| { | |
| "best_metric": 0.47318556904792786, | |
| "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4/lora/sft/checkpoint-1400", | |
| "epoch": 0.7210919392222508, | |
| "eval_steps": 50, | |
| "global_step": 1400, | |
| "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 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3882, | |
| "num_input_tokens_seen": 16374784, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1080424859697152.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |