_norm": 68.63999985815002, | |
| "learning_rate": 9.35022166553215e-05, | |
| "loss": 0.6911, | |
| "num_input_tokens_seen": 9357016, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.41205253669842906, | |
| "eval_loss": 0.7180347442626953, | |
| "eval_runtime": 19.3266, | |
| "eval_samples_per_second": 3.105, | |
| "eval_steps_per_second": 0.776, | |
| "num_input_tokens_seen": 9357016, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.41462786505279425, | |
| "grad_norm": 12.26130532110871, | |
| "learning_rate": 9.339680984288799e-05, | |
| "loss": 0.7086, | |
| "num_input_tokens_seen": 9415480, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.4172031934071594, | |
| "grad_norm": 15.883264561409183, | |
| "learning_rate": 9.329061534898783e-05, | |
| "loss": 0.7726, | |
| "num_input_tokens_seen": 9473928, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.4197785217615246, | |
| "grad_norm": 17.855002564946467, | |
| "learning_rate": 9.318363510112296e-05, | |
| "loss": 0.7286, | |
| "num_input_tokens_seen": 9532408, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.4223538501158898, | |
| "grad_norm": 11.119850082821575, | |
| "learning_rate": 9.307587104105729e-05, | |
| "loss": 0.7515, | |
| "num_input_tokens_seen": 9590920, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.42492917847025496, | |
| "grad_norm": 9.916888211602318, | |
| "learning_rate": 9.296732512478139e-05, | |
| "loss": 0.7344, | |
| "num_input_tokens_seen": 9649400, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.42750450682462016, | |
| "grad_norm": 9.805389743080928, | |
| "learning_rate": 9.285799932247714e-05, | |
| "loss": 0.6954, | |
| "num_input_tokens_seen": 9707888, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.43007983517898535, | |
| "grad_norm": 8.068508417105404, | |
| "learning_rate": 9.274789561848183e-05, | |
| "loss": 0.7312, | |
| "num_input_tokens_seen": 9766384, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.4326551635333505, | |
| "grad_norm": 8.152928433205195, | |
| "learning_rate": 9.263701601125218e-05, | |
| "loss": 0.647, | |
| "num_input_tokens_seen": 9824896, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.4352304918877157, | |
| "grad_norm": 17.465963143357314, | |
| "learning_rate": 9.252536251332813e-05, | |
| "loss": 0.7273, | |
| "num_input_tokens_seen": 9883408, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.43780582024208087, | |
| "grad_norm": 6.231784874865904, | |
| "learning_rate": 9.24129371512962e-05, | |
| "loss": 0.7455, | |
| "num_input_tokens_seen": 9941896, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.43780582024208087, | |
| "eval_loss": 0.7039459347724915, | |
| "eval_runtime": 19.7834, | |
| "eval_samples_per_second": 3.033, | |
| "eval_steps_per_second": 0.758, | |
| "num_input_tokens_seen": 9941896, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.44038114859644606, | |
| "grad_norm": 8.584709523479143, | |
| "learning_rate": 9.22997419657528e-05, | |
| "loss": 0.6829, | |
| "num_input_tokens_seen": 10000336, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.44295647695081125, | |
| "grad_norm": 9.894526327436065, | |
| "learning_rate": 9.218577901126713e-05, | |
| "loss": 0.6971, | |
| "num_input_tokens_seen": 10058816, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.4455318053051764, | |
| "grad_norm": 6.844807331677797, | |
| "learning_rate": 9.207105035634397e-05, | |
| "loss": 0.7239, | |
| "num_input_tokens_seen": 10117320, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.4481071336595416, | |
| "grad_norm": 9.911971184322747, | |
| "learning_rate": 9.195555808338603e-05, | |
| "loss": 0.7113, | |
| "num_input_tokens_seen": 10175824, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.45068246201390677, | |
| "grad_norm": 11.42729729117445, | |
| "learning_rate": 9.183930428865622e-05, | |
| "loss": 0.685, | |
| "num_input_tokens_seen": 10234288, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.45325779036827196, | |
| "grad_norm": 6.6164653318829005, | |
| "learning_rate": 9.17222910822396e-05, | |
| "loss": 0.6804, | |
| "num_input_tokens_seen": 10292736, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.45583311872263715, | |
| "grad_norm": 9.566984327413312, | |
| "learning_rate": 9.160452058800504e-05, | |
| "loss": 0.7056, | |
| "num_input_tokens_seen": 10351224, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.4584084470770023, | |
| "grad_norm": 8.37543764212447, | |
| "learning_rate": 9.148599494356671e-05, | |
| "loss": 0.7234, | |
| "num_input_tokens_seen": 10409736, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.4609837754313675, | |
| "grad_norm": 8.118764978921215, | |
| "learning_rate": 9.136671630024527e-05, | |
| "loss": 0.7505, | |
| "num_input_tokens_seen": 10468240, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.4635591037857327, | |
| "grad_norm": 8.91603360160678, | |
| "learning_rate": 9.124668682302882e-05, | |
| "loss": 0.7378, | |
| "num_input_tokens_seen": 10526712, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4635591037857327, | |
| "eval_loss": 0.7197856903076172, | |
| "eval_runtime": 19.6818, | |
| "eval_samples_per_second": 3.048, | |
| "eval_steps_per_second": 0.762, | |
| "num_input_tokens_seen": 10526712, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.46613443214009787, | |
| "grad_norm": 7.649426233722995, | |
| "learning_rate": 9.112590869053359e-05, | |
| "loss": 0.6794, | |
| "num_input_tokens_seen": 10585232, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.46870976049446306, | |
| "grad_norm": 6.066459270532772, | |
| "learning_rate": 9.100438409496444e-05, | |
| "loss": 0.6817, | |
| "num_input_tokens_seen": 10643728, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.47128508884882825, | |
| "grad_norm": 7.144597127673979, | |
| "learning_rate": 9.088211524207497e-05, | |
| "loss": 0.6503, | |
| "num_input_tokens_seen": 10702240, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.4738604172031934, | |
| "grad_norm": 9.676112884447143, | |
| "learning_rate": 9.075910435112766e-05, | |
| "loss": 0.6903, | |
| "num_input_tokens_seen": 10760656, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.4764357455575586, | |
| "grad_norm": 12.206584747037537, | |
| "learning_rate": 9.063535365485341e-05, | |
| "loss": 0.6611, | |
| "num_input_tokens_seen": 10819128, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.47901107391192377, | |
| "grad_norm": 8.724970113237934, | |
| "learning_rate": 9.051086539941108e-05, | |
| "loss": 0.6361, | |
| "num_input_tokens_seen": 10877600, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.48158640226628896, | |
| "grad_norm": 26.26773221921971, | |
| "learning_rate": 9.038564184434676e-05, | |
| "loss": 0.7006, | |
| "num_input_tokens_seen": 10936088, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.48416173062065415, | |
| "grad_norm": 6.223867131390233, | |
| "learning_rate": 9.025968526255275e-05, | |
| "loss": 0.7012, | |
| "num_input_tokens_seen": 10994560, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.4867370589750193, | |
| "grad_norm": 6.1072541360418295, | |
| "learning_rate": 9.013299794022622e-05, | |
| "loss": 0.6968, | |
| "num_input_tokens_seen": 11053016, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.4893123873293845, | |
| "grad_norm": 8.372921238626587, | |
| "learning_rate": 9.00055821768278e-05, | |
| "loss": 0.6825, | |
| "num_input_tokens_seen": 11111520, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.4893123873293845, | |
| "eval_loss": 0.6830747723579407, | |
| "eval_runtime": 19.7357, | |
| "eval_samples_per_second": 3.04, | |
| "eval_steps_per_second": 0.76, | |
| "num_input_tokens_seen": 11111520, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.49188771568374967, | |
| "grad_norm": 8.942834634941512, | |
| "learning_rate": 8.987744028503981e-05, | |
| "loss": 0.6957, | |
| "num_input_tokens_seen": 11170016, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.49446304403811486, | |
| "grad_norm": 7.280449373939037, | |
| "learning_rate": 8.974857459072435e-05, | |
| "loss": 0.6531, | |
| "num_input_tokens_seen": 11228496, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.49703837239248005, | |
| "grad_norm": 11.559627425451879, | |
| "learning_rate": 8.961898743288094e-05, | |
| "loss": 0.6201, | |
| "num_input_tokens_seen": 11286928, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.49961370074684525, | |
| "grad_norm": 8.705456467164504, | |
| "learning_rate": 8.948868116360421e-05, | |
| "loss": 0.5677, | |
| "num_input_tokens_seen": 11345400, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.5021890291012104, | |
| "grad_norm": 11.843729276311603, | |
| "learning_rate": 8.935765814804112e-05, | |
| "loss": 0.5763, | |
| "num_input_tokens_seen": 11403912, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.5047643574555756, | |
| "grad_norm": 9.09749490323839, | |
| "learning_rate": 8.922592076434804e-05, | |
| "loss": 0.6348, | |
| "num_input_tokens_seen": 11462344, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.5073396858099408, | |
| "grad_norm": 9.15512782816083, | |
| "learning_rate": 8.90934714036477e-05, | |
| "loss": 0.6541, | |
| "num_input_tokens_seen": 11520808, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.509915014164306, | |
| "grad_norm": 7.3541970927874125, | |
| "learning_rate": 8.896031246998558e-05, | |
| "loss": 0.7012, | |
| "num_input_tokens_seen": 11579248, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.5124903425186711, | |
| "grad_norm": 7.2544111988448305, | |
| "learning_rate": 8.882644638028646e-05, | |
| "loss": 0.6508, | |
| "num_input_tokens_seen": 11637712, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.5150656708730363, | |
| "grad_norm": 8.317370673188798, | |
| "learning_rate": 8.869187556431046e-05, | |
| "loss": 0.5971, | |
| "num_input_tokens_seen": 11696200, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5150656708730363, | |
| "eval_loss": 0.7078786492347717, | |
| "eval_runtime": 19.6933, | |
| "eval_samples_per_second": 3.047, | |
| "eval_steps_per_second": 0.762, | |
| "num_input_tokens_seen": 11696200, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5176409992274015, | |
| "grad_norm": 9.38238507668501, | |
| "learning_rate": 8.855660246460895e-05, | |
| "loss": 0.6959, | |
| "num_input_tokens_seen": 11754720, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.5202163275817667, | |
| "grad_norm": 8.602013574457626, | |
| "learning_rate": 8.842062953648023e-05, | |
| "loss": 0.6918, | |
| "num_input_tokens_seen": 11813216, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.5227916559361319, | |
| "grad_norm": 6.752768596735988, | |
| "learning_rate": 8.828395924792497e-05, | |
| "loss": 0.7269, | |
| "num_input_tokens_seen": 11871712, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.525366984290497, | |
| "grad_norm": 3.9336242665009187, | |
| "learning_rate": 8.814659407960141e-05, | |
| "loss": 0.7026, | |
| "num_input_tokens_seen": 11930200, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.5279423126448622, | |
| "grad_norm": 5.739197643968765, | |
| "learning_rate": 8.800853652478028e-05, | |
| "loss": 0.6467, | |
| "num_input_tokens_seen": 11988704, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.5305176409992274, | |
| "grad_norm": 4.583970239100745, | |
| "learning_rate": 8.786978908929966e-05, | |
| "loss": 0.6155, | |
| "num_input_tokens_seen": 12047176, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.5330929693535926, | |
| "grad_norm": 7.891614334520996, | |
| "learning_rate": 8.773035429151937e-05, | |
| "loss": 0.7849, | |
| "num_input_tokens_seen": 12105680, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.5356682977079578, | |
| "grad_norm": 10.308514200015722, | |
| "learning_rate": 8.759023466227538e-05, | |
| "loss": 0.6341, | |
| "num_input_tokens_seen": 12164208, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.5382436260623229, | |
| "grad_norm": 5.0434906291132995, | |
| "learning_rate": 8.744943274483376e-05, | |
| "loss": 0.7189, | |
| "num_input_tokens_seen": 12222672, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.5408189544166881, | |
| "grad_norm": 4.3092898145567125, | |
| "learning_rate": 8.730795109484461e-05, | |
| "loss": 0.6914, | |
| "num_input_tokens_seen": 12281072, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5408189544166881, | |
| "eval_loss": 0.6824291348457336, | |
| "eval_runtime": 19.7949, | |
| "eval_samples_per_second": 3.031, | |
| "eval_steps_per_second": 0.758, | |
| "num_input_tokens_seen": 12281072, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5433942827710533, | |
| "grad_norm": 6.118699079738975, | |
| "learning_rate": 8.716579228029562e-05, | |
| "loss": 0.6567, | |
| "num_input_tokens_seen": 12339544, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.5459696111254185, | |
| "grad_norm": 10.911613071983485, | |
| "learning_rate": 8.702295888146548e-05, | |
| "loss": 0.6155, | |
| "num_input_tokens_seen": 12397992, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.5485449394797837, | |
| "grad_norm": 7.643873763070769, | |
| "learning_rate": 8.687945349087703e-05, | |
| "loss": 0.6029, | |
| "num_input_tokens_seen": 12456480, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.5511202678341488, | |
| "grad_norm": 8.136001935771205, | |
| "learning_rate": 8.673527871325022e-05, | |
| "loss": 0.6129, | |
| "num_input_tokens_seen": 12515000, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.553695596188514, | |
| "grad_norm": 11.244237678841547, | |
| "learning_rate": 8.659043716545485e-05, | |
| "loss": 0.6825, | |
| "num_input_tokens_seen": 12573504, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.5562709245428792, | |
| "grad_norm": 7.506618014617338, | |
| "learning_rate": 8.644493147646302e-05, | |
| "loss": 0.6828, | |
| "num_input_tokens_seen": 12632008, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.5588462528972444, | |
| "grad_norm": 6.1353619139783415, | |
| "learning_rate": 8.629876428730145e-05, | |
| "loss": 0.6286, | |
| "num_input_tokens_seen": 12690520, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.5614215812516096, | |
| "grad_norm": 4.639695384779573, | |
| "learning_rate": 8.615193825100355e-05, | |
| "loss": 0.6361, | |
| "num_input_tokens_seen": 12749032, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.5639969096059748, | |
| "grad_norm": 8.458071149567038, | |
| "learning_rate": 8.600445603256123e-05, | |
| "loss": 0.6087, | |
| "num_input_tokens_seen": 12807504, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "grad_norm": 7.622756865192901, | |
| "learning_rate": 8.585632030887658e-05, | |
| "loss": 0.5825, | |
| "num_input_tokens_seen": 12865992, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.56657223796034, | |
| "eval_loss": 0.6431913375854492, | |
| "eval_runtime": 19.2744, | |
| "eval_samples_per_second": 3.113, | |
| "eval_steps_per_second": 0.778, | |
| "num_input_tokens_seen": 12865992, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5691475663147051, | |
| "grad_norm": 23.7865505450662, | |
| "learning_rate": 8.57075337687132e-05, | |
| "loss": 0.6113, | |
| "num_input_tokens_seen": 12924448, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.5717228946690703, | |
| "grad_norm": 9.766678144472763, | |
| "learning_rate": 8.55580991126475e-05, | |
| "loss": 0.562, | |
| "num_input_tokens_seen": 12982912, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.5742982230234355, | |
| "grad_norm": 11.601294815310595, | |
| "learning_rate": 8.540801905301963e-05, | |
| "loss": 0.6124, | |
| "num_input_tokens_seen": 13041424, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.5768735513778007, | |
| "grad_norm": 14.728116727049585, | |
| "learning_rate": 8.525729631388421e-05, | |
| "loss": 0.6788, | |
| "num_input_tokens_seen": 13099888, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.5794488797321659, | |
| "grad_norm": 9.209119741223232, | |
| "learning_rate": 8.510593363096097e-05, | |
| "loss": 0.5904, | |
| "num_input_tokens_seen": 13158344, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.582024208086531, | |
| "grad_norm": 8.883499835719407, | |
| "learning_rate": 8.495393375158504e-05, | |
| "loss": 0.5433, | |
| "num_input_tokens_seen": 13216840, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.5845995364408962, | |
| "grad_norm": 10.675613755673567, | |
| "learning_rate": 8.480129943465709e-05, | |
| "loss": 0.5937, | |
| "num_input_tokens_seen": 13275328, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.5871748647952614, | |
| "grad_norm": 18.416876655689737, | |
| "learning_rate": 8.464803345059324e-05, | |
| "loss": 0.5785, | |
| "num_input_tokens_seen": 13333784, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.5897501931496266, | |
| "grad_norm": 7.2789290785005845, | |
| "learning_rate": 8.449413858127487e-05, | |
| "loss": 0.5472, | |
| "num_input_tokens_seen": 13392280, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.5923255215039918, | |
| "grad_norm": 7.9221272500905355, | |
| "learning_rate": 8.433961761999796e-05, | |
| "loss": 0.5228, | |
| "num_input_tokens_seen": 13450720, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5923255215039918, | |
| "eval_loss": 0.6229755282402039, | |
| "eval_runtime": 19.3811, | |
| "eval_samples_per_second": 3.096, | |
| "eval_steps_per_second": 0.774, | |
| "num_input_tokens_seen": 13450720, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5949008498583569, | |
| "grad_norm": 7.6504285821029265, | |
| "learning_rate": 8.418447337142254e-05, | |
| "loss": 0.5654, | |
| "num_input_tokens_seen": 13509200, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.5974761782127221, | |
| "grad_norm": 12.935585815436268, | |
| "learning_rate": 8.402870865152172e-05, | |
| "loss": 0.5074, | |
| "num_input_tokens_seen": 13567656, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.6000515065670873, | |
| "grad_norm": 11.833351794705523, | |
| "learning_rate": 8.387232628753056e-05, | |
| "loss": 0.6436, | |
| "num_input_tokens_seen": 13626136, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.6026268349214525, | |
| "grad_norm": 6.637170802158791, | |
| "learning_rate": 8.371532911789482e-05, | |
| "loss": 0.55, | |
| "num_input_tokens_seen": 13684608, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.6052021632758177, | |
| "grad_norm": 13.363715980324447, | |
| "learning_rate": 8.355771999221937e-05, | |
| "loss": 0.5399, | |
| "num_input_tokens_seen": 13743080, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.6077774916301828, | |
| "grad_norm": 14.735226460570393, | |
| "learning_rate": 8.339950177121647e-05, | |
| "loss": 0.5402, | |
| "num_input_tokens_seen": 13801552, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.610352819984548, | |
| "grad_norm": 15.934621739592105, | |
| "learning_rate": 8.324067732665393e-05, | |
| "loss": 0.5559, | |
| "num_input_tokens_seen": 13860064, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.6129281483389132, | |
| "grad_norm": 10.693551994820394, | |
| "learning_rate": 8.308124954130289e-05, | |
| "loss": 0.5619, | |
| "num_input_tokens_seen": 13918552, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.6155034766932784, | |
| "grad_norm": 12.596573646765963, | |
| "learning_rate": 8.292122130888558e-05, | |
| "loss": 0.5933, | |
| "num_input_tokens_seen": 13977056, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.6180788050476436, | |
| "grad_norm": 8.090399041458168, | |
| "learning_rate": 8.276059553402265e-05, | |
| "loss": 0.5078, | |
| "num_input_tokens_seen": 14035544, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6180788050476436, | |
| "eval_loss": 0.6184359192848206, | |
| "eval_runtime": 19.3097, | |
| "eval_samples_per_second": 3.107, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 14035544, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6206541334020087, | |
| "grad_norm": 5.625941133087891, | |
| "learning_rate": 8.259937513218066e-05, | |
| "loss": 0.5109, | |
| "num_input_tokens_seen": 14094024, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.623229461756374, | |
| "grad_norm": 11.892235969186327, | |
| "learning_rate": 8.243756302961898e-05, | |
| "loss": 0.4738, | |
| "num_input_tokens_seen": 14152504, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.6258047901107391, | |
| "grad_norm": 45.17960159223106, | |
| "learning_rate": 8.227516216333679e-05, | |
| "loss": 0.5615, | |
| "num_input_tokens_seen": 14210992, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.6283801184651043, | |
| "grad_norm": 14.930236962628644, | |
| "learning_rate": 8.211217548101973e-05, | |
| "loss": 0.5584, | |
| "num_input_tokens_seen": 14269488, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.6309554468194695, | |
| "grad_norm": 49.91459221869246, | |
| "learning_rate": 8.194860594098635e-05, | |
| "loss": 0.4856, | |
| "num_input_tokens_seen": 14327968, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.6335307751738347, | |
| "grad_norm": 14.899444451092219, | |
| "learning_rate": 8.17844565121345e-05, | |
| "loss": 0.5378, | |
| "num_input_tokens_seen": 14386448, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.6361061035281999, | |
| "grad_norm": 10.76781481162281, | |
| "learning_rate": 8.161973017388744e-05, | |
| "loss": 0.4484, | |
| "num_input_tokens_seen": 14444912, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.638681431882565, | |
| "grad_norm": 11.97619546639196, | |
| "learning_rate": 8.145442991613963e-05, | |
| "loss": 0.4772, | |
| "num_input_tokens_seen": 14503392, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.6412567602369302, | |
| "grad_norm": 12.878458794693833, | |
| "learning_rate": 8.128855873920265e-05, | |
| "loss": 0.5807, | |
| "num_input_tokens_seen": 14561872, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.6438320885912954, | |
| "grad_norm": 5.57738881271864, | |
| "learning_rate": 8.112211965375059e-05, | |
| "loss": 0.5268, | |
| "num_input_tokens_seen": 14620336, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6438320885912954, | |
| "eval_loss": 0.5496931672096252, | |
| "eval_runtime": 19.4472, | |
| "eval_samples_per_second": 3.085, | |
| "eval_steps_per_second": 0.771, | |
| "num_input_tokens_seen": 14620336, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6464074169456606, | |
| "grad_norm": 7.347855237786093, | |
| "learning_rate": 8.095511568076548e-05, | |
| "loss": 0.6012, | |
| "num_input_tokens_seen": 14678792, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.6489827453000258, | |
| "grad_norm": 9.779072667301502, | |
| "learning_rate": 8.078754985148247e-05, | |
| "loss": 0.5358, | |
| "num_input_tokens_seen": 14737272, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.6515580736543909, | |
| "grad_norm": 13.80618279187987, | |
| "learning_rate": 8.061942520733474e-05, | |
| "loss": 0.4676, | |
| "num_input_tokens_seen": 14795784, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.6541334020087561, | |
| "grad_norm": 10.954100508877262, | |
| "learning_rate": 8.045074479989838e-05, | |
| "loss": 0.489, | |
| "num_input_tokens_seen": 14854272, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.6567087303631213, | |
| "grad_norm": 9.330856277290438, | |
| "learning_rate": 8.02815116908369e-05, | |
| "loss": 0.4505, | |
| "num_input_tokens_seen": 14912720, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.6592840587174865, | |
| "grad_norm": 12.562590417573535, | |
| "learning_rate": 8.011172895184579e-05, | |
| "loss": 0.4987, | |
| "num_input_tokens_seen": 14971192, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.6618593870718517, | |
| "grad_norm": 13.11335003986863, | |
| "learning_rate": 7.994139966459664e-05, | |
| "loss": 0.5156, | |
| "num_input_tokens_seen": 15029656, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.6644347154262168, | |
| "grad_norm": 9.518625656710672, | |
| "learning_rate": 7.977052692068127e-05, | |
| "loss": 0.5266, | |
| "num_input_tokens_seen": 15088144, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.667010043780582, | |
| "grad_norm": 8.95720787325786, | |
| "learning_rate": 7.959911382155566e-05, | |
| "loss": 0.4502, | |
| "num_input_tokens_seen": 15146600, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.6695853721349472, | |
| "grad_norm": 11.65058483213029, | |
| "learning_rate": 7.942716347848353e-05, | |
| "loss": 0.4578, | |
| "num_input_tokens_seen": 15205064, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6695853721349472, | |
| "eval_loss": 0.49471279978752136, | |
| "eval_runtime": 19.2738, | |
| "eval_samples_per_second": 3.113, | |
| "eval_steps_per_second": 0.778, | |
| "num_input_tokens_seen": 15205064, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6721607004893124, | |
| "grad_norm": 10.254593495214214, | |
| "learning_rate": 7.925467901247996e-05, | |
| "loss": 0.4589, | |
| "num_input_tokens_seen": 15263560, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.6747360288436776, | |
| "grad_norm": 10.097755490465826, | |
| "learning_rate": 7.908166355425475e-05, | |
| "loss": 0.457, | |
| "num_input_tokens_seen": 15322016, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.6773113571980427, | |
| "grad_norm": 10.727169120741898, | |
| "learning_rate": 7.890812024415555e-05, | |
| "loss": 0.51, | |
| "num_input_tokens_seen": 15380504, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.6798866855524079, | |
| "grad_norm": 11.12869176509039, | |
| "learning_rate": 7.873405223211087e-05, | |
| "loss": 0.4994, | |
| "num_input_tokens_seen": 15438944, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.6824620139067731, | |
| "grad_norm": 8.499688286725998, | |
| "learning_rate": 7.855946267757295e-05, | |
| "loss": 0.4501, | |
| "num_input_tokens_seen": 15497384, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.6850373422611383, | |
| "grad_norm": 10.352066646699223, | |
| "learning_rate": 7.838435474946034e-05, | |
| "loss": 0.4807, | |
| "num_input_tokens_seen": 15555856, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.6876126706155035, | |
| "grad_norm": 14.714795422962215, | |
| "learning_rate": 7.820873162610044e-05, | |
| "loss": 0.5112, | |
| "num_input_tokens_seen": 15614368, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.6901879989698687, | |
| "grad_norm": 8.466874504995866, | |
| "learning_rate": 7.803259649517178e-05, | |
| "loss": 0.4825, | |
| "num_input_tokens_seen": 15672864, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.6927633273242338, | |
| "grad_norm": 7.62934190428385, | |
| "learning_rate": 7.78559525536462e-05, | |
| "loss": 0.5147, | |
| "num_input_tokens_seen": 15731376, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.695338655678599, | |
| "grad_norm": 9.019045929732858, | |
| "learning_rate": 7.767880300773074e-05, | |
| "loss": 0.4702, | |
| "num_input_tokens_seen": 15789848, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.695338655678599, | |
| "eval_loss": 0.5247787237167358, | |
| "eval_runtime": 19.436, | |
| "eval_samples_per_second": 3.087, | |
| "eval_steps_per_second": 0.772, | |
| "num_input_tokens_seen": 15789848, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6979139840329642, | |
| "grad_norm": 9.176622281786903, | |
| "learning_rate": 7.750115107280959e-05, | |
| "loss": 0.4601, | |
| "num_input_tokens_seen": 15848328, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.7004893123873294, | |
| "grad_norm": 13.657128530320302, | |
| "learning_rate": 7.732299997338557e-05, | |
| "loss": 0.4704, | |
| "num_input_tokens_seen": 15906824, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.7030646407416946, | |
| "grad_norm": 20.00043922120396, | |
| "learning_rate": 7.714435294302168e-05, | |
| "loss": 0.4937, | |
| "num_input_tokens_seen": 15965312, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.7056399690960597, | |
| "grad_norm": 10.050026656050768, | |
| "learning_rate": 7.696521322428245e-05, | |
| "loss": 0.4635, | |
| "num_input_tokens_seen": 16023824, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.7082152974504249, | |
| "grad_norm": 10.723911953770791, | |
| "learning_rate": 7.678558406867498e-05, | |
| "loss": 0.4421, | |
| "num_input_tokens_seen": 16082280, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.7107906258047901, | |
| "grad_norm": 8.12550455034103, | |
| "learning_rate": 7.660546873659e-05, | |
| "loss": 0.4823, | |
| "num_input_tokens_seen": 16140800, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.7133659541591553, | |
| "grad_norm": 9.105312428399467, | |
| "learning_rate": 7.642487049724271e-05, | |
| "loss": 0.4122, | |
| "num_input_tokens_seen": 16199320, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.7159412825135205, | |
| "grad_norm": 5.873152833761692, | |
| "learning_rate": 7.624379262861335e-05, | |
| "loss": 0.4372, | |
| "num_input_tokens_seen": 16257768, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.7185166108678857, | |
| "grad_norm": 10.07764587174093, | |
| "learning_rate": 7.606223841738775e-05, | |
| "loss": 0.4899, | |
| "num_input_tokens_seen": 16316264, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.7210919392222508, | |
| "grad_norm": 20.283363042209615, | |
| "learning_rate": 7.588021115889777e-05, | |
| "loss": 0.4294, | |
| "num_input_tokens_seen": 16374784, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7210919392222508, | |
| "eval_loss": 0.47318556904792786, | |
| "eval_runtime": 19.2484, | |
| "eval_samples_per_second": 3.117, | |
| "eval_steps_per_second": 0.779, | |
| "num_input_tokens_seen": 16374784, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.723667267576616, | |
| "grad_norm": 9.384799103772558, | |
| "learning_rate": 7.569771415706126e-05, | |
| "loss": 0.444, | |
| "num_input_tokens_seen": 16433288, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.7262425959309812, | |
| "grad_norm": 16.840151224890615, | |
| "learning_rate": 7.551475072432237e-05, | |
| "loss": 0.4971, | |
| "num_input_tokens_seen": 16491784, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.7288179242853464, | |
| "grad_norm": 10.190076716766358, | |
| "learning_rate": 7.533132418159119e-05, | |
| "loss": 0.4284, | |
| "num_input_tokens_seen": 16550272, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.7313932526397116, | |
| "grad_norm": 7.663975666748285, | |
| "learning_rate": 7.514743785818361e-05, | |
| "loss": 0.414, | |
| "num_input_tokens_seen": 16608704, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.7339685809940767, | |
| "grad_norm": 7.403751704217463, | |
| "learning_rate": 7.496309509176082e-05, | |
| "loss": 0.3715, | |
| "num_input_tokens_seen": 16667200, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.7365439093484419, | |
| "grad_norm": 15.05075115467088, | |
| "learning_rate": 7.477829922826883e-05, | |
| "loss": 0.4723, | |
| "num_input_tokens_seen": 16725704, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.7391192377028071, | |
| "grad_norm": 8.817475778915243, | |
| "learning_rate": 7.459305362187756e-05, | |
| "loss": 0.4357, | |
| "num_input_tokens_seen": 16784192, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.7416945660571723, | |
| "grad_norm": 14.070137984729548, | |
| "learning_rate": 7.440736163492016e-05, | |
| "loss": 0.4402, | |
| "num_input_tokens_seen": 16842704, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.7442698944115375, | |
| "grad_norm": 14.494333760708628, | |
| "learning_rate": 7.422122663783187e-05, | |
| "loss": 0.4457, | |
| "num_input_tokens_seen": 16901176, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.7468452227659027, | |
| "grad_norm": 8.298786058991697, | |
| "learning_rate": 7.403465200908883e-05, | |
| "loss": 0.4353, | |
| "num_input_tokens_seen": 16959632, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7468452227659027, | |
| "eval_loss": 0.43503889441490173, | |
| "eval_runtime": 19.5652, | |
| "eval_samples_per_second": 3.067, | |
| "eval_steps_per_second": 0.767, | |
| "num_input_tokens_seen": 16959632, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7494205511202678, | |
| "grad_norm": 8.48162757316697, | |
| "learning_rate": 7.38476411351468e-05, | |
| "loss": 0.4183, | |
| "num_input_tokens_seen": 17018072, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.751995879474633, | |
| "grad_norm": 6.408395141132007, | |
| "learning_rate": 7.366019741037973e-05, | |
| "loss": 0.4632, | |
| "num_input_tokens_seen": 17076560, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.7545712078289982, | |
| "grad_norm": 8.824594003357785, | |
| "learning_rate": 7.347232423701804e-05, | |
| "loss": 0.4512, | |
| "num_input_tokens_seen": 17135016, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.7571465361833634, | |
| "grad_norm": 6.923088148907062, | |
| "learning_rate": 7.328402502508701e-05, | |
| "loss": 0.4121, | |
| "num_input_tokens_seen": 17193496, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.7597218645377286, | |
| "grad_norm": 7.015139822100635, | |
| "learning_rate": 7.309530319234472e-05, | |
| "loss": 0.5234, | |
| "num_input_tokens_seen": 17251944, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.7622971928920937, | |
| "grad_norm": 9.64129523887212, | |
| "learning_rate": 7.290616216422017e-05, | |
| "loss": 0.3895, | |
| "num_input_tokens_seen": 17310456, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.7648725212464589, | |
| "grad_norm": 10.31264909937419, | |
| "learning_rate": 7.271660537375102e-05, | |
| "loss": 0.3641, | |
| "num_input_tokens_seen": 17368968, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.7674478496008241, | |
| "grad_norm": 12.820424037076199, | |
| "learning_rate": 7.25266362615213e-05, | |
| "loss": 0.3867, | |
| "num_input_tokens_seen": 17427424, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.7700231779551893, | |
| "grad_norm": 19.961448856074927, | |
| "learning_rate": 7.233625827559893e-05, | |
| "loss": 0.3214, | |
| "num_input_tokens_seen": 17485936, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.7725985063095545, | |
| "grad_norm": 7.797571046303324, | |
| "learning_rate": 7.21454748714732e-05, | |
| "loss": 0.3369, | |
| "num_input_tokens_seen": 17544440, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7725985063095545, | |
| "eval_loss": 0.3963810205459595, | |
| "eval_runtime": 19.2433, | |
| "eval_samples_per_second": 3.118, | |
| "eval_steps_per_second": 0.779, | |
| "num_input_tokens_seen": 17544440, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7751738346639196, | |
| "grad_norm": 10.358996803929989, | |
| "learning_rate": 7.195428951199204e-05, | |
| "loss": 0.3397, | |
| "num_input_tokens_seen": 17602952, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.7777491630182848, | |
| "grad_norm": 11.954413440576635, | |
| "learning_rate": 7.176270566729904e-05, | |
| "loss": 0.5039, | |
| "num_input_tokens_seen": 17661440, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.78032449137265, | |
| "grad_norm": 15.247523980815545, | |
| "learning_rate": 7.157072681477069e-05, | |
| "loss": 0.426, | |
| "num_input_tokens_seen": 17719928, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.7828998197270152, | |
| "grad_norm": 11.560314722738736, | |
| "learning_rate": 7.137835643895305e-05, | |
| "loss": 0.3587, | |
| "num_input_tokens_seen": 17778424, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.7854751480813804, | |
| "grad_norm": 9.214361802688169, | |
| "learning_rate": 7.118559803149865e-05, | |
| "loss": 0.4849, | |
| "num_input_tokens_seen": 17836936, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.7880504764357456, | |
| "grad_norm": 9.825924936343675, | |
| "learning_rate": 7.099245509110299e-05, | |
| "loss": 0.3795, | |
| "num_input_tokens_seen": 17895392, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.7906258047901107, | |
| "grad_norm": 28.893219975863104, | |
| "learning_rate": 7.079893112344118e-05, | |
| "loss": 0.4206, | |
| "num_input_tokens_seen": 17953872, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.7932011331444759, | |
| "grad_norm": 9.96463686082691, | |
| "learning_rate": 7.060502964110418e-05, | |
| "loss": 0.3567, | |
| "num_input_tokens_seen": 18012320, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.7957764614988411, | |
| "grad_norm": 16.21585017609129, | |
| "learning_rate": 7.041075416353513e-05, | |
| "loss": 0.4172, | |
| "num_input_tokens_seen": 18070792, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.7983517898532063, | |
| "grad_norm": 7.729155059823011, | |
| "learning_rate": 7.02161082169654e-05, | |
| "loss": 0.4666, | |
| "num_input_tokens_seen": 18129304, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7983517898532063, | |
| "eval_loss": 0.42660555243492126, | |
| "eval_runtime": 19.4313, | |
| "eval_samples_per_second": 3.088, | |
| "eval_steps_per_second": 0.772, | |
| "num_input_tokens_seen": 18129304, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.8009271182075715, | |
| "grad_norm": 6.105522334359041, | |
| "learning_rate": 7.002109533435066e-05, | |
| "loss": 0.4305, | |
| "num_input_tokens_seen": 18187728, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.8035024465619367, | |
| "grad_norm": 7.852746488368037, | |
| "learning_rate": 6.982571905530669e-05, | |
| "loss": 0.4529, | |
| "num_input_tokens_seen": 18246192, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.8060777749163018, | |
| "grad_norm": 5.8884808032636275, | |
| "learning_rate": 6.962998292604517e-05, | |
| "loss": 0.4569, | |
| "num_input_tokens_seen": 18304632, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.808653103270667, | |
| "grad_norm": 8.738504630489588, | |
| "learning_rate": 6.943389049930931e-05, | |
| "loss": 0.3936, | |
| "num_input_tokens_seen": 18363136, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.8112284316250322, | |
| "grad_norm": 8.410645723765466, | |
| "learning_rate": 6.923744533430937e-05, | |
| "loss": 0.4083, | |
| "num_input_tokens_seen": 18421592, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.8138037599793974, | |
| "grad_norm": 7.654296364994705, | |
| "learning_rate": 6.904065099665803e-05, | |
| "loss": 0.4564, | |
| "num_input_tokens_seen": 18480104, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.8163790883337626, | |
| "grad_norm": 17.3461741974751, | |
| "learning_rate": 6.884351105830568e-05, | |
| "loss": 0.3928, | |
| "num_input_tokens_seen": 18538600, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.8189544166881277, | |
| "grad_norm": 16.63308936698189, | |
| "learning_rate": 6.864602909747563e-05, | |
| "loss": 0.4278, | |
| "num_input_tokens_seen": 18597104, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.8215297450424929, | |
| "grad_norm": 10.83446543348463, | |
| "learning_rate": 6.84482086985991e-05, | |
| "loss": 0.3956, | |
| "num_input_tokens_seen": 18655584, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.8241050733968581, | |
| "grad_norm": 7.98539427128297, | |
| "learning_rate": 6.825005345225019e-05, | |
| "loss": 0.3834, | |
| "num_input_tokens_seen": 18714072, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8241050733968581, | |
| "eval_loss": 0.44774264097213745, | |
| "eval_runtime": 19.316, | |
| "eval_samples_per_second": 3.106, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 18714072, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8266804017512233, | |
| "grad_norm": 6.7599286769908815, | |
| "learning_rate": 6.805156695508075e-05, | |
| "loss": 0.4136, | |
| "num_input_tokens_seen": 18772552, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.8292557301055885, | |
| "grad_norm": 5.6959660380818, | |
| "learning_rate": 6.7852752809755e-05, | |
| "loss": 0.3523, | |
| "num_input_tokens_seen": 18830992, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.8318310584599536, | |
| "grad_norm": 5.054175814859553, | |
| "learning_rate": 6.765361462488424e-05, | |
| "loss": 0.2983, | |
| "num_input_tokens_seen": 18889480, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.8344063868143188, | |
| "grad_norm": 8.9830923866359, | |
| "learning_rate": 6.745415601496127e-05, | |
| "loss": 0.3987, | |
| "num_input_tokens_seen": 18947936, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.836981715168684, | |
| "grad_norm": 9.543713321488678, | |
| "learning_rate": 6.725438060029485e-05, | |
| "loss": 0.5012, | |
| "num_input_tokens_seen": 19006432, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.8395570435230492, | |
| "grad_norm": 9.329917566254677, | |
| "learning_rate": 6.705429200694396e-05, | |
| "loss": 0.36, | |
| "num_input_tokens_seen": 19064920, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.8421323718774144, | |
| "grad_norm": 4.257164474078224, | |
| "learning_rate": 6.685389386665197e-05, | |
| "loss": 0.3816, | |
| "num_input_tokens_seen": 19123376, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.8447077002317795, | |
| "grad_norm": 5.420005475317537, | |
| "learning_rate": 6.665318981678072e-05, | |
| "loss": 0.3503, | |
| "num_input_tokens_seen": 19181864, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.8472830285861447, | |
| "grad_norm": 6.544911058180563, | |
| "learning_rate": 6.645218350024456e-05, | |
| "loss": 0.3644, | |
| "num_input_tokens_seen": 19240352, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.8498583569405099, | |
| "grad_norm": 9.593843549483235, | |
| "learning_rate": 6.625087856544416e-05, | |
| "loss": 0.475, | |
| "num_input_tokens_seen": 19298848, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8498583569405099, | |
| "eval_loss": 0.35129043459892273, | |
| "eval_runtime": 19.4001, | |
| "eval_samples_per_second": 3.093, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 19298848, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8524336852948751, | |
| "grad_norm": 6.358459669534092, | |
| "learning_rate": 6.604927866620031e-05, | |
| "loss": 0.3414, | |
| "num_input_tokens_seen": 19357304, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.8550090136492403, | |
| "grad_norm": 9.39994214990231, | |
| "learning_rate": 6.584738746168762e-05, | |
| "loss": 0.4728, | |
| "num_input_tokens_seen": 19415800, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.8575843420036054, | |
| "grad_norm": 14.50676995208697, | |
| "learning_rate": 6.564520861636808e-05, | |
| "loss": 0.4264, | |
| "num_input_tokens_seen": 19474256, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.8601596703579707, | |
| "grad_norm": 4.791356534368335, | |
| "learning_rate": 6.544274579992453e-05, | |
| "loss": 0.4038, | |
| "num_input_tokens_seen": 19532736, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.8627349987123358, | |
| "grad_norm": 6.4285821594117225, | |
| "learning_rate": 6.524000268719411e-05, | |
| "loss": 0.3241, | |
| "num_input_tokens_seen": 19591184, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.865310327066701, | |
| "grad_norm": 8.268794944409354, | |
| "learning_rate": 6.503698295810154e-05, | |
| "loss": 0.3248, | |
| "num_input_tokens_seen": 19649656, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.8678856554210662, | |
| "grad_norm": 12.365745303187085, | |
| "learning_rate": 6.483369029759229e-05, | |
| "loss": 0.4295, | |
| "num_input_tokens_seen": 19708144, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.8704609837754314, | |
| "grad_norm": 6.3136571538884505, | |
| "learning_rate": 6.463012839556569e-05, | |
| "loss": 0.3785, | |
| "num_input_tokens_seen": 19766592, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.8730363121297966, | |
| "grad_norm": 6.1513513385401195, | |
| "learning_rate": 6.442630094680805e-05, | |
| "loss": 0.3376, | |
| "num_input_tokens_seen": 19825064, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.8756116404841617, | |
| "grad_norm": 9.59752445262446, | |
| "learning_rate": 6.42222116509255e-05, | |
| "loss": 0.3752, | |
| "num_input_tokens_seen": 19883504, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8756116404841617, | |
| "eval_loss": 0.34382957220077515, | |
| "eval_runtime": 19.3987, | |
| "eval_samples_per_second": 3.093, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 19883504, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8781869688385269, | |
| "grad_norm": 18.837461373103466, | |
| "learning_rate": 6.401786421227686e-05, | |
| "loss": 0.3453, | |
| "num_input_tokens_seen": 19942000, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.8807622971928921, | |
| "grad_norm": 10.315591123527769, | |
| "learning_rate": 6.381326233990644e-05, | |
| "loss": 0.3278, | |
| "num_input_tokens_seen": 20000440, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.8833376255472573, | |
| "grad_norm": 14.473376988028903, | |
| "learning_rate": 6.360840974747666e-05, | |
| "loss": 0.3695, | |
| "num_input_tokens_seen": 20058920, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.8859129539016225, | |
| "grad_norm": 13.569903569955356, | |
| "learning_rate": 6.340331015320073e-05, | |
| "loss": 0.4362, | |
| "num_input_tokens_seen": 20117416, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.8884882822559876, | |
| "grad_norm": 8.610173422350266, | |
| "learning_rate": 6.319796727977509e-05, | |
| "loss": 0.3178, | |
| "num_input_tokens_seen": 20175936, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.8910636106103528, | |
| "grad_norm": 13.406485921668688, | |
| "learning_rate": 6.299238485431183e-05, | |
| "loss": 0.3679, | |
| "num_input_tokens_seen": 20234368, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.893638938964718, | |
| "grad_norm": 10.15746393869747, | |
| "learning_rate": 6.27865666082711e-05, | |
| "loss": 0.3529, | |
| "num_input_tokens_seen": 20292856, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.8962142673190832, | |
| "grad_norm": 6.0390850533631, | |
| "learning_rate": 6.258051627739337e-05, | |
| "loss": 0.281, | |
| "num_input_tokens_seen": 20351272, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.8987895956734484, | |
| "grad_norm": 11.746443511207032, | |
| "learning_rate": 6.237423760163156e-05, | |
| "loss": 0.3148, | |
| "num_input_tokens_seen": 20409744, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.9013649240278135, | |
| "grad_norm": 23.680917449871366, | |
| "learning_rate": 6.216773432508325e-05, | |
| "loss": 0.3233, | |
| "num_input_tokens_seen": 20468200, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.9013649240278135, | |
| "eval_loss": 0.3325226604938507, | |
| "eval_runtime": 19.3673, | |
| "eval_samples_per_second": 3.098, | |
| "eval_steps_per_second": 0.775, | |
| "num_input_tokens_seen": 20468200, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.9039402523821787, | |
| "grad_norm": 10.184672332401709, | |
| "learning_rate": 6.196101019592264e-05, | |
| "loss": 0.3731, | |
| "num_input_tokens_seen": 20526696, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.9065155807365439, | |
| "grad_norm": 14.226563654043238, | |
| "learning_rate": 6.175406896633258e-05, | |
| "loss": 0.3092, | |
| "num_input_tokens_seen": 20585160, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 16.003520349130227, | |
| "learning_rate": 6.154691439243644e-05, | |
| "loss": 0.311, | |
| "num_input_tokens_seen": 20643672, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.9116662374452743, | |
| "grad_norm": 13.517061006658674, | |
| "learning_rate": 6.133955023422991e-05, | |
| "loss": 0.3085, | |
| "num_input_tokens_seen": 20702152, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.9142415657996394, | |
| "grad_norm": 12.015661764026639, | |
| "learning_rate": 6.11319802555128e-05, | |
| "loss": 0.3236, | |
| "num_input_tokens_seen": 20760664, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.9168168941540046, | |
| "grad_norm": 11.503732085983884, | |
| "learning_rate": 6.092420822382069e-05, | |
| "loss": 0.4067, | |
| "num_input_tokens_seen": 20819144, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.9193922225083698, | |
| "grad_norm": 24.85467047869542, | |
| "learning_rate": 6.071623791035657e-05, | |
| "loss": 0.3228, | |
| "num_input_tokens_seen": 20877624, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.921967550862735, | |
| "grad_norm": 7.500048546411068, | |
| "learning_rate": 6.050807308992234e-05, | |
| "loss": 0.2672, | |
| "num_input_tokens_seen": 20936112, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.9245428792171002, | |
| "grad_norm": 7.916795517296481, | |
| "learning_rate": 6.02997175408504e-05, | |
| "loss": 0.3308, | |
| "num_input_tokens_seen": 20994608, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.9271182075714653, | |
| "grad_norm": 13.438136619817039, | |
| "learning_rate": 6.009117504493493e-05, | |
| "loss": 0.3279, | |
| "num_input_tokens_seen": 21053080, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9271182075714653, | |
| "eval_loss": 0.3501794636249542, | |
| "eval_runtime": 19.2844, | |
| "eval_samples_per_second": 3.111, | |
| "eval_steps_per_second": 0.778, | |
| "num_input_tokens_seen": 21053080, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9296935359258306, | |
| "grad_norm": 10.926380171957325, | |
| "learning_rate": 5.98824493873634e-05, | |
| "loss": 0.3107, | |
| "num_input_tokens_seen": 21111592, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.9322688642801957, | |
| "grad_norm": 9.204735754102403, | |
| "learning_rate": 5.9673544356647706e-05, | |
| "loss": 0.3453, | |
| "num_input_tokens_seen": 21170024, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.9348441926345609, | |
| "grad_norm": 10.122487159211746, | |
| "learning_rate": 5.946446374455555e-05, | |
| "loss": 0.3607, | |
| "num_input_tokens_seen": 21228480, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.9374195209889261, | |
| "grad_norm": 9.590674638217761, | |
| "learning_rate": 5.9255211346041526e-05, | |
| "loss": 0.3375, | |
| "num_input_tokens_seen": 21286944, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.9399948493432912, | |
| "grad_norm": 5.469697379095751, | |
| "learning_rate": 5.9045790959178296e-05, | |
| "loss": 0.2521, | |
| "num_input_tokens_seen": 21345456, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.9425701776976565, | |
| "grad_norm": 12.20617548886948, | |
| "learning_rate": 5.883620638508756e-05, | |
| "loss": 0.3855, | |
| "num_input_tokens_seen": 21403896, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.9451455060520216, | |
| "grad_norm": 12.862485307076343, | |
| "learning_rate": 5.8626461427871204e-05, | |
| "loss": 0.2947, | |
| "num_input_tokens_seen": 21462360, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.9477208344063868, | |
| "grad_norm": 15.353261731205423, | |
| "learning_rate": 5.841655989454213e-05, | |
| "loss": 0.4505, | |
| "num_input_tokens_seen": 21520864, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.950296162760752, | |
| "grad_norm": 9.642536812282682, | |
| "learning_rate": 5.820650559495523e-05, | |
| "loss": 0.3758, | |
| "num_input_tokens_seen": 21579376, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.9528714911151172, | |
| "grad_norm": 9.811875826616257, | |
| "learning_rate": 5.7996302341738164e-05, | |
| "loss": 0.3221, | |
| "num_input_tokens_seen": 21637848, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9528714911151172, | |
| "eval_loss": 0.2935050129890442, | |
| "eval_runtime": 19.4702, | |
| "eval_samples_per_second": 3.082, | |
| "eval_steps_per_second": 0.77, | |
| "num_input_tokens_seen": 21637848, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9554468194694824, | |
| "grad_norm": 11.793922029031792, | |
| "learning_rate": 5.778595395022226e-05, | |
| "loss": 0.4205, | |
| "num_input_tokens_seen": 21696328, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.9580221478238475, | |
| "grad_norm": 7.242120499330675, | |
| "learning_rate": 5.757546423837314e-05, | |
| "loss": 0.3075, | |
| "num_input_tokens_seen": 21754816, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.9605974761782127, | |
| "grad_norm": 15.811484589504676, | |
| "learning_rate": 5.736483702672155e-05, | |
| "loss": 0.2604, | |
| "num_input_tokens_seen": 21813296, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.9631728045325779, | |
| "grad_norm": 13.712784450465344, | |
| "learning_rate": 5.7154076138293914e-05, | |
| "loss": 0.342, | |
| "num_input_tokens_seen": 21871800, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.9657481328869431, | |
| "grad_norm": 7.941289555505942, | |
| "learning_rate": 5.694318539854297e-05, | |
| "loss": 0.411, | |
| "num_input_tokens_seen": 21930272, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.9683234612413083, | |
| "grad_norm": 13.422362176081661, | |
| "learning_rate": 5.673216863527836e-05, | |
| "loss": 0.2606, | |
| "num_input_tokens_seen": 21988736, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.9708987895956734, | |
| "grad_norm": 3.5902749610502247, | |
| "learning_rate": 5.652102967859715e-05, | |
| "loss": 0.2647, | |
| "num_input_tokens_seen": 22047200, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.9734741179500386, | |
| "grad_norm": 10.785857611570844, | |
| "learning_rate": 5.6309772360814295e-05, | |
| "loss": 0.2961, | |
| "num_input_tokens_seen": 22105664, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.9760494463044038, | |
| "grad_norm": 12.758145270494738, | |
| "learning_rate": 5.6098400516393065e-05, | |
| "loss": 0.2776, | |
| "num_input_tokens_seen": 22164184, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.978624774658769, | |
| "grad_norm": 9.907554223635353, | |
| "learning_rate": 5.5886917981875485e-05, | |
| "loss": 0.3781, | |
| "num_input_tokens_seen": 22222632, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.978624774658769, | |
| "eval_loss": 0.297338604927063, | |
| "eval_runtime": 19.4745, | |
| "eval_samples_per_second": 3.081, | |
| "eval_steps_per_second": 0.77, | |
| "num_input_tokens_seen": 22222632, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9812001030131342, | |
| "grad_norm": 8.000918034870224, | |
| "learning_rate": 5.567532859581267e-05, | |
| "loss": 0.2966, | |
| "num_input_tokens_seen": 22281080, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.9837754313674993, | |
| "grad_norm": 7.463040505678827, | |
| "learning_rate": 5.5463636198695166e-05, | |
| "loss": 0.304, | |
| "num_input_tokens_seen": 22339552, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.9863507597218646, | |
| "grad_norm": 8.329553137160708, | |
| "learning_rate": 5.5251844632883244e-05, | |
| "loss": 0.3534, | |
| "num_input_tokens_seen": 22398056, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.9889260880762297, | |
| "grad_norm": 6.690575164415027, | |
| "learning_rate": 5.503995774253714e-05, | |
| "loss": 0.319, | |
| "num_input_tokens_seen": 22456520, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.9915014164305949, | |
| "grad_norm": 6.058967141203479, | |
| "learning_rate": 5.482797937354731e-05, | |
| "loss": 0.312, | |
| "num_input_tokens_seen": 22515024, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.9940767447849601, | |
| "grad_norm": 6.871005440128773, | |
| "learning_rate": 5.461591337346461e-05, | |
| "loss": 0.3001, | |
| "num_input_tokens_seen": 22573480, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.9966520731393252, | |
| "grad_norm": 7.544493120290949, | |
| "learning_rate": 5.4403763591430436e-05, | |
| "loss": 0.2938, | |
| "num_input_tokens_seen": 22631960, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.9992274014936905, | |
| "grad_norm": 7.715734053518216, | |
| "learning_rate": 5.419153387810693e-05, | |
| "loss": 0.3429, | |
| "num_input_tokens_seen": 22690432, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.001545197012619, | |
| "grad_norm": 18.765317639079587, | |
| "learning_rate": 5.397922808560698e-05, | |
| "loss": 0.292, | |
| "num_input_tokens_seen": 22743048, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 1.0041205253669843, | |
| "grad_norm": 7.403981126755249, | |
| "learning_rate": 5.376685006742441e-05, | |
| "loss": 0.2845, | |
| "num_input_tokens_seen": 22801512, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.0041205253669843, | |
| "eval_loss": 0.2472737729549408, | |
| "eval_runtime": 19.468, | |
| "eval_samples_per_second": 3.082, | |
| "eval_steps_per_second": 0.77, | |
| "num_input_tokens_seen": 22801512, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.0066958537213495, | |
| "grad_norm": 9.441611539164802, | |
| "learning_rate": 5.355440367836396e-05, | |
| "loss": 0.278, | |
| "num_input_tokens_seen": 22859952, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 1.0092711820757148, | |
| "grad_norm": 13.17108131671136, | |
| "learning_rate": 5.334189277447138e-05, | |
| "loss": 0.3433, | |
| "num_input_tokens_seen": 22918440, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.0118465104300798, | |
| "grad_norm": 6.702666612997951, | |
| "learning_rate": 5.312932121296339e-05, | |
| "loss": 0.2929, | |
| "num_input_tokens_seen": 22976944, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 1.014421838784445, | |
| "grad_norm": 8.293945652706178, | |
| "learning_rate": 5.291669285215766e-05, | |
| "loss": 0.2804, | |
| "num_input_tokens_seen": 23035408, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.0169971671388103, | |
| "grad_norm": 9.067903045446336, | |
| "learning_rate": 5.270401155140284e-05, | |
| "loss": 0.2583, | |
| "num_input_tokens_seen": 23093912, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.0195724954931753, | |
| "grad_norm": 6.0243656792037905, | |
| "learning_rate": 5.2491281171008476e-05, | |
| "loss": 0.3232, | |
| "num_input_tokens_seen": 23152344, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.0221478238475405, | |
| "grad_norm": 11.796220731230777, | |
| "learning_rate": 5.227850557217494e-05, | |
| "loss": 0.2935, | |
| "num_input_tokens_seen": 23210800, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 1.0247231522019058, | |
| "grad_norm": 12.531746818475774, | |
| "learning_rate": 5.2065688616923314e-05, | |
| "loss": 0.2677, | |
| "num_input_tokens_seen": 23269304, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.0272984805562708, | |
| "grad_norm": 12.674176291351744, | |
| "learning_rate": 5.185283416802539e-05, | |
| "loss": 0.2697, | |
| "num_input_tokens_seen": 23327800, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 1.029873808910636, | |
| "grad_norm": 9.205507664261733, | |
| "learning_rate": 5.1639946088933444e-05, | |
| "loss": 0.2272, | |
| "num_input_tokens_seen": 23386232, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.029873808910636, | |
| "eval_loss": 0.2834003269672394, | |
| "eval_runtime": 19.4052, | |
| "eval_samples_per_second": 3.092, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 23386232, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0324491372650013, | |
| "grad_norm": 11.997812805404342, | |
| "learning_rate": 5.1427028243710174e-05, | |
| "loss": 0.2455, | |
| "num_input_tokens_seen": 23444712, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 1.0350244656193666, | |
| "grad_norm": 5.4126484214019825, | |
| "learning_rate": 5.121408449695856e-05, | |
| "loss": 0.268, | |
| "num_input_tokens_seen": 23503192, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.0375997939737316, | |
| "grad_norm": 9.189153902836047, | |
| "learning_rate": 5.100111871375173e-05, | |
| "loss": 0.2721, | |
| "num_input_tokens_seen": 23561688, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 1.0401751223280968, | |
| "grad_norm": 13.140777565626072, | |
| "learning_rate": 5.078813475956276e-05, | |
| "loss": 0.3521, | |
| "num_input_tokens_seen": 23620160, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.042750450682462, | |
| "grad_norm": 12.09033726574419, | |
| "learning_rate": 5.057513650019452e-05, | |
| "loss": 0.3624, | |
| "num_input_tokens_seen": 23678624, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.045325779036827, | |
| "grad_norm": 16.274994870434952, | |
| "learning_rate": 5.0362127801709614e-05, | |
| "loss": 0.2742, | |
| "num_input_tokens_seen": 23737064, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.0479011073911924, | |
| "grad_norm": 7.84210743850582, | |
| "learning_rate": 5.014911253036004e-05, | |
| "loss": 0.3377, | |
| "num_input_tokens_seen": 23795568, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 1.0504764357455576, | |
| "grad_norm": 14.343911569057362, | |
| "learning_rate": 4.993609455251713e-05, | |
| "loss": 0.3059, | |
| "num_input_tokens_seen": 23854040, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.0530517640999228, | |
| "grad_norm": 13.491088361277422, | |
| "learning_rate": 4.972307773460133e-05, | |
| "loss": 0.2534, | |
| "num_input_tokens_seen": 23912520, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 1.0556270924542879, | |
| "grad_norm": 6.573215232214223, | |
| "learning_rate": 4.9510065943012076e-05, | |
| "loss": 0.2924, | |
| "num_input_tokens_seen": 23971048, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.0556270924542879, | |
| "eval_loss": 0.2703675329685211, | |
| "eval_runtime": 19.3939, | |
| "eval_samples_per_second": 3.094, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 23971048, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.0582024208086531, | |
| "grad_norm": 11.207729973488336, | |
| "learning_rate": 4.929706304405748e-05, | |
| "loss": 0.217, | |
| "num_input_tokens_seen": 24029544, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 1.0607777491630184, | |
| "grad_norm": 10.285736762582813, | |
| "learning_rate": 4.9084072903884345e-05, | |
| "loss": 0.2132, | |
| "num_input_tokens_seen": 24088008, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.0633530775173834, | |
| "grad_norm": 6.469754305471942, | |
| "learning_rate": 4.887109938840783e-05, | |
| "loss": 0.2438, | |
| "num_input_tokens_seen": 24146480, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 1.0659284058717486, | |
| "grad_norm": 7.546288384087562, | |
| "learning_rate": 4.8658146363241406e-05, | |
| "loss": 0.2623, | |
| "num_input_tokens_seen": 24204984, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.0685037342261139, | |
| "grad_norm": 4.658066041307915, | |
| "learning_rate": 4.844521769362654e-05, | |
| "loss": 0.2041, | |
| "num_input_tokens_seen": 24263456, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.071079062580479, | |
| "grad_norm": 6.232031131112278, | |
| "learning_rate": 4.823231724436271e-05, | |
| "loss": 0.246, | |
| "num_input_tokens_seen": 24321960, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.0736543909348442, | |
| "grad_norm": 10.347547308861373, | |
| "learning_rate": 4.801944887973714e-05, | |
| "loss": 0.2857, | |
| "num_input_tokens_seen": 24380464, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 1.0762297192892094, | |
| "grad_norm": 7.357894649180612, | |
| "learning_rate": 4.7806616463454715e-05, | |
| "loss": 0.2577, | |
| "num_input_tokens_seen": 24438976, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.0788050476435747, | |
| "grad_norm": 9.485170393194913, | |
| "learning_rate": 4.759382385856779e-05, | |
| "loss": 0.2523, | |
| "num_input_tokens_seen": 24497448, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 1.0813803759979397, | |
| "grad_norm": 6.0022045554501045, | |
| "learning_rate": 4.738107492740619e-05, | |
| "loss": 0.2805, | |
| "num_input_tokens_seen": 24555904, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.0813803759979397, | |
| "eval_loss": 0.3205481469631195, | |
| "eval_runtime": 19.3676, | |
| "eval_samples_per_second": 3.098, | |
| "eval_steps_per_second": 0.774, | |
| "num_input_tokens_seen": 24555904, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.083955704352305, | |
| "grad_norm": 10.785937986790138, | |
| "learning_rate": 4.716837353150695e-05, | |
| "loss": 0.2942, | |
| "num_input_tokens_seen": 24614392, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 1.0865310327066702, | |
| "grad_norm": 7.201431051550072, | |
| "learning_rate": 4.695572353154438e-05, | |
| "loss": 0.2357, | |
| "num_input_tokens_seen": 24672848, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.0891063610610352, | |
| "grad_norm": 10.470411807057468, | |
| "learning_rate": 4.674312878725985e-05, | |
| "loss": 0.2476, | |
| "num_input_tokens_seen": 24731344, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 1.0916816894154004, | |
| "grad_norm": 10.029698195020993, | |
| "learning_rate": 4.653059315739188e-05, | |
| "loss": 0.3875, | |
| "num_input_tokens_seen": 24789832, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.0942570177697657, | |
| "grad_norm": 5.623217865601237, | |
| "learning_rate": 4.631812049960595e-05, | |
| "loss": 0.3313, | |
| "num_input_tokens_seen": 24848264, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.0968323461241307, | |
| "grad_norm": 4.705669392169022, | |
| "learning_rate": 4.61057146704246e-05, | |
| "loss": 0.2385, | |
| "num_input_tokens_seen": 24906744, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.099407674478496, | |
| "grad_norm": 9.334998248379781, | |
| "learning_rate": 4.589337952515736e-05, | |
| "loss": 0.2478, | |
| "num_input_tokens_seen": 24965256, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 1.1019830028328612, | |
| "grad_norm": 8.45475259780102, | |
| "learning_rate": 4.5681118917830835e-05, | |
| "loss": 0.214, | |
| "num_input_tokens_seen": 25023768, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.1045583311872265, | |
| "grad_norm": 23.234169875193494, | |
| "learning_rate": 4.546893670111866e-05, | |
| "loss": 0.2806, | |
| "num_input_tokens_seen": 25082248, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 1.1071336595415915, | |
| "grad_norm": 7.852580632471935, | |
| "learning_rate": 4.525683672627168e-05, | |
| "loss": 0.2536, | |
| "num_input_tokens_seen": 25140752, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.1071336595415915, | |
| "eval_loss": 0.30806976556777954, | |
| "eval_runtime": 19.3086, | |
| "eval_samples_per_second": 3.107, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 25140752, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.1097089878959567, | |
| "grad_norm": 25.69995406882716, | |
| "learning_rate": 4.504482284304795e-05, | |
| "loss": 0.2318, | |
| "num_input_tokens_seen": 25199208, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 1.112284316250322, | |
| "grad_norm": 7.248312268680657, | |
| "learning_rate": 4.4832898899642974e-05, | |
| "loss": 0.2371, | |
| "num_input_tokens_seen": 25257680, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.114859644604687, | |
| "grad_norm": 5.020751335158321, | |
| "learning_rate": 4.462106874261969e-05, | |
| "loss": 0.2517, | |
| "num_input_tokens_seen": 25316200, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 1.1174349729590523, | |
| "grad_norm": 6.9914691655915915, | |
| "learning_rate": 4.440933621683882e-05, | |
| "loss": 0.3029, | |
| "num_input_tokens_seen": 25374656, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.1200103013134175, | |
| "grad_norm": 16.522791503108277, | |
| "learning_rate": 4.419770516538899e-05, | |
| "loss": 0.3005, | |
| "num_input_tokens_seen": 25433168, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.1225856296677827, | |
| "grad_norm": 5.579772115611286, | |
| "learning_rate": 4.398617942951703e-05, | |
| "loss": 0.3059, | |
| "num_input_tokens_seen": 25491664, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.1251609580221478, | |
| "grad_norm": 5.159164617041174, | |
| "learning_rate": 4.3774762848558124e-05, | |
| "loss": 0.2385, | |
| "num_input_tokens_seen": 25550128, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 1.127736286376513, | |
| "grad_norm": 6.950405613058986, | |
| "learning_rate": 4.356345925986637e-05, | |
| "loss": 0.2795, | |
| "num_input_tokens_seen": 25608624, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.1303116147308783, | |
| "grad_norm": 11.442249196591066, | |
| "learning_rate": 4.335227249874484e-05, | |
| "loss": 0.2622, | |
| "num_input_tokens_seen": 25667128, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 1.1328869430852433, | |
| "grad_norm": 9.573659203425603, | |
| "learning_rate": 4.314120639837619e-05, | |
| "loss": 0.3184, | |
| "num_input_tokens_seen": 25725560, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.1328869430852433, | |
| "eval_loss": 0.24919146299362183, | |
| "eval_runtime": 19.1706, | |
| "eval_samples_per_second": 3.13, | |
| "eval_steps_per_second": 0.782, | |
| "num_input_tokens_seen": 25725560, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.1354622714396085, | |
| "grad_norm": 18.05516134286847, | |
| "learning_rate": 4.2930264789752974e-05, | |
| "loss": 0.3121, | |
| "num_input_tokens_seen": 25784048, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 1.1380375997939738, | |
| "grad_norm": 5.276257572884321, | |
| "learning_rate": 4.271945150160815e-05, | |
| "loss": 0.2448, | |
| "num_input_tokens_seen": 25842512, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.140612928148339, | |
| "grad_norm": 9.772532033416248, | |
| "learning_rate": 4.250877036034552e-05, | |
| "loss": 0.3141, | |
| "num_input_tokens_seen": 25900992, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 1.143188256502704, | |
| "grad_norm": 4.984185148660987, | |
| "learning_rate": 4.2298225189970424e-05, | |
| "loss": 0.2589, | |
| "num_input_tokens_seen": 25959448, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.1457635848570693, | |
| "grad_norm": 5.610565971454716, | |
| "learning_rate": 4.2087819812020155e-05, | |
| "loss": 0.3071, | |
| "num_input_tokens_seen": 26017936, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 1.1483389132114346, | |
| "grad_norm": 6.203972820387514, | |
| "learning_rate": 4.1877558045494735e-05, | |
| "loss": 0.1913, | |
| "num_input_tokens_seen": 26076440, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.1509142415657996, | |
| "grad_norm": 6.8902811910693185, | |
| "learning_rate": 4.166744370678748e-05, | |
| "loss": 0.1998, | |
| "num_input_tokens_seen": 26134896, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 1.1534895699201648, | |
| "grad_norm": 13.51914586072303, | |
| "learning_rate": 4.1457480609615866e-05, | |
| "loss": 0.2382, | |
| "num_input_tokens_seen": 26193368, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.15606489827453, | |
| "grad_norm": 10.238408014223214, | |
| "learning_rate": 4.124767256495217e-05, | |
| "loss": 0.231, | |
| "num_input_tokens_seen": 26251848, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 1.158640226628895, | |
| "grad_norm": 3.473707001713829, | |
| "learning_rate": 4.1038023380954415e-05, | |
| "loss": 0.273, | |
| "num_input_tokens_seen": 26310336, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.158640226628895, | |
| "eval_loss": 0.22014015913009644, | |
| "eval_runtime": 20.315, | |
| "eval_samples_per_second": 2.953, | |
| "eval_steps_per_second": 0.738, | |
| "num_input_tokens_seen": 26310336, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.1612155549832603, | |
| "grad_norm": 8.283787630987762, | |
| "learning_rate": 4.0828536862897125e-05, | |
| "loss": 0.2986, | |
| "num_input_tokens_seen": 26368840, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 1.1637908833376256, | |
| "grad_norm": 20.215982883136522, | |
| "learning_rate": 4.061921681310241e-05, | |
| "loss": 0.263, | |
| "num_input_tokens_seen": 26427280, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.1663662116919906, | |
| "grad_norm": 6.802291856358878, | |
| "learning_rate": 4.04100670308708e-05, | |
| "loss": 0.2282, | |
| "num_input_tokens_seen": 26485760, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 1.1689415400463559, | |
| "grad_norm": 8.985818465549714, | |
| "learning_rate": 4.0201091312412394e-05, | |
| "loss": 0.2311, | |
| "num_input_tokens_seen": 26544224, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.1715168684007211, | |
| "grad_norm": 8.383045025215052, | |
| "learning_rate": 3.999229345077789e-05, | |
| "loss": 0.2939, | |
| "num_input_tokens_seen": 26602712, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.1740921967550864, | |
| "grad_norm": 6.558546292884369, | |
| "learning_rate": 3.978367723578981e-05, | |
| "loss": 0.2165, | |
| "num_input_tokens_seen": 26661160, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.1766675251094514, | |
| "grad_norm": 7.108641756919162, | |
| "learning_rate": 3.957524645397359e-05, | |
| "loss": 0.1823, | |
| "num_input_tokens_seen": 26719648, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 1.1792428534638166, | |
| "grad_norm": 11.468609977960636, | |
| "learning_rate": 3.936700488848899e-05, | |
| "loss": 0.2827, | |
| "num_input_tokens_seen": 26778112, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 11.548102910785317, | |
| "learning_rate": 3.915895631906135e-05, | |
| "loss": 0.2897, | |
| "num_input_tokens_seen": 26836592, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 1.184393510172547, | |
| "grad_norm": 4.826501140271565, | |
| "learning_rate": 3.895110452191301e-05, | |
| "loss": 0.2903, | |
| "num_input_tokens_seen": 26895096, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.184393510172547, | |
| "eval_loss": 0.2940039336681366, | |
| "eval_runtime": 20.1001, | |
| "eval_samples_per_second": 2.985, | |
| "eval_steps_per_second": 0.746, | |
| "num_input_tokens_seen": 26895096, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.1869688385269122, | |
| "grad_norm": 14.75757212453522, | |
| "learning_rate": 3.874345326969471e-05, | |
| "loss": 0.2475, | |
| "num_input_tokens_seen": 26953560, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 1.1895441668812774, | |
| "grad_norm": 8.582159713261374, | |
| "learning_rate": 3.853600633141725e-05, | |
| "loss": 0.2921, | |
| "num_input_tokens_seen": 27012024, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.1921194952356426, | |
| "grad_norm": 5.07888266594019, | |
| "learning_rate": 3.8328767472382896e-05, | |
| "loss": 0.2065, | |
| "num_input_tokens_seen": 27070520, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 1.1946948235900077, | |
| "grad_norm": 9.693667990788615, | |
| "learning_rate": 3.812174045411724e-05, | |
| "loss": 0.2232, | |
| "num_input_tokens_seen": 27128984, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.197270151944373, | |
| "grad_norm": 8.720131927787088, | |
| "learning_rate": 3.791492903430071e-05, | |
| "loss": 0.266, | |
| "num_input_tokens_seen": 27187432, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.1998454802987382, | |
| "grad_norm": 4.72913904175421, | |
| "learning_rate": 3.7708336966700574e-05, | |
| "loss": 0.2451, | |
| "num_input_tokens_seen": 27245920, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.2024208086531032, | |
| "grad_norm": 7.832988091306638, | |
| "learning_rate": 3.7501968001102634e-05, | |
| "loss": 0.2031, | |
| "num_input_tokens_seen": 27304384, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 1.2049961370074684, | |
| "grad_norm": 9.913047640861075, | |
| "learning_rate": 3.7295825883243306e-05, | |
| "loss": 0.2605, | |
| "num_input_tokens_seen": 27362864, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.2075714653618337, | |
| "grad_norm": 15.020677650419302, | |
| "learning_rate": 3.708991435474151e-05, | |
| "loss": 0.2293, | |
| "num_input_tokens_seen": 27421360, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 1.210146793716199, | |
| "grad_norm": 15.606205008499776, | |
| "learning_rate": 3.688423715303082e-05, | |
| "loss": 0.2757, | |
| "num_input_tokens_seen": 27479840, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.210146793716199, | |
| "eval_loss": 0.26213815808296204, | |
| "eval_runtime": 19.7609, | |
| "eval_samples_per_second": 3.036, | |
| "eval_steps_per_second": 0.759, | |
| "num_input_tokens_seen": 27479840, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.212722122070564, | |
| "grad_norm": 9.144283973474371, | |
| "learning_rate": 3.6678798011291674e-05, | |
| "loss": 0.242, | |
| "num_input_tokens_seen": 27538344, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 1.2152974504249292, | |
| "grad_norm": 12.80063906167105, | |
| "learning_rate": 3.647360065838348e-05, | |
| "loss": 0.2451, | |
| "num_input_tokens_seen": 27596808, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.2178727787792945, | |
| "grad_norm": 3.44448459243246, | |
| "learning_rate": 3.6268648818777105e-05, | |
| "loss": 0.2237, | |
| "num_input_tokens_seen": 27655272, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 1.2204481071336595, | |
| "grad_norm": 14.301919876267943, | |
| "learning_rate": 3.606394621248709e-05, | |
| "loss": 0.2033, | |
| "num_input_tokens_seen": 27713784, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.2230234354880247, | |
| "grad_norm": 11.349699284999199, | |
| "learning_rate": 3.585949655500429e-05, | |
| "loss": 0.2741, | |
| "num_input_tokens_seen": 27772248, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 1.22559876384239, | |
| "grad_norm": 4.036313729279471, | |
| "learning_rate": 3.5655303557228335e-05, | |
| "loss": 0.2677, | |
| "num_input_tokens_seen": 27830704, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.228174092196755, | |
| "grad_norm": 5.042006341816937, | |
| "learning_rate": 3.545137092540035e-05, | |
| "loss": 0.2117, | |
| "num_input_tokens_seen": 27889160, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 1.2307494205511202, | |
| "grad_norm": 4.191635671104207, | |
| "learning_rate": 3.524770236103556e-05, | |
| "loss": 0.2216, | |
| "num_input_tokens_seen": 27947608, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.2333247489054855, | |
| "grad_norm": 13.530120109841187, | |
| "learning_rate": 3.504430156085629e-05, | |
| "loss": 0.28, | |
| "num_input_tokens_seen": 28006112, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 1.2359000772598505, | |
| "grad_norm": 23.252663154179324, | |
| "learning_rate": 3.484117221672465e-05, | |
| "loss": 0.2766, | |
| "num_input_tokens_seen": 28064552, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.2359000772598505, | |
| "eval_loss": 0.2361450344324112, | |
| "eval_runtime": 19.8674, | |
| "eval_samples_per_second": 3.02, | |
| "eval_steps_per_second": 0.755, | |
| "num_input_tokens_seen": 28064552, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.2384754056142158, | |
| "grad_norm": 16.379510205091783, | |
| "learning_rate": 3.463831801557577e-05, | |
| "loss": 0.1933, | |
| "num_input_tokens_seen": 28123016, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 1.241050733968581, | |
| "grad_norm": 3.6631986381781556, | |
| "learning_rate": 3.443574263935062e-05, | |
| "loss": 0.2014, | |
| "num_input_tokens_seen": 28181464, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.2436260623229463, | |
| "grad_norm": 5.654529592966364, | |
| "learning_rate": 3.42334497649294e-05, | |
| "loss": 0.2383, | |
| "num_input_tokens_seen": 28239920, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 1.2462013906773113, | |
| "grad_norm": 14.005033039787135, | |
| "learning_rate": 3.403144306406466e-05, | |
| "loss": 0.2074, | |
| "num_input_tokens_seen": 28298432, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.2487767190316765, | |
| "grad_norm": 7.470199127973674, | |
| "learning_rate": 3.382972620331475e-05, | |
| "loss": 0.2202, | |
| "num_input_tokens_seen": 28356904, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 1.2513520473860418, | |
| "grad_norm": 3.9239650586287484, | |
| "learning_rate": 3.362830284397716e-05, | |
| "loss": 0.1756, | |
| "num_input_tokens_seen": 28415384, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.2539273757404068, | |
| "grad_norm": 32.67443269914418, | |
| "learning_rate": 3.342717664202223e-05, | |
| "loss": 0.2564, | |
| "num_input_tokens_seen": 28473848, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 1.256502704094772, | |
| "grad_norm": 8.79661830656602, | |
| "learning_rate": 3.322635124802658e-05, | |
| "loss": 0.242, | |
| "num_input_tokens_seen": 28532312, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.2590780324491373, | |
| "grad_norm": 9.41003020617472, | |
| "learning_rate": 3.3025830307107035e-05, | |
| "loss": 0.3455, | |
| "num_input_tokens_seen": 28590784, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 1.2616533608035025, | |
| "grad_norm": 23.884422578805488, | |
| "learning_rate": 3.2825617458854376e-05, | |
| "loss": 0.3076, | |
| "num_input_tokens_seen": 28649256, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.2616533608035025, | |
| "eval_loss": 0.2371988147497177, | |
| "eval_runtime": 19.6997, | |
| "eval_samples_per_second": 3.046, | |
| "eval_steps_per_second": 0.761, | |
| "num_input_tokens_seen": 28649256, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.2642286891578676, | |
| "grad_norm": 13.48575395754194, | |
| "learning_rate": 3.2625716337267295e-05, | |
| "loss": 0.2041, | |
| "num_input_tokens_seen": 28707736, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 1.2668040175122328, | |
| "grad_norm": 3.1641318472119986, | |
| "learning_rate": 3.242613057068641e-05, | |
| "loss": 0.3022, | |
| "num_input_tokens_seen": 28766232, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.269379345866598, | |
| "grad_norm": 17.472204317681474, | |
| "learning_rate": 3.222686378172847e-05, | |
| "loss": 0.2756, | |
| "num_input_tokens_seen": 28824688, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 1.271954674220963, | |
| "grad_norm": 4.051662934956441, | |
| "learning_rate": 3.2027919587220516e-05, | |
| "loss": 0.2395, | |
| "num_input_tokens_seen": 28883176, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.2745300025753283, | |
| "grad_norm": 5.058807389542336, | |
| "learning_rate": 3.1829301598134355e-05, | |
| "loss": 0.2204, | |
| "num_input_tokens_seen": 28941592, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.2771053309296936, | |
| "grad_norm": 4.820344297526228, | |
| "learning_rate": 3.1631013419520855e-05, | |
| "loss": 0.2477, | |
| "num_input_tokens_seen": 29000064, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.2796806592840588, | |
| "grad_norm": 6.098120285465299, | |
| "learning_rate": 3.143305865044467e-05, | |
| "loss": 0.2645, | |
| "num_input_tokens_seen": 29058496, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 1.2822559876384239, | |
| "grad_norm": 10.021136804794267, | |
| "learning_rate": 3.123544088391881e-05, | |
| "loss": 0.2184, | |
| "num_input_tokens_seen": 29116992, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.284831315992789, | |
| "grad_norm": 32.07716009409277, | |
| "learning_rate": 3.10381637068395e-05, | |
| "loss": 0.1857, | |
| "num_input_tokens_seen": 29175496, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 1.2874066443471541, | |
| "grad_norm": 10.697788786097991, | |
| "learning_rate": 3.084123069992096e-05, | |
| "loss": 0.257, | |
| "num_input_tokens_seen": 29233968, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2874066443471541, | |
| "eval_loss": 0.2488754242658615, | |
| "eval_runtime": 19.5416, | |
| "eval_samples_per_second": 3.07, | |
| "eval_steps_per_second": 0.768, | |
| "num_input_tokens_seen": 29233968, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2899819727015194, | |
| "grad_norm": 3.8096764598668864, | |
| "learning_rate": 3.064464543763057e-05, | |
| "loss": 0.1617, | |
| "num_input_tokens_seen": 29292464, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 1.2925573010558846, | |
| "grad_norm": 8.299858124153992, | |
| "learning_rate": 3.0448411488123862e-05, | |
| "loss": 0.2068, | |
| "num_input_tokens_seen": 29350952, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.2951326294102499, | |
| "grad_norm": 10.959075314673317, | |
| "learning_rate": 3.0252532413179825e-05, | |
| "loss": 0.2188, | |
| "num_input_tokens_seen": 29409432, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 1.2977079577646151, | |
| "grad_norm": 7.014945794108391, | |
| "learning_rate": 3.0057011768136223e-05, | |
| "loss": 0.1948, | |
| "num_input_tokens_seen": 29467880, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.3002832861189801, | |
| "grad_norm": 5.3992920228602665, | |
| "learning_rate": 2.9861853101825094e-05, | |
| "loss": 0.2366, | |
| "num_input_tokens_seen": 29526384, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 1.3028586144733454, | |
| "grad_norm": 7.369149060264004, | |
| "learning_rate": 2.966705995650827e-05, | |
| "loss": 0.2601, | |
| "num_input_tokens_seen": 29584880, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.3054339428277104, | |
| "grad_norm": 8.85591028977132, | |
| "learning_rate": 2.9472635867813185e-05, | |
| "loss": 0.1913, | |
| "num_input_tokens_seen": 29643344, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 1.3080092711820757, | |
| "grad_norm": 6.292489461251922, | |
| "learning_rate": 2.927858436466861e-05, | |
| "loss": 0.2, | |
| "num_input_tokens_seen": 29701864, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.310584599536441, | |
| "grad_norm": 10.28646529424139, | |
| "learning_rate": 2.9084908969240664e-05, | |
| "loss": 0.2503, | |
| "num_input_tokens_seen": 29760376, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 1.3131599278908062, | |
| "grad_norm": 6.3979585721541135, | |
| "learning_rate": 2.8891613196868816e-05, | |
| "loss": 0.2192, | |
| "num_input_tokens_seen": 29818856, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.3131599278908062, | |
| "eval_loss": 0.24317465722560883, | |
| "eval_runtime": 19.477, | |
| "eval_samples_per_second": 3.081, | |
| "eval_steps_per_second": 0.77, | |
| "num_input_tokens_seen": 29818856, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.3157352562451712, | |
| "grad_norm": 5.864909751734038, | |
| "learning_rate": 2.8698700556002178e-05, | |
| "loss": 0.2231, | |
| "num_input_tokens_seen": 29877288, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 1.3183105845995364, | |
| "grad_norm": 11.12053960539336, | |
| "learning_rate": 2.8506174548135695e-05, | |
| "loss": 0.3007, | |
| "num_input_tokens_seen": 29935776, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.3208859129539017, | |
| "grad_norm": 5.495356583672569, | |
| "learning_rate": 2.8314038667746732e-05, | |
| "loss": 0.1895, | |
| "num_input_tokens_seen": 29994232, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 1.3234612413082667, | |
| "grad_norm": 11.482142819244615, | |
| "learning_rate": 2.81222964022315e-05, | |
| "loss": 0.2728, | |
| "num_input_tokens_seen": 30052760, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.326036569662632, | |
| "grad_norm": 8.217608228490523, | |
| "learning_rate": 2.793095123184193e-05, | |
| "loss": 0.2827, | |
| "num_input_tokens_seen": 30111200, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 1.3286118980169972, | |
| "grad_norm": 5.535041581031614, | |
| "learning_rate": 2.77400066296223e-05, | |
| "loss": 0.2191, | |
| "num_input_tokens_seen": 30169680, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.3311872263713624, | |
| "grad_norm": 6.639368336077178, | |
| "learning_rate": 2.7549466061346386e-05, | |
| "loss": 0.2317, | |
| "num_input_tokens_seen": 30228176, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 1.3337625547257275, | |
| "grad_norm": 5.625387657466934, | |
| "learning_rate": 2.7359332985454443e-05, | |
| "loss": 0.2293, | |
| "num_input_tokens_seen": 30286656, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.3363378830800927, | |
| "grad_norm": 3.631245501478199, | |
| "learning_rate": 2.716961085299049e-05, | |
| "loss": 0.1903, | |
| "num_input_tokens_seen": 30345160, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 1.338913211434458, | |
| "grad_norm": 11.391263066967507, | |
| "learning_rate": 2.698030310753958e-05, | |
| "loss": 0.224, | |
| "num_input_tokens_seen": 30403640, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.338913211434458, | |
| "eval_loss": 0.20262545347213745, | |
| "eval_runtime": 19.6125, | |
| "eval_samples_per_second": 3.059, | |
| "eval_steps_per_second": 0.765, | |
| "num_input_tokens_seen": 30403640, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.341488539788823, | |
| "grad_norm": 8.177384294556918, | |
| "learning_rate": 2.6791413185165442e-05, | |
| "loss": 0.2563, | |
| "num_input_tokens_seen": 30462128, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 1.3440638681431882, | |
| "grad_norm": 6.121025769450026, | |
| "learning_rate": 2.660294451434796e-05, | |
| "loss": 0.235, | |
| "num_input_tokens_seen": 30520616, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.3466391964975535, | |
| "grad_norm": 8.690869571731369, | |
| "learning_rate": 2.641490051592107e-05, | |
| "loss": 0.2113, | |
| "num_input_tokens_seen": 30579024, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 1.3492145248519187, | |
| "grad_norm": 7.285970612374189, | |
| "learning_rate": 2.6227284603010604e-05, | |
| "loss": 0.216, | |
| "num_input_tokens_seen": 30637464, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.3517898532062838, | |
| "grad_norm": 5.682668591040817, | |
| "learning_rate": 2.6040100180972355e-05, | |
| "loss": 0.2599, | |
| "num_input_tokens_seen": 30695936, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.354365181560649, | |
| "grad_norm": 5.815763005326374, | |
| "learning_rate": 2.585335064733022e-05, | |
| "loss": 0.2421, | |
| "num_input_tokens_seen": 30754408, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.356940509915014, | |
| "grad_norm": 6.8726858718673975, | |
| "learning_rate": 2.5667039391714666e-05, | |
| "loss": 0.2095, | |
| "num_input_tokens_seen": 30812848, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 1.3595158382693793, | |
| "grad_norm": 10.374721228070925, | |
| "learning_rate": 2.5481169795801008e-05, | |
| "loss": 0.2223, | |
| "num_input_tokens_seen": 30871344, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.3620911666237445, | |
| "grad_norm": 4.502700102041516, | |
| "learning_rate": 2.5295745233248248e-05, | |
| "loss": 0.2273, | |
| "num_input_tokens_seen": 30929824, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 1.3646664949781098, | |
| "grad_norm": 6.715540062682421, | |
| "learning_rate": 2.511076906963763e-05, | |
| "loss": 0.2377, | |
| "num_input_tokens_seen": 30988344, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.3646664949781098, | |
| "eval_loss": 0.18780523538589478, | |
| "eval_runtime": 19.4103, | |
| "eval_samples_per_second": 3.091, | |
| "eval_steps_per_second": 0.773, | |
| "num_input_tokens_seen": 30988344, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.367241823332475, | |
| "grad_norm": 7.2025231601123085, | |
| "learning_rate": 2.4926244662411734e-05, | |
| "loss": 0.2109, | |
| "num_input_tokens_seen": 31046848, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 1.36981715168684, | |
| "grad_norm": 4.944078503740031, | |
| "learning_rate": 2.474217536081342e-05, | |
| "loss": 0.2544, | |
| "num_input_tokens_seen": 31105352, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.3723924800412053, | |
| "grad_norm": 20.15441745302564, | |
| "learning_rate": 2.4558564505825088e-05, | |
| "loss": 0.2616, | |
| "num_input_tokens_seen": 31163848, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 1.3749678083955703, | |
| "grad_norm": 9.97997619530482, | |
| "learning_rate": 2.4375415430107977e-05, | |
| "loss": 0.1722, | |
| "num_input_tokens_seen": 31222360, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.3775431367499356, | |
| "grad_norm": 2.1763725749744465, | |
| "learning_rate": 2.4192731457941805e-05, | |
| "loss": 0.1966, | |
| "num_input_tokens_seen": 31280840, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 1.3801184651043008, | |
| "grad_norm": 10.60754914489294, | |
| "learning_rate": 2.4010515905164243e-05, | |
| "loss": 0.2578, | |
| "num_input_tokens_seen": 31339264, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.382693793458666, | |
| "grad_norm": 15.190148047284161, | |
| "learning_rate": 2.3828772079110907e-05, | |
| "loss": 0.3076, | |
| "num_input_tokens_seen": 31397744, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 1.385269121813031, | |
| "grad_norm": 20.889251542966374, | |
| "learning_rate": 2.3647503278555233e-05, | |
| "loss": 0.1911, | |
| "num_input_tokens_seen": 31456240, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.3878444501673963, | |
| "grad_norm": 4.797824757647722, | |
| "learning_rate": 2.3466712793648638e-05, | |
| "loss": 0.2204, | |
| "num_input_tokens_seen": 31514744, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 1.3904197785217616, | |
| "grad_norm": 16.36975645045513, | |
| "learning_rate": 2.3286403905860733e-05, | |
| "loss": 0.2269, | |
| "num_input_tokens_seen": 31573240, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.3904197785217616, | |
| "eval_loss": 0.24001093208789825, | |
| "eval_runtime": 19.3768, | |
| "eval_samples_per_second": 3.096, | |
| "eval_steps_per_second": 0.774, | |
| "num_input_tokens_seen": 31573240, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.3929951068761266, | |
| "grad_norm": 23.383619982845065, | |
| "learning_rate": 2.3106579887919894e-05, | |
| "loss": 0.2339, | |
| "num_input_tokens_seen": 31631688, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 1.3955704352304918, | |
| "grad_norm": 4.588108718468969, | |
| "learning_rate": 2.2927244003753694e-05, | |
| "loss": 0.2197, | |
| "num_input_tokens_seen": 31690200, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.398145763584857, | |
| "grad_norm": 3.4659557649616284, | |
| "learning_rate": 2.2748399508429834e-05, | |
| "loss": 0.1999, | |
| "num_input_tokens_seen": 31748664, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 1.4007210919392223, | |
| "grad_norm": 5.297859489588456, | |
| "learning_rate": 2.2570049648096902e-05, | |
| "loss": 0.2757, | |
| "num_input_tokens_seen": 31807176, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.4032964202935874, | |
| "grad_norm": 8.718394323594142, | |
| "learning_rate": 2.239219765992557e-05, | |
| "loss": 0.2128, | |
| "num_input_tokens_seen": 31865696, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 1.4058717486479526, | |
| "grad_norm": 11.91241028531398, | |
| "learning_rate": 2.221484677204978e-05, | |
| "loss": 0.2657, | |
| "num_input_tokens_seen": 31924200, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.4084470770023179, | |
| "grad_norm": 6.407371884386196, | |
| "learning_rate": 2.203800020350819e-05, | |
| "loss": 0.2349, | |
| "num_input_tokens_seen": 31982712, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 1.4110224053566829, | |
| "grad_norm": 4.998470631619502, | |
| "learning_rate": 2.1861661164185652e-05, | |
| "loss": 0.2188, | |
| "num_input_tokens_seen": 32041176, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.4135977337110481, | |
| "grad_norm": 6.503122447364567, | |
| "learning_rate": 2.1685832854755115e-05, | |
| "loss": 0.2531, | |
| "num_input_tokens_seen": 32099656, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 1.4161730620654134, | |
| "grad_norm": 3.8963890551505123, | |
| "learning_rate": 2.1510518466619334e-05, | |
| "loss": 0.1416, | |
| "num_input_tokens_seen": 32158144, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.4161730620654134, | |
| "eval_loss": 0.24715903401374817, | |
| "eval_runtime": 19.5042, | |
| "eval_samples_per_second": 3.076, | |
| "eval_steps_per_second": 0.769, | |
| "num_input_tokens_seen": 32158144, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.4187483904197786, | |
| "grad_norm": 8.62691802455825, | |
| "learning_rate": 2.133572118185313e-05, | |
| "loss": 0.2459, | |
| "num_input_tokens_seen": 32216656, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 1.4213237187741437, | |
| "grad_norm": 11.518284151131217, | |
| "learning_rate": 2.1161444173145468e-05, | |
| "loss": 0.2656, | |
| "num_input_tokens_seen": 32275168, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.423899047128509, | |
| "grad_norm": 5.717001204241147, | |
| "learning_rate": 2.098769060374206e-05, | |
| "loss": 0.199, | |
| "num_input_tokens_seen": 32333664, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 1.4264743754828741, | |
| "grad_norm": 5.060469427631098, | |
| "learning_rate": 2.0814463627387744e-05, | |
| "loss": 0.2552, | |
| "num_input_tokens_seen": 32392088, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.4290497038372392, | |
| "grad_norm": 10.068742247308663, | |
| "learning_rate": 2.0641766388269345e-05, | |
| "loss": 0.2123, | |
| "num_input_tokens_seen": 32450584, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 1.4316250321916044, | |
| "grad_norm": 8.04329511861408, | |
| "learning_rate": 2.046960202095866e-05, | |
| "loss": 0.1827, | |
| "num_input_tokens_seen": 32509096, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.4342003605459697, | |
| "grad_norm": 5.111975388475009, | |
| "learning_rate": 2.0297973650355435e-05, | |
| "loss": 0.3038, | |
| "num_input_tokens_seen": 32567560, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 1.436775688900335, | |
| "grad_norm": 2.2165480876124666, | |
| "learning_rate": 2.012688439163075e-05, | |
| "loss": 0.2078, | |
| "num_input_tokens_seen": 32626056, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.4393510172547, | |
| "grad_norm": 5.208837069631258, | |
| "learning_rate": 1.9956337350170446e-05, | |
| "loss": 0.23, | |
| "num_input_tokens_seen": 32684520, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 1.4419263456090652, | |
| "grad_norm": 14.804471075670579, | |
| "learning_rate": 1.978633562151875e-05, | |
| "loss": 0.2162, | |
| "num_input_tokens_seen": 32743032, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.4419263456090652, | |
| "eval_loss": 0.2771253287792206, | |
| "eval_runtime": 19.4256, | |
| "eval_samples_per_second": 3.089, | |
| "eval_steps_per_second": 0.772, | |
| "num_input_tokens_seen": 32743032, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.4445016739634302, | |
| "grad_norm": 5.47081802170478, | |
| "learning_rate": 1.9616882291322043e-05, | |
| "loss": 0.2128, | |
| "num_input_tokens_seen": 32801504, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 1.4470770023177955, | |
| "grad_norm": 8.153473173608221, | |
| "learning_rate": 1.9447980435272982e-05, | |
| "loss": 0.226, | |
| "num_input_tokens_seen": 32860032, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.4496523306721607, | |
| "grad_norm": 3.2012899866356275, | |
| "learning_rate": 1.9279633119054524e-05, | |
| "loss": 0.1945, | |
| "num_input_tokens_seen": 32918472, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 1.452227659026526, | |
| "grad_norm": 3.275737115662877, | |
| "learning_rate": 1.9111843398284412e-05, | |
| "loss": 0.1593, | |
| "num_input_tokens_seen": 32976944, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.4548029873808912, | |
| "grad_norm": 5.6817295869650755, | |
| "learning_rate": 1.8944614318459604e-05, | |
| "loss": 0.2154, | |
| "num_input_tokens_seen": 33035424, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 1.4573783157352562, | |
| "grad_norm": 4.248487908153702, | |
| "learning_rate": 1.8777948914901066e-05, | |
| "loss": 0.2266, | |
| "num_input_tokens_seen": 33093880, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.4599536440896215, | |
| "grad_norm": 4.65833753095402, | |
| "learning_rate": 1.8611850212698678e-05, | |
| "loss": 0.1948, | |
| "num_input_tokens_seen": 33152328, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 1.4625289724439865, | |
| "grad_norm": 6.9576190671694205, | |
| "learning_rate": 1.84463212266563e-05, | |
| "loss": 0.2159, | |
| "num_input_tokens_seen": 33210816, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.4651043007983517, | |
| "grad_norm": 28.44341760505862, | |
| "learning_rate": 1.8281364961237013e-05, | |
| "loss": 0.2326, | |
| "num_input_tokens_seen": 33269320, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 1.467679629152717, | |
| "grad_norm": 12.408239979973144, | |
| "learning_rate": 1.8116984410508696e-05, | |
| "loss": 0.1912, | |
| "num_input_tokens_seen": 33327720, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.467679629152717, | |
| "eval_loss": 0.2647402584552765, | |
| "eval_runtime": 19.6149, | |
| "eval_samples_per_second": 3.059, | |
| "eval_steps_per_second": 0.765, | |
| "num_input_tokens_seen": 33327720, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.4702549575070822, | |
| "grad_norm": 8.379574283067335, | |
| "learning_rate": 1.795318255808956e-05, | |
| "loss": 0.2166, | |
| "num_input_tokens_seen": 33386160, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 1.4728302858614473, | |
| "grad_norm": 9.376274649781424, | |
| "learning_rate": 1.7789962377094088e-05, | |
| "loss": 0.1843, | |
| "num_input_tokens_seen": 33444648, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.4754056142158125, | |
| "grad_norm": 2.5653090157172724, | |
| "learning_rate": 1.762732683007902e-05, | |
| "loss": 0.1988, | |
| "num_input_tokens_seen": 33503144, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 1.4779809425701778, | |
| "grad_norm": 12.205543974310553, | |
| "learning_rate": 1.746527886898962e-05, | |
| "loss": 0.1715, | |
| "num_input_tokens_seen": 33561600, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.4805562709245428, | |
| "grad_norm": 2.016900668078144, | |
| "learning_rate": 1.7303821435105998e-05, | |
| "loss": 0.1577, | |
| "num_input_tokens_seen": 33620056, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 1.483131599278908, | |
| "grad_norm": 7.53734329898392, | |
| "learning_rate": 1.714295745898989e-05, | |
| "loss": 0.2204, | |
| "num_input_tokens_seen": 33678512, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.4857069276332733, | |
| "grad_norm": 25.928242388695963, | |
| "learning_rate": 1.6982689860431283e-05, | |
| "loss": 0.2283, | |
| "num_input_tokens_seen": 33736960, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 1.4882822559876385, | |
| "grad_norm": 21.45493152674021, | |
| "learning_rate": 1.682302154839558e-05, | |
| "loss": 0.2632, | |
| "num_input_tokens_seen": 33795416, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.4908575843420036, | |
| "grad_norm": 8.396238950090229, | |
| "learning_rate": 1.6663955420970667e-05, | |
| "loss": 0.1844, | |
| "num_input_tokens_seen": 33853936, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 1.4934329126963688, | |
| "grad_norm": 4.710042357794161, | |
| "learning_rate": 1.650549436531442e-05, | |
| "loss": 0.2015, | |
| "num_input_tokens_seen": 33912440, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.4934329126963688, | |
| "eval_loss": 0.23923428356647491, | |
| "eval_runtime": 19.3819, | |
| "eval_samples_per_second": 3.096, | |
| "eval_steps_per_second": 0.774, | |
| "num_input_tokens_seen": 33912440, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.496008241050734, | |
| "grad_norm": 4.859449394658537, | |
| "learning_rate": 1.6347641257602236e-05, | |
| "loss": 0.2244, | |
| "num_input_tokens_seen": 33970888, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 1.498583569405099, | |
| "grad_norm": 3.9094863370380684, | |
| "learning_rate": 1.6190398962974856e-05, | |
| "loss": 0.1864, | |
| "num_input_tokens_seen": 34029376, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.5011588977594643, | |
| "grad_norm": 2.8103187330737267, | |
| "learning_rate": 1.6033770335486305e-05, | |
| "loss": 0.1969, | |
| "num_input_tokens_seen": 34087864, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 1.5037342261138296, | |
| "grad_norm": 6.033935213601098, | |
| "learning_rate": 1.5877758218052207e-05, | |
| "loss": 0.2449, | |
| "num_input_tokens_seen": 34146296, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.5063095544681948, | |
| "grad_norm": 4.397544925205015, | |
| "learning_rate": 1.572236544239803e-05, | |
| "loss": 0.155, | |
| "num_input_tokens_seen": 34204800, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 1.5088848828225598, | |
| "grad_norm": 5.933520955975732, | |
| "learning_rate": 1.5567594829007835e-05, | |
| "loss": 0.2031, | |
| "num_input_tokens_seen": 34263296, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.511460211176925, | |
| "grad_norm": 6.341695577358793, | |
| "learning_rate": 1.541344918707299e-05, | |
| "loss": 0.1917, | |
| "num_input_tokens_seen": 34321792, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 1.51403553953129, | |
| "grad_norm": 4.985028365945458, | |
| "learning_rate": 1.525993131444123e-05, | |
| "loss": 0.1609, | |
| "num_input_tokens_seen": 34380264, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.5166108678856554, | |
| "grad_norm": 6.463643326585979, | |
| "learning_rate": 1.5107043997565795e-05, | |
| "loss": 0.2217, | |
| "num_input_tokens_seen": 34438752, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 1.5191861962400206, | |
| "grad_norm": 15.279246366044804, | |
| "learning_rate": 1.495479001145499e-05, | |
| "loss": 0.2069, | |
| "num_input_tokens_seen": 34497216, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.5191861962400206, | |
| "eval_loss": 0.2638954222202301, | |
| "eval_runtime": 19.2939, | |
| "eval_samples_per_second": 3.11, | |
| "eval_steps_per_second": 0.777, | |
| "num_input_tokens_seen": 34497216, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.5217615245943859, | |
| "grad_norm": 7.283233671161431, | |
| "learning_rate": 1.4803172119621661e-05, | |
| "loss": 0.2811, | |
| "num_input_tokens_seen": 34555704, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 1.524336852948751, | |
| "grad_norm": 5.1545528457087295, | |
| "learning_rate": 1.4652193074033188e-05, | |
| "loss": 0.2056, | |
| "num_input_tokens_seen": 34614168, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.5269121813031161, | |
| "grad_norm": 5.345680235559109, | |
| "learning_rate": 1.4501855615061376e-05, | |
| "loss": 0.2097, | |
| "num_input_tokens_seen": 34672624, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 1.5294875096574814, | |
| "grad_norm": 5.662685942725516, | |
| "learning_rate": 1.4352162471432872e-05, | |
| "loss": 0.1913, | |
| "num_input_tokens_seen": 34731056, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.5320628380118464, | |
| "grad_norm": 7.857317097258681, | |
| "learning_rate": 1.420311636017953e-05, | |
| "loss": 0.1996, | |
| "num_input_tokens_seen": 34789552, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.5346381663662116, | |
| "grad_norm": 5.32739810275719, | |
| "learning_rate": 1.4054719986589148e-05, | |
| "loss": 0.2102, | |
| "num_input_tokens_seen": 34848064, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.537213494720577, | |
| "grad_norm": 18.39581577669835, | |
| "learning_rate": 1.39069760441563e-05, | |
| "loss": 0.232, | |
| "num_input_tokens_seen": 34906592, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 1.5397888230749421, | |
| "grad_norm": 8.502936446963005, | |
| "learning_rate": 1.3759887214533557e-05, | |
| "loss": 0.2109, | |
| "num_input_tokens_seen": 34965064, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.5423641514293074, | |
| "grad_norm": 5.97229161259624, | |
| "learning_rate": 1.3613456167482685e-05, | |
| "loss": 0.1989, | |
| "num_input_tokens_seen": 35023552, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 1.5449394797836724, | |
| "grad_norm": 17.874594504088744, | |
| "learning_rate": 1.3467685560826315e-05, | |
| "loss": 0.2027, | |
| "num_input_tokens_seen": 35082056, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.5449394797836724, | |
| "eval_loss": 0.2371213436126709, | |
| "eval_runtime": 19.9605, | |
| "eval_samples_per_second": 3.006, | |
| "eval_steps_per_second": 0.751, | |
| "num_input_tokens_seen": 35082056, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.5475148081380374, | |
| "grad_norm": 4.476150794936761, | |
| "learning_rate": 1.3322578040399558e-05, | |
| "loss": 0.1383, | |
| "num_input_tokens_seen": 35140568, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 1.5500901364924027, | |
| "grad_norm": 8.697328407960805, | |
| "learning_rate": 1.3178136240002164e-05, | |
| "loss": 0.2006, | |
| "num_input_tokens_seen": 35199064, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.552665464846768, | |
| "grad_norm": 5.605565161628193, | |
| "learning_rate": 1.3034362781350524e-05, | |
| "loss": 0.251, | |
| "num_input_tokens_seen": 35257576, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 1.5552407932011332, | |
| "grad_norm": 9.015316943288264, | |
| "learning_rate": 1.289126027403023e-05, | |
| "loss": 0.1584, | |
| "num_input_tokens_seen": 35316064, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.5578161215554984, | |
| "grad_norm": 43.17142293680494, | |
| "learning_rate": 1.2748831315448606e-05, | |
| "loss": 0.2173, | |
| "num_input_tokens_seen": 35374504, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 1.5603914499098637, | |
| "grad_norm": 79.21408258106743, | |
| "learning_rate": 1.260707849078766e-05, | |
| "loss": 0.2518, | |
| "num_input_tokens_seen": 35432984, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 1.5629667782642287, | |
| "grad_norm": 3.4648607953939714, | |
| "learning_rate": 1.2466004372957068e-05, | |
| "loss": 0.1936, | |
| "num_input_tokens_seen": 35491488, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 1.5655421066185937, | |
| "grad_norm": 2.890163536607479, | |
| "learning_rate": 1.2325611522547547e-05, | |
| "loss": 0.1677, | |
| "num_input_tokens_seen": 35549984, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.568117434972959, | |
| "grad_norm": 3.8910029052375856, | |
| "learning_rate": 1.218590248778434e-05, | |
| "loss": 0.2021, | |
| "num_input_tokens_seen": 35608488, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 1.5706927633273242, | |
| "grad_norm": 7.663989340971129, | |
| "learning_rate": 1.2046879804480993e-05, | |
| "loss": 0.1925, | |
| "num_input_tokens_seen": 35666976, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.5706927633273242, | |
| "eval_loss": 0.24840803444385529, | |
| "eval_runtime": 20.1238, | |
| "eval_samples_per_second": 2.982, | |
| "eval_steps_per_second": 0.745, | |
| "num_input_tokens_seen": 35666976, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.5732680916816895, | |
| "grad_norm": 2.403638244773669, | |
| "learning_rate": 1.1908545995993253e-05, | |
| "loss": 0.1686, | |
| "num_input_tokens_seen": 35725456, | |
| "step": 3055 | |
| }, | |
| { | |
| "epoch": 1.5758434200360547, | |
| "grad_norm": 14.854500855372818, | |
| "learning_rate": 1.1770903573173398e-05, | |
| "loss": 0.2366, | |
| "num_input_tokens_seen": 35783912, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.5784187483904197, | |
| "grad_norm": 4.505603869422207, | |
| "learning_rate": 1.1633955034324507e-05, | |
| "loss": 0.2029, | |
| "num_input_tokens_seen": 35842376, | |
| "step": 3065 | |
| }, | |
| { | |
| "epoch": 1.580994076744785, | |
| "grad_norm": 6.561062574184342, | |
| "learning_rate": 1.1497702865155274e-05, | |
| "loss": 0.2116, | |
| "num_input_tokens_seen": 35900824, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.58356940509915, | |
| "grad_norm": 3.075946215121841, | |
| "learning_rate": 1.1362149538734745e-05, | |
| "loss": 0.1676, | |
| "num_input_tokens_seen": 35959264, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 1.5861447334535153, | |
| "grad_norm": 3.932942100960138, | |
| "learning_rate": 1.1227297515447543e-05, | |
| "loss": 0.1811, | |
| "num_input_tokens_seen": 36017760, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.5887200618078805, | |
| "grad_norm": 2.914398659228269, | |
| "learning_rate": 1.1093149242949152e-05, | |
| "loss": 0.1298, | |
| "num_input_tokens_seen": 36076280, | |
| "step": 3085 | |
| }, | |
| { | |
| "epoch": 1.5912953901622457, | |
| "grad_norm": 7.36077869474613, | |
| "learning_rate": 1.0959707156121506e-05, | |
| "loss": 0.1979, | |
| "num_input_tokens_seen": 36134784, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.593870718516611, | |
| "grad_norm": 7.180782753385591, | |
| "learning_rate": 1.0826973677028767e-05, | |
| "loss": 0.2539, | |
| "num_input_tokens_seen": 36193288, | |
| "step": 3095 | |
| }, | |
| { | |
| "epoch": 1.596446046870976, | |
| "grad_norm": 5.80837569754525, | |
| "learning_rate": 1.0694951214873427e-05, | |
| "loss": 0.2139, | |
| "num_input_tokens_seen": 36251744, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.596446046870976, | |
| "eval_loss": 0.2746882140636444, | |
| "eval_runtime": 20.8164, | |
| "eval_samples_per_second": 2.882, | |
| "eval_steps_per_second": 0.721, | |
| "num_input_tokens_seen": 36251744, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.5990213752253413, | |
| "grad_norm": 7.332248506243341, | |
| "learning_rate": 1.0563642165952497e-05, | |
| "loss": 0.1658, | |
| "num_input_tokens_seen": 36310200, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 1.6015967035797063, | |
| "grad_norm": 4.227211949206946, | |
| "learning_rate": 1.043304891361408e-05, | |
| "loss": 0.2308, | |
| "num_input_tokens_seen": 36368688, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 1.6041720319340715, | |
| "grad_norm": 7.364454762284429, | |
| "learning_rate": 1.030317382821409e-05, | |
| "loss": 0.1838, | |
| "num_input_tokens_seen": 36427192, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 1.6067473602884368, | |
| "grad_norm": 3.831562577565949, | |
| "learning_rate": 1.0174019267073225e-05, | |
| "loss": 0.1604, | |
| "num_input_tokens_seen": 36485656, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.609322688642802, | |
| "grad_norm": 7.497731599778419, | |
| "learning_rate": 1.0045587574434157e-05, | |
| "loss": 0.2069, | |
| "num_input_tokens_seen": 36544128, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 1.6118980169971673, | |
| "grad_norm": 6.255929929298457, | |
| "learning_rate": 9.917881081419033e-06, | |
| "loss": 0.2161, | |
| "num_input_tokens_seen": 36602568, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.6144733453515323, | |
| "grad_norm": 5.299301385448033, | |
| "learning_rate": 9.790902105987103e-06, | |
| "loss": 0.2202, | |
| "num_input_tokens_seen": 36661064, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 1.6170486737058976, | |
| "grad_norm": 5.618502845362283, | |
| "learning_rate": 9.66465295289274e-06, | |
| "loss": 0.1867, | |
| "num_input_tokens_seen": 36719544, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.6196240020602626, | |
| "grad_norm": 3.7802756504457067, | |
| "learning_rate": 9.539135913643465e-06, | |
| "loss": 0.1811, | |
| "num_input_tokens_seen": 36778064, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 1.6221993304146278, | |
| "grad_norm": 5.770789580720362, | |
| "learning_rate": 9.414353266458509e-06, | |
| "loss": 0.204, | |
| "num_input_tokens_seen": 36836560, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.6221993304146278, | |
| "eval_loss": 0.2422773241996765, | |
| "eval_runtime": 20.2302, | |
| "eval_samples_per_second": 2.966, | |
| "eval_steps_per_second": 0.741, | |
| "num_input_tokens_seen": 36836560, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.624774658768993, | |
| "grad_norm": 5.877162783758339, | |
| "learning_rate": 9.29030727622735e-06, | |
| "loss": 0.211, | |
| "num_input_tokens_seen": 36895016, | |
| "step": 3155 | |
| }, | |
| { | |
| "epoch": 1.6273499871233583, | |
| "grad_norm": 6.742491213588064, | |
| "learning_rate": 9.167000194468684e-06, | |
| "loss": 0.1973, | |
| "num_input_tokens_seen": 36953528, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.6299253154777236, | |
| "grad_norm": 3.9319298837048304, | |
| "learning_rate": 9.044434259289452e-06, | |
| "loss": 0.2209, | |
| "num_input_tokens_seen": 37012056, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 1.6325006438320886, | |
| "grad_norm": 4.3444513188690355, | |
| "learning_rate": 8.922611695344352e-06, | |
| "loss": 0.1527, | |
| "num_input_tokens_seen": 37070528, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 1.6350759721864536, | |
| "grad_norm": 6.583116555049651, | |
| "learning_rate": 8.801534713795339e-06, | |
| "loss": 0.189, | |
| "num_input_tokens_seen": 37129008, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 1.6376513005408189, | |
| "grad_norm": 2.419245633548623, | |
| "learning_rate": 8.681205512271574e-06, | |
| "loss": 0.1712, | |
| "num_input_tokens_seen": 37187472, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.6402266288951841, | |
| "grad_norm": 8.598240776469794, | |
| "learning_rate": 8.561626274829498e-06, | |
| "loss": 0.1751, | |
| "num_input_tokens_seen": 37245936, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 1.6428019572495494, | |
| "grad_norm": 3.6018632639200225, | |
| "learning_rate": 8.442799171913201e-06, | |
| "loss": 0.1963, | |
| "num_input_tokens_seen": 37304424, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 1.6453772856039146, | |
| "grad_norm": 2.5245912719574277, | |
| "learning_rate": 8.324726360314995e-06, | |
| "loss": 0.1133, | |
| "num_input_tokens_seen": 37362888, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 1.6479526139582796, | |
| "grad_norm": 6.895930963412961, | |
| "learning_rate": 8.207409983136332e-06, | |
| "loss": 0.1851, | |
| "num_input_tokens_seen": 37421416, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.6479526139582796, | |
| "eval_loss": 0.22857078909873962, | |
| "eval_runtime": 20.4323, | |
| "eval_samples_per_second": 2.937, | |
| "eval_steps_per_second": 0.734, | |
| "num_input_tokens_seen": 37421416, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.6505279423126449, | |
| "grad_norm": 3.0909496285264964, | |
| "learning_rate": 8.090852169748848e-06, | |
| "loss": 0.2208, | |
| "num_input_tokens_seen": 37479848, | |
| "step": 3205 | |
| }, | |
| { | |
| "epoch": 1.65310327066701, | |
| "grad_norm": 4.235698681690494, | |
| "learning_rate": 7.975055035755713e-06, | |
| "loss": 0.2252, | |
| "num_input_tokens_seen": 37538312, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 1.6556785990213752, | |
| "grad_norm": 10.661168860452113, | |
| "learning_rate": 7.860020682953284e-06, | |
| "loss": 0.254, | |
| "num_input_tokens_seen": 37596800, | |
| "step": 3215 | |
| }, | |
| { | |
| "epoch": 1.6582539273757404, | |
| "grad_norm": 3.6874689284357736, | |
| "learning_rate": 7.745751199292923e-06, | |
| "loss": 0.1741, | |
| "num_input_tokens_seen": 37655312, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.6608292557301056, | |
| "grad_norm": 10.065911223324512, | |
| "learning_rate": 7.632248658843088e-06, | |
| "loss": 0.2133, | |
| "num_input_tokens_seen": 37713800, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 1.663404584084471, | |
| "grad_norm": 3.799333032004199, | |
| "learning_rate": 7.51951512175168e-06, | |
| "loss": 0.1509, | |
| "num_input_tokens_seen": 37772280, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 1.665979912438836, | |
| "grad_norm": 11.66939874014716, | |
| "learning_rate": 7.407552634208714e-06, | |
| "loss": 0.2229, | |
| "num_input_tokens_seen": 37830800, | |
| "step": 3235 | |
| }, | |
| { | |
| "epoch": 1.6685552407932012, | |
| "grad_norm": 5.949219050013212, | |
| "learning_rate": 7.2963632284090756e-06, | |
| "loss": 0.1795, | |
| "num_input_tokens_seen": 37889280, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.6711305691475662, | |
| "grad_norm": 6.566491462966474, | |
| "learning_rate": 7.185948922515762e-06, | |
| "loss": 0.2316, | |
| "num_input_tokens_seen": 37947728, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 1.6737058975019314, | |
| "grad_norm": 6.379883324544748, | |
| "learning_rate": 7.076311720623108e-06, | |
| "loss": 0.2072, | |
| "num_input_tokens_seen": 38006200, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.6737058975019314, | |
| "eval_loss": 0.2405671775341034, | |
| "eval_runtime": 20.709, | |
| "eval_samples_per_second": 2.897, | |
| "eval_steps_per_second": 0.724, | |
| "num_input_tokens_seen": 38006200, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.6762812258562967, | |
| "grad_norm": 3.5869080263938082, | |
| "learning_rate": 6.967453612720543e-06, | |
| "loss": 0.2139, | |
| "num_input_tokens_seen": 38064672, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 1.678856554210662, | |
| "grad_norm": 6.877217191111715, | |
| "learning_rate": 6.859376574656395e-06, | |
| "loss": 0.2038, | |
| "num_input_tokens_seen": 38123192, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.6814318825650272, | |
| "grad_norm": 3.2559262371448146, | |
| "learning_rate": 6.7520825681020476e-06, | |
| "loss": 0.232, | |
| "num_input_tokens_seen": 38181696, | |
| "step": 3265 | |
| }, | |
| { | |
| "epoch": 1.6840072109193922, | |
| "grad_norm": 8.785530689010578, | |
| "learning_rate": 6.6455735405163145e-06, | |
| "loss": 0.1632, | |
| "num_input_tokens_seen": 38240216, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 1.6865825392737575, | |
| "grad_norm": 5.531242921031575, | |
| "learning_rate": 6.539851425110138e-06, | |
| "loss": 0.1423, | |
| "num_input_tokens_seen": 38298688, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 1.6891578676281225, | |
| "grad_norm": 4.0644227405062345, | |
| "learning_rate": 6.434918140811447e-06, | |
| "loss": 0.1673, | |
| "num_input_tokens_seen": 38357128, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.6917331959824877, | |
| "grad_norm": 2.3469449774677957, | |
| "learning_rate": 6.330775592230365e-06, | |
| "loss": 0.137, | |
| "num_input_tokens_seen": 38415600, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 1.694308524336853, | |
| "grad_norm": 13.136879672491618, | |
| "learning_rate": 6.2274256696246314e-06, | |
| "loss": 0.241, | |
| "num_input_tokens_seen": 38474112, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 1.6968838526912182, | |
| "grad_norm": 7.6753531592588295, | |
| "learning_rate": 6.124870248865289e-06, | |
| "loss": 0.1795, | |
| "num_input_tokens_seen": 38532624, | |
| "step": 3295 | |
| }, | |
| { | |
| "epoch": 1.6994591810455835, | |
| "grad_norm": 3.6160334005930412, | |
| "learning_rate": 6.023111191402603e-06, | |
| "loss": 0.2145, | |
| "num_input_tokens_seen": 38591128, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.6994591810455835, | |
| "eval_loss": 0.2692144513130188, | |
| "eval_runtime": 19.8713, | |
| "eval_samples_per_second": 3.019, | |
| "eval_steps_per_second": 0.755, | |
| "num_input_tokens_seen": 38591128, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.7020345093999485, | |
| "grad_norm": 4.245599320283208, | |
| "learning_rate": 5.922150344232358e-06, | |
| "loss": 0.1577, | |
| "num_input_tokens_seen": 38649640, | |
| "step": 3305 | |
| }, | |
| { | |
| "epoch": 1.7046098377543135, | |
| "grad_norm": 6.439585458462034, | |
| "learning_rate": 5.821989539862227e-06, | |
| "loss": 0.1865, | |
| "num_input_tokens_seen": 38708112, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 1.7071851661086788, | |
| "grad_norm": 4.332556239205023, | |
| "learning_rate": 5.722630596278617e-06, | |
| "loss": 0.2041, | |
| "num_input_tokens_seen": 38766624, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 1.709760494463044, | |
| "grad_norm": 8.300709555053524, | |
| "learning_rate": 5.624075316913568e-06, | |
| "loss": 0.2379, | |
| "num_input_tokens_seen": 38825104, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.7123358228174093, | |
| "grad_norm": 3.5209088708004423, | |
| "learning_rate": 5.526325490612106e-06, | |
| "loss": 0.1446, | |
| "num_input_tokens_seen": 38883560, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 1.7149111511717745, | |
| "grad_norm": 6.083318731157017, | |
| "learning_rate": 5.429382891599732e-06, | |
| "loss": 0.2214, | |
| "num_input_tokens_seen": 38942040, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 1.7174864795261395, | |
| "grad_norm": 5.245646471007174, | |
| "learning_rate": 5.333249279450231e-06, | |
| "loss": 0.1735, | |
| "num_input_tokens_seen": 39000488, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 1.7200618078805048, | |
| "grad_norm": 5.482406255032746, | |
| "learning_rate": 5.237926399053699e-06, | |
| "loss": 0.1996, | |
| "num_input_tokens_seen": 39058960, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.7226371362348698, | |
| "grad_norm": 6.210583442446586, | |
| "learning_rate": 5.143415980584948e-06, | |
| "loss": 0.2478, | |
| "num_input_tokens_seen": 39117416, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 1.725212464589235, | |
| "grad_norm": 5.159144010193508, | |
| "learning_rate": 5.049719739472009e-06, | |
| "loss": 0.2158, | |
| "num_input_tokens_seen": 39175888, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.725212464589235, | |
| "eval_loss": 0.2447366714477539, | |
| "eval_runtime": 20.3156, | |
| "eval_samples_per_second": 2.953, | |
| "eval_steps_per_second": 0.738, | |
| "num_input_tokens_seen": 39175888, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.7277877929436003, | |
| "grad_norm": 6.187206503231987, | |
| "learning_rate": 4.956839376365069e-06, | |
| "loss": 0.1795, | |
| "num_input_tokens_seen": 39234336, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 1.7303631212979655, | |
| "grad_norm": 4.18667410182292, | |
| "learning_rate": 4.864776577105584e-06, | |
| "loss": 0.1964, | |
| "num_input_tokens_seen": 39292800, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.7329384496523308, | |
| "grad_norm": 5.8485329747855275, | |
| "learning_rate": 4.773533012695663e-06, | |
| "loss": 0.1558, | |
| "num_input_tokens_seen": 39351272, | |
| "step": 3365 | |
| }, | |
| { | |
| "epoch": 1.7355137780066958, | |
| "grad_norm": 2.991559338645507, | |
| "learning_rate": 4.683110339267732e-06, | |
| "loss": 0.187, | |
| "num_input_tokens_seen": 39409736, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 1.738089106361061, | |
| "grad_norm": 3.7473435202339376, | |
| "learning_rate": 4.5935101980545295e-06, | |
| "loss": 0.1945, | |
| "num_input_tokens_seen": 39468176, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 1.740664434715426, | |
| "grad_norm": 3.664152846888827, | |
| "learning_rate": 4.5047342153592245e-06, | |
| "loss": 0.1475, | |
| "num_input_tokens_seen": 39526688, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.7432397630697913, | |
| "grad_norm": 2.0318595088746334, | |
| "learning_rate": 4.416784002526003e-06, | |
| "loss": 0.1334, | |
| "num_input_tokens_seen": 39585152, | |
| "step": 3385 | |
| }, | |
| { | |
| "epoch": 1.7458150914241566, | |
| "grad_norm": 4.706820298087635, | |
| "learning_rate": 4.329661155910736e-06, | |
| "loss": 0.1953, | |
| "num_input_tokens_seen": 39643640, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 1.7483904197785218, | |
| "grad_norm": 9.496012423646269, | |
| "learning_rate": 4.243367256852049e-06, | |
| "loss": 0.2158, | |
| "num_input_tokens_seen": 39702144, | |
| "step": 3395 | |
| }, | |
| { | |
| "epoch": 1.750965748132887, | |
| "grad_norm": 4.388828356289149, | |
| "learning_rate": 4.15790387164261e-06, | |
| "loss": 0.1488, | |
| "num_input_tokens_seen": 39760664, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.750965748132887, | |
| "eval_loss": 0.22250184416770935, | |
| "eval_runtime": 20.8021, | |
| "eval_samples_per_second": 2.884, | |
| "eval_steps_per_second": 0.721, | |
| "num_input_tokens_seen": 39760664, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.751995879474633, | |
| "num_input_tokens_seen": 39772368, | |
| "step": 3401, | |
| "total_flos": 2624309677719552.0, | |
| "train_loss": 9.810503915070576e-05, | |
| "train_runtime": 113.2963, | |
| "train_samples_per_second": 720.235, | |
| "train_steps_per_second": 30.01 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3400, | |
| "num_input_tokens_seen": 39772368, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2624309677719552.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |