| { | |
| "best_metric": 4.805818557739258, | |
| "best_model_checkpoint": "/users/hr1171/scratch/T5LAA/checkpoint-200000", | |
| "epoch": 4.10692, | |
| "eval_steps": 1000, | |
| "global_step": 200000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 0.42752909660339355, | |
| "learning_rate": 4.9875000000000006e-05, | |
| "loss": 9.2783, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 0.6895659565925598, | |
| "learning_rate": 4.975e-05, | |
| "loss": 8.7605, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "eval_accuracy": 0.033912700987924906, | |
| "eval_loss": 8.507349967956543, | |
| "eval_runtime": 91.5333, | |
| "eval_samples_per_second": 39.253, | |
| "eval_steps_per_second": 2.458, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 1.0673288106918335, | |
| "learning_rate": 4.962500000000001e-05, | |
| "loss": 8.3738, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6839419603347778, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 8.0954, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.03104558957478346, | |
| "eval_loss": 8.017916679382324, | |
| "eval_runtime": 91.927, | |
| "eval_samples_per_second": 39.085, | |
| "eval_steps_per_second": 2.448, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 0.950947105884552, | |
| "learning_rate": 4.937525e-05, | |
| "loss": 7.8869, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 1.0953532457351685, | |
| "learning_rate": 4.925025e-05, | |
| "loss": 7.7188, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "eval_accuracy": 0.03081947497059626, | |
| "eval_loss": 7.6839141845703125, | |
| "eval_runtime": 90.9808, | |
| "eval_samples_per_second": 39.492, | |
| "eval_steps_per_second": 2.473, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 0.5422408580780029, | |
| "learning_rate": 4.912525e-05, | |
| "loss": 7.5854, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.3019630908966064, | |
| "learning_rate": 4.900025e-05, | |
| "loss": 7.4459, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.032928381396291694, | |
| "eval_loss": 7.432972431182861, | |
| "eval_runtime": 92.5405, | |
| "eval_samples_per_second": 38.826, | |
| "eval_steps_per_second": 2.431, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 16.127534866333008, | |
| "learning_rate": 4.88755e-05, | |
| "loss": 7.3365, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 1.8640549182891846, | |
| "learning_rate": 4.875050000000001e-05, | |
| "loss": 7.2526, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "eval_accuracy": 0.032260649460460894, | |
| "eval_loss": 7.2563862800598145, | |
| "eval_runtime": 91.289, | |
| "eval_samples_per_second": 39.359, | |
| "eval_steps_per_second": 2.465, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 1.704673171043396, | |
| "learning_rate": 4.862575e-05, | |
| "loss": 7.1831, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 2.844064235687256, | |
| "learning_rate": 4.850075e-05, | |
| "loss": 7.1018, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.033544686544888576, | |
| "eval_loss": 7.128678321838379, | |
| "eval_runtime": 94.2173, | |
| "eval_samples_per_second": 38.135, | |
| "eval_steps_per_second": 2.388, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 1.2851128578186035, | |
| "learning_rate": 4.837575e-05, | |
| "loss": 7.0525, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 0.74603670835495, | |
| "learning_rate": 4.825075e-05, | |
| "loss": 7.014, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "eval_accuracy": 0.03406153936155956, | |
| "eval_loss": 7.0242919921875, | |
| "eval_runtime": 91.5738, | |
| "eval_samples_per_second": 39.236, | |
| "eval_steps_per_second": 2.457, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 0.937613308429718, | |
| "learning_rate": 4.812575e-05, | |
| "loss": 6.9613, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.0788276195526123, | |
| "learning_rate": 4.800075e-05, | |
| "loss": 6.9585, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.03162039956436886, | |
| "eval_loss": 6.953730583190918, | |
| "eval_runtime": 98.804, | |
| "eval_samples_per_second": 36.365, | |
| "eval_steps_per_second": 2.277, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 0.7946870923042297, | |
| "learning_rate": 4.787575e-05, | |
| "loss": 6.9196, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 1.7380784749984741, | |
| "learning_rate": 4.775075e-05, | |
| "loss": 6.9082, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "eval_accuracy": 0.032857907650823, | |
| "eval_loss": 6.873142242431641, | |
| "eval_runtime": 100.6418, | |
| "eval_samples_per_second": 35.701, | |
| "eval_steps_per_second": 2.236, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 1.8795133829116821, | |
| "learning_rate": 4.7625750000000004e-05, | |
| "loss": 6.8796, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.129756212234497, | |
| "learning_rate": 4.7501e-05, | |
| "loss": 6.8857, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.032590025788220955, | |
| "eval_loss": 6.822448253631592, | |
| "eval_runtime": 96.3312, | |
| "eval_samples_per_second": 37.298, | |
| "eval_steps_per_second": 2.336, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 0.6531652212142944, | |
| "learning_rate": 4.7376e-05, | |
| "loss": 6.8436, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 1.2178057432174683, | |
| "learning_rate": 4.7251e-05, | |
| "loss": 6.8166, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "eval_accuracy": 0.032403501647221764, | |
| "eval_loss": 6.821002006530762, | |
| "eval_runtime": 95.9352, | |
| "eval_samples_per_second": 37.452, | |
| "eval_steps_per_second": 2.345, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 1.195275902748108, | |
| "learning_rate": 4.7126e-05, | |
| "loss": 6.8214, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.0131785869598389, | |
| "learning_rate": 4.700125e-05, | |
| "loss": 6.8225, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.033441832970420755, | |
| "eval_loss": 6.764980316162109, | |
| "eval_runtime": 94.995, | |
| "eval_samples_per_second": 37.823, | |
| "eval_steps_per_second": 2.369, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 2.522235870361328, | |
| "learning_rate": 4.687625000000001e-05, | |
| "loss": 6.7924, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 0.894263505935669, | |
| "learning_rate": 4.6751250000000004e-05, | |
| "loss": 6.791, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "eval_accuracy": 0.03224772473880158, | |
| "eval_loss": 6.734119415283203, | |
| "eval_runtime": 117.5831, | |
| "eval_samples_per_second": 30.557, | |
| "eval_steps_per_second": 1.914, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 2.9750237464904785, | |
| "learning_rate": 4.662625000000001e-05, | |
| "loss": 6.7703, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.03080153465271, | |
| "learning_rate": 4.6501250000000005e-05, | |
| "loss": 6.7786, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.03289967490923784, | |
| "eval_loss": 6.726984024047852, | |
| "eval_runtime": 103.0616, | |
| "eval_samples_per_second": 34.863, | |
| "eval_steps_per_second": 2.183, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 2.6716787815093994, | |
| "learning_rate": 4.63765e-05, | |
| "loss": 6.7565, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 0.8023720383644104, | |
| "learning_rate": 4.62515e-05, | |
| "loss": 6.7516, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "eval_accuracy": 0.03358686195240845, | |
| "eval_loss": 6.673779010772705, | |
| "eval_runtime": 97.0967, | |
| "eval_samples_per_second": 37.004, | |
| "eval_steps_per_second": 2.317, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 0.9706649780273438, | |
| "learning_rate": 4.61265e-05, | |
| "loss": 6.7337, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.0966403484344482, | |
| "learning_rate": 4.60015e-05, | |
| "loss": 6.7343, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.03371406842347646, | |
| "eval_loss": 6.695716857910156, | |
| "eval_runtime": 95.0805, | |
| "eval_samples_per_second": 37.789, | |
| "eval_steps_per_second": 2.366, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 0.998198390007019, | |
| "learning_rate": 4.58765e-05, | |
| "loss": 6.7044, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 0.5809659957885742, | |
| "learning_rate": 4.5751500000000004e-05, | |
| "loss": 6.7027, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "eval_accuracy": 0.03325081918926622, | |
| "eval_loss": 6.647298336029053, | |
| "eval_runtime": 111.1392, | |
| "eval_samples_per_second": 32.329, | |
| "eval_steps_per_second": 2.024, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 1.1927660703659058, | |
| "learning_rate": 4.56265e-05, | |
| "loss": 6.7058, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.1725599765777588, | |
| "learning_rate": 4.5501500000000005e-05, | |
| "loss": 6.6741, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.034510367327392044, | |
| "eval_loss": 6.625380039215088, | |
| "eval_runtime": 91.7433, | |
| "eval_samples_per_second": 39.164, | |
| "eval_steps_per_second": 2.452, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 1.0063527822494507, | |
| "learning_rate": 4.537675e-05, | |
| "loss": 6.7041, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 2.5089831352233887, | |
| "learning_rate": 4.525175e-05, | |
| "loss": 6.6426, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "eval_accuracy": 0.03386848483487988, | |
| "eval_loss": 6.642553806304932, | |
| "eval_runtime": 95.8961, | |
| "eval_samples_per_second": 37.468, | |
| "eval_steps_per_second": 2.346, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 1.1984361410140991, | |
| "learning_rate": 4.512675e-05, | |
| "loss": 6.6729, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.813727855682373, | |
| "learning_rate": 4.500175e-05, | |
| "loss": 6.6475, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.03304606438824231, | |
| "eval_loss": 6.6046462059021, | |
| "eval_runtime": 95.7736, | |
| "eval_samples_per_second": 37.516, | |
| "eval_steps_per_second": 2.349, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.1025, | |
| "grad_norm": 1.4854774475097656, | |
| "learning_rate": 4.4877000000000004e-05, | |
| "loss": 6.6445, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 1.47989022731781, | |
| "learning_rate": 4.4752e-05, | |
| "loss": 6.6649, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "eval_accuracy": 0.034226567649693784, | |
| "eval_loss": 6.570390224456787, | |
| "eval_runtime": 99.1817, | |
| "eval_samples_per_second": 36.226, | |
| "eval_steps_per_second": 2.269, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.1075, | |
| "grad_norm": 1.1667526960372925, | |
| "learning_rate": 4.4627000000000005e-05, | |
| "loss": 6.6509, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.3919010162353516, | |
| "learning_rate": 4.4502e-05, | |
| "loss": 6.619, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.032384726788390335, | |
| "eval_loss": 6.571103096008301, | |
| "eval_runtime": 95.7384, | |
| "eval_samples_per_second": 37.529, | |
| "eval_steps_per_second": 2.35, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 2.1141815185546875, | |
| "learning_rate": 4.437725e-05, | |
| "loss": 6.6248, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 2.2613210678100586, | |
| "learning_rate": 4.425225e-05, | |
| "loss": 6.6216, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "eval_accuracy": 0.03199086290203537, | |
| "eval_loss": 6.581330299377441, | |
| "eval_runtime": 91.9194, | |
| "eval_samples_per_second": 39.089, | |
| "eval_steps_per_second": 2.448, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.1175, | |
| "grad_norm": 1.3900034427642822, | |
| "learning_rate": 4.4127250000000003e-05, | |
| "loss": 6.5989, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.3075273036956787, | |
| "learning_rate": 4.400225e-05, | |
| "loss": 6.5812, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.033095314380249395, | |
| "eval_loss": 6.547011375427246, | |
| "eval_runtime": 94.3249, | |
| "eval_samples_per_second": 38.092, | |
| "eval_steps_per_second": 2.385, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.1225, | |
| "grad_norm": 1.2836869955062866, | |
| "learning_rate": 4.387750000000001e-05, | |
| "loss": 6.597, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.1456223726272583, | |
| "learning_rate": 4.375275e-05, | |
| "loss": 6.5995, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "eval_accuracy": 0.033780188578491493, | |
| "eval_loss": 6.51839542388916, | |
| "eval_runtime": 93.2456, | |
| "eval_samples_per_second": 38.533, | |
| "eval_steps_per_second": 2.413, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.1275, | |
| "grad_norm": 1.2860591411590576, | |
| "learning_rate": 4.362775e-05, | |
| "loss": 6.5882, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.200269103050232, | |
| "learning_rate": 4.350275e-05, | |
| "loss": 6.5891, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.03334578188103678, | |
| "eval_loss": 6.508150100708008, | |
| "eval_runtime": 90.9178, | |
| "eval_samples_per_second": 39.519, | |
| "eval_steps_per_second": 2.475, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.1325, | |
| "grad_norm": 1.4053945541381836, | |
| "learning_rate": 4.337775e-05, | |
| "loss": 6.5754, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": 1.9518871307373047, | |
| "learning_rate": 4.3252750000000004e-05, | |
| "loss": 6.5767, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "eval_accuracy": 0.03279600503655996, | |
| "eval_loss": 6.481350898742676, | |
| "eval_runtime": 93.0531, | |
| "eval_samples_per_second": 38.612, | |
| "eval_steps_per_second": 2.418, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.1375, | |
| "grad_norm": 0.9082052111625671, | |
| "learning_rate": 4.312775e-05, | |
| "loss": 6.5661, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.2394309043884277, | |
| "learning_rate": 4.3002750000000004e-05, | |
| "loss": 6.5387, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.03242513354978841, | |
| "eval_loss": 6.50333833694458, | |
| "eval_runtime": 91.851, | |
| "eval_samples_per_second": 39.118, | |
| "eval_steps_per_second": 2.45, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.1425, | |
| "grad_norm": 1.4448879957199097, | |
| "learning_rate": 4.287775e-05, | |
| "loss": 6.541, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": 1.214563250541687, | |
| "learning_rate": 4.2752750000000005e-05, | |
| "loss": 6.5427, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "eval_accuracy": 0.03188379178681556, | |
| "eval_loss": 6.480025291442871, | |
| "eval_runtime": 103.8976, | |
| "eval_samples_per_second": 34.582, | |
| "eval_steps_per_second": 2.166, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.1475, | |
| "grad_norm": 0.9117876291275024, | |
| "learning_rate": 4.2628e-05, | |
| "loss": 6.5505, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.4780124425888062, | |
| "learning_rate": 4.2503e-05, | |
| "loss": 6.5139, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.03140081534586215, | |
| "eval_loss": 6.477231025695801, | |
| "eval_runtime": 97.6245, | |
| "eval_samples_per_second": 36.804, | |
| "eval_steps_per_second": 2.305, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.1525, | |
| "grad_norm": 0.9774089455604553, | |
| "learning_rate": 4.2378e-05, | |
| "loss": 6.5255, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": 1.5147466659545898, | |
| "learning_rate": 4.225325e-05, | |
| "loss": 6.5186, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "eval_accuracy": 0.03227180553599841, | |
| "eval_loss": 6.446476936340332, | |
| "eval_runtime": 92.5361, | |
| "eval_samples_per_second": 38.828, | |
| "eval_steps_per_second": 2.431, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.1575, | |
| "grad_norm": 1.4620882272720337, | |
| "learning_rate": 4.2128250000000004e-05, | |
| "loss": 6.5019, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.446492314338684, | |
| "learning_rate": 4.200325e-05, | |
| "loss": 6.5233, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.03262907205260226, | |
| "eval_loss": 6.422818660736084, | |
| "eval_runtime": 91.1245, | |
| "eval_samples_per_second": 39.43, | |
| "eval_steps_per_second": 2.469, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.1625, | |
| "grad_norm": 1.022921085357666, | |
| "learning_rate": 4.1878250000000005e-05, | |
| "loss": 6.4829, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": 1.4783859252929688, | |
| "learning_rate": 4.175325e-05, | |
| "loss": 6.4659, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "eval_accuracy": 0.031788829095045004, | |
| "eval_loss": 6.436858654022217, | |
| "eval_runtime": 95.3969, | |
| "eval_samples_per_second": 37.664, | |
| "eval_steps_per_second": 2.359, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.1675, | |
| "grad_norm": 3.6760544776916504, | |
| "learning_rate": 4.162825e-05, | |
| "loss": 6.5373, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 2.7687697410583496, | |
| "learning_rate": 4.15035e-05, | |
| "loss": 6.4819, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.033804269375688326, | |
| "eval_loss": 6.397607803344727, | |
| "eval_runtime": 94.8411, | |
| "eval_samples_per_second": 37.884, | |
| "eval_steps_per_second": 2.372, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.1725, | |
| "grad_norm": 1.5380724668502808, | |
| "learning_rate": 4.1378500000000004e-05, | |
| "loss": 6.4747, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 1.8788790702819824, | |
| "learning_rate": 4.12535e-05, | |
| "loss": 6.4735, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "eval_accuracy": 0.033044159692418834, | |
| "eval_loss": 6.411598205566406, | |
| "eval_runtime": 92.6637, | |
| "eval_samples_per_second": 38.775, | |
| "eval_steps_per_second": 2.428, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.1775, | |
| "grad_norm": 1.3821016550064087, | |
| "learning_rate": 4.1128500000000004e-05, | |
| "loss": 6.4538, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 2.0021932125091553, | |
| "learning_rate": 4.10035e-05, | |
| "loss": 6.4659, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.031257418960294575, | |
| "eval_loss": 6.4191389083862305, | |
| "eval_runtime": 102.9081, | |
| "eval_samples_per_second": 34.915, | |
| "eval_steps_per_second": 2.186, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.1825, | |
| "grad_norm": 0.9058569073677063, | |
| "learning_rate": 4.0878500000000005e-05, | |
| "loss": 6.4517, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": 1.922741174697876, | |
| "learning_rate": 4.07535e-05, | |
| "loss": 6.443, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "eval_accuracy": 0.03225167018015021, | |
| "eval_loss": 6.378974437713623, | |
| "eval_runtime": 105.2589, | |
| "eval_samples_per_second": 34.135, | |
| "eval_steps_per_second": 2.138, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 2.298774480819702, | |
| "learning_rate": 4.0628500000000006e-05, | |
| "loss": 6.4497, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 1.7634875774383545, | |
| "learning_rate": 4.050375e-05, | |
| "loss": 6.448, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.0315727821687819, | |
| "eval_loss": 6.390995979309082, | |
| "eval_runtime": 97.37, | |
| "eval_samples_per_second": 36.9, | |
| "eval_steps_per_second": 2.311, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.1925, | |
| "grad_norm": 1.2913744449615479, | |
| "learning_rate": 4.0378750000000004e-05, | |
| "loss": 6.4289, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": 1.5835742950439453, | |
| "learning_rate": 4.025375e-05, | |
| "loss": 6.421, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "eval_accuracy": 0.0321972502994794, | |
| "eval_loss": 6.371878147125244, | |
| "eval_runtime": 96.1284, | |
| "eval_samples_per_second": 37.377, | |
| "eval_steps_per_second": 2.341, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.1975, | |
| "grad_norm": 1.9730321168899536, | |
| "learning_rate": 4.0128750000000004e-05, | |
| "loss": 6.4357, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.8616057634353638, | |
| "learning_rate": 4.0004000000000005e-05, | |
| "loss": 6.4127, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.03198569301337165, | |
| "eval_loss": 6.374399662017822, | |
| "eval_runtime": 92.9371, | |
| "eval_samples_per_second": 38.661, | |
| "eval_steps_per_second": 2.421, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.2025, | |
| "grad_norm": 1.4953457117080688, | |
| "learning_rate": 3.9879e-05, | |
| "loss": 6.4233, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "grad_norm": 1.2381442785263062, | |
| "learning_rate": 3.9754e-05, | |
| "loss": 6.4213, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "eval_accuracy": 0.03152353217677482, | |
| "eval_loss": 6.381062030792236, | |
| "eval_runtime": 130.2985, | |
| "eval_samples_per_second": 27.575, | |
| "eval_steps_per_second": 1.727, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.2075, | |
| "grad_norm": 1.2648102045059204, | |
| "learning_rate": 3.9628999999999996e-05, | |
| "loss": 6.4195, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 1.322369933128357, | |
| "learning_rate": 3.9504250000000004e-05, | |
| "loss": 6.42, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.031080010149307745, | |
| "eval_loss": 6.351558685302734, | |
| "eval_runtime": 97.1612, | |
| "eval_samples_per_second": 36.98, | |
| "eval_steps_per_second": 2.316, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.2125, | |
| "grad_norm": 1.8557090759277344, | |
| "learning_rate": 3.937925e-05, | |
| "loss": 6.4013, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "grad_norm": 2.21213436126709, | |
| "learning_rate": 3.9254250000000005e-05, | |
| "loss": 6.414, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "eval_accuracy": 0.03100681540980551, | |
| "eval_loss": 6.333887100219727, | |
| "eval_runtime": 96.5646, | |
| "eval_samples_per_second": 37.208, | |
| "eval_steps_per_second": 2.33, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.2175, | |
| "grad_norm": 1.817885160446167, | |
| "learning_rate": 3.912925e-05, | |
| "loss": 6.4259, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.3436046838760376, | |
| "learning_rate": 3.90045e-05, | |
| "loss": 6.3899, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.03152108328214463, | |
| "eval_loss": 6.350229263305664, | |
| "eval_runtime": 110.9053, | |
| "eval_samples_per_second": 32.397, | |
| "eval_steps_per_second": 2.029, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.2225, | |
| "grad_norm": 1.5731582641601562, | |
| "learning_rate": 3.887975e-05, | |
| "loss": 6.3756, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.00173, | |
| "grad_norm": 1.9111318588256836, | |
| "learning_rate": 3.875475e-05, | |
| "loss": 6.3715, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.00173, | |
| "eval_accuracy": 0.03136843551686302, | |
| "eval_loss": 6.31905460357666, | |
| "eval_runtime": 98.2753, | |
| "eval_samples_per_second": 36.561, | |
| "eval_steps_per_second": 2.289, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.00423, | |
| "grad_norm": 1.8441720008850098, | |
| "learning_rate": 3.8629750000000004e-05, | |
| "loss": 6.3367, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.00673, | |
| "grad_norm": 1.122545838356018, | |
| "learning_rate": 3.850475e-05, | |
| "loss": 6.3588, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.00673, | |
| "eval_accuracy": 0.03153237540738382, | |
| "eval_loss": 6.308679103851318, | |
| "eval_runtime": 103.4383, | |
| "eval_samples_per_second": 34.736, | |
| "eval_steps_per_second": 2.175, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.00923, | |
| "grad_norm": 1.5169119834899902, | |
| "learning_rate": 3.8379750000000005e-05, | |
| "loss": 6.3561, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.01173, | |
| "grad_norm": 2.325814723968506, | |
| "learning_rate": 3.825475e-05, | |
| "loss": 6.3802, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.01173, | |
| "eval_accuracy": 0.03152312402766979, | |
| "eval_loss": 6.2924675941467285, | |
| "eval_runtime": 92.1003, | |
| "eval_samples_per_second": 39.012, | |
| "eval_steps_per_second": 2.443, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.01423, | |
| "grad_norm": 2.1370677947998047, | |
| "learning_rate": 3.8129750000000005e-05, | |
| "loss": 6.3738, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.01673, | |
| "grad_norm": 1.6703208684921265, | |
| "learning_rate": 3.8005e-05, | |
| "loss": 6.3708, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.01673, | |
| "eval_accuracy": 0.03175032702947041, | |
| "eval_loss": 6.304358959197998, | |
| "eval_runtime": 92.2936, | |
| "eval_samples_per_second": 38.93, | |
| "eval_steps_per_second": 2.438, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.01923, | |
| "grad_norm": 2.00714111328125, | |
| "learning_rate": 3.788e-05, | |
| "loss": 6.3374, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.02173, | |
| "grad_norm": 1.4548686742782593, | |
| "learning_rate": 3.7755e-05, | |
| "loss": 6.3189, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.02173, | |
| "eval_accuracy": 0.030815393479545948, | |
| "eval_loss": 6.318645477294922, | |
| "eval_runtime": 91.5251, | |
| "eval_samples_per_second": 39.257, | |
| "eval_steps_per_second": 2.458, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.02423, | |
| "grad_norm": 1.719914436340332, | |
| "learning_rate": 3.7630000000000004e-05, | |
| "loss": 6.3527, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.02673, | |
| "grad_norm": 1.7514491081237793, | |
| "learning_rate": 3.7505e-05, | |
| "loss": 6.3545, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.02673, | |
| "eval_accuracy": 0.030726689074052533, | |
| "eval_loss": 6.3023600578308105, | |
| "eval_runtime": 92.8566, | |
| "eval_samples_per_second": 38.694, | |
| "eval_steps_per_second": 2.423, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.02923, | |
| "grad_norm": 1.5919264554977417, | |
| "learning_rate": 3.7380000000000005e-05, | |
| "loss": 6.3373, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.03173, | |
| "grad_norm": 2.918543815612793, | |
| "learning_rate": 3.7255e-05, | |
| "loss": 6.3255, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.03173, | |
| "eval_accuracy": 0.030562341034426697, | |
| "eval_loss": 6.30160665512085, | |
| "eval_runtime": 92.2685, | |
| "eval_samples_per_second": 38.941, | |
| "eval_steps_per_second": 2.439, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.03423, | |
| "grad_norm": 2.352147340774536, | |
| "learning_rate": 3.713025e-05, | |
| "loss": 6.3399, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.03673, | |
| "grad_norm": 2.9179019927978516, | |
| "learning_rate": 3.700525e-05, | |
| "loss": 6.3162, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.03673, | |
| "eval_accuracy": 0.03165182704545624, | |
| "eval_loss": 6.283206462860107, | |
| "eval_runtime": 91.4548, | |
| "eval_samples_per_second": 39.287, | |
| "eval_steps_per_second": 2.46, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.03923, | |
| "grad_norm": 1.9093166589736938, | |
| "learning_rate": 3.6880249999999996e-05, | |
| "loss": 6.2978, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.04173, | |
| "grad_norm": 1.792311668395996, | |
| "learning_rate": 3.675525e-05, | |
| "loss": 6.309, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.04173, | |
| "eval_accuracy": 0.030514859688541417, | |
| "eval_loss": 6.273383140563965, | |
| "eval_runtime": 99.4034, | |
| "eval_samples_per_second": 36.146, | |
| "eval_steps_per_second": 2.264, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.04423, | |
| "grad_norm": 1.311917781829834, | |
| "learning_rate": 3.663025e-05, | |
| "loss": 6.303, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.04673, | |
| "grad_norm": 1.8375986814498901, | |
| "learning_rate": 3.6505500000000005e-05, | |
| "loss": 6.314, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.04673, | |
| "eval_accuracy": 0.03121020971381265, | |
| "eval_loss": 6.250477313995361, | |
| "eval_runtime": 91.4556, | |
| "eval_samples_per_second": 39.287, | |
| "eval_steps_per_second": 2.46, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.04923, | |
| "grad_norm": 1.672000527381897, | |
| "learning_rate": 3.63805e-05, | |
| "loss": 6.296, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.05173, | |
| "grad_norm": 1.5362963676452637, | |
| "learning_rate": 3.6255500000000005e-05, | |
| "loss": 6.293, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.05173, | |
| "eval_accuracy": 0.031686927868488916, | |
| "eval_loss": 6.259158611297607, | |
| "eval_runtime": 90.5801, | |
| "eval_samples_per_second": 39.667, | |
| "eval_steps_per_second": 2.484, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.05423, | |
| "grad_norm": 1.3914135694503784, | |
| "learning_rate": 3.61305e-05, | |
| "loss": 6.2675, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.05673, | |
| "grad_norm": 1.923341989517212, | |
| "learning_rate": 3.6005500000000006e-05, | |
| "loss": 6.2813, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.05673, | |
| "eval_accuracy": 0.0307902242847357, | |
| "eval_loss": 6.2271199226379395, | |
| "eval_runtime": 108.1752, | |
| "eval_samples_per_second": 33.215, | |
| "eval_steps_per_second": 2.08, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.05923, | |
| "grad_norm": 1.8110476732254028, | |
| "learning_rate": 3.58805e-05, | |
| "loss": 6.2753, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.06173, | |
| "grad_norm": 3.4441418647766113, | |
| "learning_rate": 3.575575e-05, | |
| "loss": 6.2781, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.06173, | |
| "eval_accuracy": 0.030471595883408125, | |
| "eval_loss": 6.252005100250244, | |
| "eval_runtime": 119.6594, | |
| "eval_samples_per_second": 30.027, | |
| "eval_steps_per_second": 1.88, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.06423, | |
| "grad_norm": 2.464296340942383, | |
| "learning_rate": 3.563075e-05, | |
| "loss": 6.2624, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.06673, | |
| "grad_norm": 1.7239878177642822, | |
| "learning_rate": 3.5505750000000005e-05, | |
| "loss": 6.2625, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.06673, | |
| "eval_accuracy": 0.03089743144965719, | |
| "eval_loss": 6.220044136047363, | |
| "eval_runtime": 91.2098, | |
| "eval_samples_per_second": 39.393, | |
| "eval_steps_per_second": 2.467, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.06923, | |
| "grad_norm": 3.2937629222869873, | |
| "learning_rate": 3.538075e-05, | |
| "loss": 6.2822, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.07173, | |
| "grad_norm": 2.1419010162353516, | |
| "learning_rate": 3.5255750000000005e-05, | |
| "loss": 6.2638, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.07173, | |
| "eval_accuracy": 0.03013310422563571, | |
| "eval_loss": 6.199001789093018, | |
| "eval_runtime": 92.4858, | |
| "eval_samples_per_second": 38.849, | |
| "eval_steps_per_second": 2.433, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.07423, | |
| "grad_norm": 1.3166654109954834, | |
| "learning_rate": 3.5131e-05, | |
| "loss": 6.2721, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.07673, | |
| "grad_norm": 2.0733723640441895, | |
| "learning_rate": 3.5005999999999997e-05, | |
| "loss": 6.2455, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.07673, | |
| "eval_accuracy": 0.031115110972340414, | |
| "eval_loss": 6.203488349914551, | |
| "eval_runtime": 110.8283, | |
| "eval_samples_per_second": 32.42, | |
| "eval_steps_per_second": 2.03, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.07923, | |
| "grad_norm": 1.416002631187439, | |
| "learning_rate": 3.4881e-05, | |
| "loss": 6.2489, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.08173, | |
| "grad_norm": 2.517613172531128, | |
| "learning_rate": 3.4756e-05, | |
| "loss": 6.253, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.08173, | |
| "eval_accuracy": 0.03135415029818693, | |
| "eval_loss": 6.215968608856201, | |
| "eval_runtime": 101.5668, | |
| "eval_samples_per_second": 35.376, | |
| "eval_steps_per_second": 2.215, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.08423, | |
| "grad_norm": 1.8757721185684204, | |
| "learning_rate": 3.4631e-05, | |
| "loss": 6.2412, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.08673, | |
| "grad_norm": 1.971893072128296, | |
| "learning_rate": 3.4506e-05, | |
| "loss": 6.2408, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.08673, | |
| "eval_accuracy": 0.030135144971160866, | |
| "eval_loss": 6.208563804626465, | |
| "eval_runtime": 92.1622, | |
| "eval_samples_per_second": 38.986, | |
| "eval_steps_per_second": 2.441, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.08923, | |
| "grad_norm": 1.688067078590393, | |
| "learning_rate": 3.4381e-05, | |
| "loss": 6.2355, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.09173, | |
| "grad_norm": 1.7897340059280396, | |
| "learning_rate": 3.4256e-05, | |
| "loss": 6.2332, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.09173, | |
| "eval_accuracy": 0.029759647794532298, | |
| "eval_loss": 6.192452907562256, | |
| "eval_runtime": 91.4457, | |
| "eval_samples_per_second": 39.291, | |
| "eval_steps_per_second": 2.46, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.09423, | |
| "grad_norm": 1.7778252363204956, | |
| "learning_rate": 3.4131250000000006e-05, | |
| "loss": 6.2307, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.09673, | |
| "grad_norm": 2.530224561691284, | |
| "learning_rate": 3.400625e-05, | |
| "loss": 6.2182, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.09673, | |
| "eval_accuracy": 0.030409149070338377, | |
| "eval_loss": 6.166359901428223, | |
| "eval_runtime": 93.8927, | |
| "eval_samples_per_second": 38.267, | |
| "eval_steps_per_second": 2.396, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.09923, | |
| "grad_norm": 2.602126121520996, | |
| "learning_rate": 3.388125e-05, | |
| "loss": 6.2163, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.10173, | |
| "grad_norm": 2.1342318058013916, | |
| "learning_rate": 3.37565e-05, | |
| "loss": 6.2301, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.10173, | |
| "eval_accuracy": 0.030321941211563407, | |
| "eval_loss": 6.158266067504883, | |
| "eval_runtime": 97.9208, | |
| "eval_samples_per_second": 36.693, | |
| "eval_steps_per_second": 2.298, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.10423, | |
| "grad_norm": 1.733469843864441, | |
| "learning_rate": 3.363175e-05, | |
| "loss": 6.2318, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.10673, | |
| "grad_norm": 3.459373950958252, | |
| "learning_rate": 3.3506750000000006e-05, | |
| "loss": 6.2379, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.10673, | |
| "eval_accuracy": 0.030465745746236016, | |
| "eval_loss": 6.1884002685546875, | |
| "eval_runtime": 95.0294, | |
| "eval_samples_per_second": 37.809, | |
| "eval_steps_per_second": 2.368, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.10923, | |
| "grad_norm": 2.1125833988189697, | |
| "learning_rate": 3.338175e-05, | |
| "loss": 6.2044, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.11173, | |
| "grad_norm": 1.7863088846206665, | |
| "learning_rate": 3.3256750000000006e-05, | |
| "loss": 6.2211, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.11173, | |
| "eval_accuracy": 0.03108939757872346, | |
| "eval_loss": 6.161408424377441, | |
| "eval_runtime": 94.8294, | |
| "eval_samples_per_second": 37.889, | |
| "eval_steps_per_second": 2.373, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.11423, | |
| "grad_norm": 2.1072041988372803, | |
| "learning_rate": 3.3131750000000003e-05, | |
| "loss": 6.2086, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.11673, | |
| "grad_norm": 1.647073745727539, | |
| "learning_rate": 3.300675e-05, | |
| "loss": 6.2018, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.11673, | |
| "eval_accuracy": 0.030671997093978373, | |
| "eval_loss": 6.1607513427734375, | |
| "eval_runtime": 91.8853, | |
| "eval_samples_per_second": 39.103, | |
| "eval_steps_per_second": 2.449, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.11923, | |
| "grad_norm": 2.174481153488159, | |
| "learning_rate": 3.288175e-05, | |
| "loss": 6.1837, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.12173, | |
| "grad_norm": 1.5667694807052612, | |
| "learning_rate": 3.275675e-05, | |
| "loss": 6.1969, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.12173, | |
| "eval_accuracy": 0.030524519217360487, | |
| "eval_loss": 6.133298397064209, | |
| "eval_runtime": 140.1649, | |
| "eval_samples_per_second": 25.634, | |
| "eval_steps_per_second": 1.605, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.12423, | |
| "grad_norm": 2.3138535022735596, | |
| "learning_rate": 3.263175e-05, | |
| "loss": 6.2001, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.12673, | |
| "grad_norm": 2.0583817958831787, | |
| "learning_rate": 3.2507000000000006e-05, | |
| "loss": 6.1989, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.12673, | |
| "eval_accuracy": 0.030227250619196205, | |
| "eval_loss": 6.131419658660889, | |
| "eval_runtime": 92.9886, | |
| "eval_samples_per_second": 38.639, | |
| "eval_steps_per_second": 2.42, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.12923, | |
| "grad_norm": 2.3746538162231445, | |
| "learning_rate": 3.2382e-05, | |
| "loss": 6.2039, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.1317300000000001, | |
| "grad_norm": 2.146286964416504, | |
| "learning_rate": 3.2257000000000006e-05, | |
| "loss": 6.2058, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.1317300000000001, | |
| "eval_accuracy": 0.029887942663213724, | |
| "eval_loss": 6.151033878326416, | |
| "eval_runtime": 115.2908, | |
| "eval_samples_per_second": 31.165, | |
| "eval_steps_per_second": 1.952, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.13423, | |
| "grad_norm": 1.7566348314285278, | |
| "learning_rate": 3.2132e-05, | |
| "loss": 6.1963, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.13673, | |
| "grad_norm": 1.7382845878601074, | |
| "learning_rate": 3.2007e-05, | |
| "loss": 6.1994, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.13673, | |
| "eval_accuracy": 0.02953489368736187, | |
| "eval_loss": 6.144207954406738, | |
| "eval_runtime": 106.6363, | |
| "eval_samples_per_second": 33.694, | |
| "eval_steps_per_second": 2.11, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.13923, | |
| "grad_norm": 2.3577260971069336, | |
| "learning_rate": 3.188225e-05, | |
| "loss": 6.1737, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.14173, | |
| "grad_norm": 1.917486310005188, | |
| "learning_rate": 3.175725e-05, | |
| "loss": 6.1715, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.14173, | |
| "eval_accuracy": 0.029909030366973663, | |
| "eval_loss": 6.13955545425415, | |
| "eval_runtime": 92.2027, | |
| "eval_samples_per_second": 38.968, | |
| "eval_steps_per_second": 2.44, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.14423, | |
| "grad_norm": 2.7271180152893066, | |
| "learning_rate": 3.163225e-05, | |
| "loss": 6.1803, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.14673, | |
| "grad_norm": 1.5343501567840576, | |
| "learning_rate": 3.150725e-05, | |
| "loss": 6.1849, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.14673, | |
| "eval_accuracy": 0.029956919861963974, | |
| "eval_loss": 6.108343601226807, | |
| "eval_runtime": 94.132, | |
| "eval_samples_per_second": 38.17, | |
| "eval_steps_per_second": 2.39, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.14923, | |
| "grad_norm": 2.063617706298828, | |
| "learning_rate": 3.138225e-05, | |
| "loss": 6.1601, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.15173, | |
| "grad_norm": 1.7743293046951294, | |
| "learning_rate": 3.1257500000000004e-05, | |
| "loss": 6.1709, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.15173, | |
| "eval_accuracy": 0.030241399788170614, | |
| "eval_loss": 6.083706855773926, | |
| "eval_runtime": 91.1389, | |
| "eval_samples_per_second": 39.423, | |
| "eval_steps_per_second": 2.469, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.15423, | |
| "grad_norm": 2.292107343673706, | |
| "learning_rate": 3.11325e-05, | |
| "loss": 6.1532, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.15673, | |
| "grad_norm": 1.8466393947601318, | |
| "learning_rate": 3.10075e-05, | |
| "loss": 6.1669, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.15673, | |
| "eval_accuracy": 0.02916497454850206, | |
| "eval_loss": 6.0924787521362305, | |
| "eval_runtime": 93.9311, | |
| "eval_samples_per_second": 38.251, | |
| "eval_steps_per_second": 2.395, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.15923, | |
| "grad_norm": 2.8982222080230713, | |
| "learning_rate": 3.08825e-05, | |
| "loss": 6.1602, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.16173, | |
| "grad_norm": 2.5072736740112305, | |
| "learning_rate": 3.07575e-05, | |
| "loss": 6.16, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.16173, | |
| "eval_accuracy": 0.029235040144865724, | |
| "eval_loss": 6.0938825607299805, | |
| "eval_runtime": 98.3356, | |
| "eval_samples_per_second": 36.538, | |
| "eval_steps_per_second": 2.288, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.1642299999999999, | |
| "grad_norm": 1.8945947885513306, | |
| "learning_rate": 3.06325e-05, | |
| "loss": 6.1295, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.16673, | |
| "grad_norm": 3.0348196029663086, | |
| "learning_rate": 3.0507750000000003e-05, | |
| "loss": 6.1637, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.16673, | |
| "eval_accuracy": 0.029682371563979754, | |
| "eval_loss": 6.0949811935424805, | |
| "eval_runtime": 95.4626, | |
| "eval_samples_per_second": 37.638, | |
| "eval_steps_per_second": 2.357, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.16923, | |
| "grad_norm": 1.6715943813323975, | |
| "learning_rate": 3.038275e-05, | |
| "loss": 6.1729, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.17173, | |
| "grad_norm": 1.6270267963409424, | |
| "learning_rate": 3.025775e-05, | |
| "loss": 6.1446, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.17173, | |
| "eval_accuracy": 0.029339254216350318, | |
| "eval_loss": 6.08974552154541, | |
| "eval_runtime": 91.6584, | |
| "eval_samples_per_second": 39.2, | |
| "eval_steps_per_second": 2.455, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.17423, | |
| "grad_norm": 2.177884817123413, | |
| "learning_rate": 3.0132750000000004e-05, | |
| "loss": 6.1339, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.17673, | |
| "grad_norm": 2.0329620838165283, | |
| "learning_rate": 3.000775e-05, | |
| "loss": 6.1231, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.17673, | |
| "eval_accuracy": 0.02976223273886416, | |
| "eval_loss": 6.078031063079834, | |
| "eval_runtime": 98.9799, | |
| "eval_samples_per_second": 36.3, | |
| "eval_steps_per_second": 2.273, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.17923, | |
| "grad_norm": 2.5211639404296875, | |
| "learning_rate": 2.9883e-05, | |
| "loss": 6.1297, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 1.18173, | |
| "grad_norm": 3.6579315662384033, | |
| "learning_rate": 2.9758000000000002e-05, | |
| "loss": 6.1287, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.18173, | |
| "eval_accuracy": 0.029048379954164854, | |
| "eval_loss": 6.091179370880127, | |
| "eval_runtime": 94.4808, | |
| "eval_samples_per_second": 38.029, | |
| "eval_steps_per_second": 2.381, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.18423, | |
| "grad_norm": 2.1335196495056152, | |
| "learning_rate": 2.9633e-05, | |
| "loss": 6.1302, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 1.18673, | |
| "grad_norm": 1.8634554147720337, | |
| "learning_rate": 2.9508000000000003e-05, | |
| "loss": 6.1196, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.18673, | |
| "eval_accuracy": 0.028964029139125106, | |
| "eval_loss": 6.08493709564209, | |
| "eval_runtime": 102.0825, | |
| "eval_samples_per_second": 35.197, | |
| "eval_steps_per_second": 2.204, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.18923, | |
| "grad_norm": 3.3065264225006104, | |
| "learning_rate": 2.938325e-05, | |
| "loss": 6.1363, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 1.19173, | |
| "grad_norm": 2.0532631874084473, | |
| "learning_rate": 2.9258250000000004e-05, | |
| "loss": 6.1136, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.19173, | |
| "eval_accuracy": 0.029438298399171184, | |
| "eval_loss": 6.061553478240967, | |
| "eval_runtime": 114.3059, | |
| "eval_samples_per_second": 31.433, | |
| "eval_steps_per_second": 1.968, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.1942300000000001, | |
| "grad_norm": 1.6184016466140747, | |
| "learning_rate": 2.913325e-05, | |
| "loss": 6.1084, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 1.19673, | |
| "grad_norm": 3.0933752059936523, | |
| "learning_rate": 2.9008250000000005e-05, | |
| "loss": 6.1135, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.19673, | |
| "eval_accuracy": 0.02910620107737759, | |
| "eval_loss": 6.051595211029053, | |
| "eval_runtime": 97.7568, | |
| "eval_samples_per_second": 36.754, | |
| "eval_steps_per_second": 2.302, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.19923, | |
| "grad_norm": 2.0492806434631348, | |
| "learning_rate": 2.888325e-05, | |
| "loss": 6.1135, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 1.20173, | |
| "grad_norm": 2.1396772861480713, | |
| "learning_rate": 2.87585e-05, | |
| "loss": 6.1157, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.20173, | |
| "eval_accuracy": 0.029641148504371616, | |
| "eval_loss": 6.051669120788574, | |
| "eval_runtime": 135.3455, | |
| "eval_samples_per_second": 26.547, | |
| "eval_steps_per_second": 1.662, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.20423, | |
| "grad_norm": 1.9825798273086548, | |
| "learning_rate": 2.8633500000000003e-05, | |
| "loss": 6.1003, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 1.20673, | |
| "grad_norm": 4.120855331420898, | |
| "learning_rate": 2.85085e-05, | |
| "loss": 6.1102, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.20673, | |
| "eval_accuracy": 0.029109058121112804, | |
| "eval_loss": 6.062215328216553, | |
| "eval_runtime": 93.9666, | |
| "eval_samples_per_second": 38.237, | |
| "eval_steps_per_second": 2.394, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.20923, | |
| "grad_norm": 1.7419639825820923, | |
| "learning_rate": 2.83835e-05, | |
| "loss": 6.1052, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 1.21173, | |
| "grad_norm": 1.9040395021438599, | |
| "learning_rate": 2.825875e-05, | |
| "loss": 6.1218, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.21173, | |
| "eval_accuracy": 0.02853969011959449, | |
| "eval_loss": 6.063874244689941, | |
| "eval_runtime": 91.0034, | |
| "eval_samples_per_second": 39.482, | |
| "eval_steps_per_second": 2.472, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.21423, | |
| "grad_norm": 3.0082874298095703, | |
| "learning_rate": 2.813375e-05, | |
| "loss": 6.1101, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 1.21673, | |
| "grad_norm": 1.843441367149353, | |
| "learning_rate": 2.8008750000000002e-05, | |
| "loss": 6.1104, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.21673, | |
| "eval_accuracy": 0.029038720425345787, | |
| "eval_loss": 6.0515055656433105, | |
| "eval_runtime": 92.5288, | |
| "eval_samples_per_second": 38.831, | |
| "eval_steps_per_second": 2.432, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.21923, | |
| "grad_norm": 1.9573761224746704, | |
| "learning_rate": 2.7883750000000002e-05, | |
| "loss": 6.1118, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 1.22173, | |
| "grad_norm": 2.1925711631774902, | |
| "learning_rate": 2.7759000000000003e-05, | |
| "loss": 6.0777, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 1.22173, | |
| "eval_accuracy": 0.02947503181862398, | |
| "eval_loss": 6.0190510749816895, | |
| "eval_runtime": 91.9724, | |
| "eval_samples_per_second": 39.066, | |
| "eval_steps_per_second": 2.446, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.00096, | |
| "grad_norm": 2.6323490142822266, | |
| "learning_rate": 2.7634e-05, | |
| "loss": 6.1035, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.00346, | |
| "grad_norm": 2.907351016998291, | |
| "learning_rate": 2.7509e-05, | |
| "loss": 6.051, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.00346, | |
| "eval_accuracy": 0.028725125862980264, | |
| "eval_loss": 6.004823207855225, | |
| "eval_runtime": 111.8414, | |
| "eval_samples_per_second": 32.126, | |
| "eval_steps_per_second": 2.012, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.00596, | |
| "grad_norm": 2.1557071208953857, | |
| "learning_rate": 2.7383999999999997e-05, | |
| "loss": 6.0777, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.00846, | |
| "grad_norm": 2.466111183166504, | |
| "learning_rate": 2.7259e-05, | |
| "loss": 6.065, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.00846, | |
| "eval_accuracy": 0.0288474345447879, | |
| "eval_loss": 6.030221462249756, | |
| "eval_runtime": 91.3043, | |
| "eval_samples_per_second": 39.352, | |
| "eval_steps_per_second": 2.464, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.01096, | |
| "grad_norm": 2.554461717605591, | |
| "learning_rate": 2.713425e-05, | |
| "loss": 6.1054, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.01346, | |
| "grad_norm": 2.1461994647979736, | |
| "learning_rate": 2.7009250000000002e-05, | |
| "loss": 6.0941, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.01346, | |
| "eval_accuracy": 0.028430578258849523, | |
| "eval_loss": 6.029834747314453, | |
| "eval_runtime": 137.2429, | |
| "eval_samples_per_second": 26.18, | |
| "eval_steps_per_second": 1.639, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.01596, | |
| "grad_norm": 1.8053221702575684, | |
| "learning_rate": 2.688425e-05, | |
| "loss": 6.0738, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.01846, | |
| "grad_norm": 1.9942346811294556, | |
| "learning_rate": 2.6759250000000003e-05, | |
| "loss": 6.0833, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.01846, | |
| "eval_accuracy": 0.02874675776554691, | |
| "eval_loss": 6.014132022857666, | |
| "eval_runtime": 96.8636, | |
| "eval_samples_per_second": 37.093, | |
| "eval_steps_per_second": 2.323, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.02096, | |
| "grad_norm": 1.6957967281341553, | |
| "learning_rate": 2.663425e-05, | |
| "loss": 6.0429, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.02346, | |
| "grad_norm": 2.633817672729492, | |
| "learning_rate": 2.6509500000000004e-05, | |
| "loss": 6.0816, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.02346, | |
| "eval_accuracy": 0.0281086846646817, | |
| "eval_loss": 6.0137176513671875, | |
| "eval_runtime": 97.3569, | |
| "eval_samples_per_second": 36.905, | |
| "eval_steps_per_second": 2.311, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.02596, | |
| "grad_norm": 2.664257049560547, | |
| "learning_rate": 2.6384750000000002e-05, | |
| "loss": 6.0638, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 2.02846, | |
| "grad_norm": 2.147036552429199, | |
| "learning_rate": 2.625975e-05, | |
| "loss": 6.0771, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.02846, | |
| "eval_accuracy": 0.029002667254401378, | |
| "eval_loss": 6.028487205505371, | |
| "eval_runtime": 97.1346, | |
| "eval_samples_per_second": 36.99, | |
| "eval_steps_per_second": 2.316, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.03096, | |
| "grad_norm": 2.5634896755218506, | |
| "learning_rate": 2.6134750000000002e-05, | |
| "loss": 6.0474, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 2.03346, | |
| "grad_norm": 2.277717113494873, | |
| "learning_rate": 2.600975e-05, | |
| "loss": 6.0646, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.03346, | |
| "eval_accuracy": 0.027694413323075186, | |
| "eval_loss": 6.009863376617432, | |
| "eval_runtime": 92.8998, | |
| "eval_samples_per_second": 38.676, | |
| "eval_steps_per_second": 2.422, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.03596, | |
| "grad_norm": 2.0405683517456055, | |
| "learning_rate": 2.5884750000000003e-05, | |
| "loss": 6.0532, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 2.03846, | |
| "grad_norm": 1.5538651943206787, | |
| "learning_rate": 2.575975e-05, | |
| "loss": 6.0421, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.03846, | |
| "eval_accuracy": 0.029365511808773982, | |
| "eval_loss": 6.003146648406982, | |
| "eval_runtime": 112.494, | |
| "eval_samples_per_second": 31.939, | |
| "eval_steps_per_second": 2.0, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.04096, | |
| "grad_norm": 2.2698843479156494, | |
| "learning_rate": 2.563475e-05, | |
| "loss": 6.0434, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 2.04346, | |
| "grad_norm": 3.3169667720794678, | |
| "learning_rate": 2.5509749999999997e-05, | |
| "loss": 6.0477, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.04346, | |
| "eval_accuracy": 0.027985151535558972, | |
| "eval_loss": 5.9978766441345215, | |
| "eval_runtime": 110.0502, | |
| "eval_samples_per_second": 32.649, | |
| "eval_steps_per_second": 2.045, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.04596, | |
| "grad_norm": 1.6990258693695068, | |
| "learning_rate": 2.5385000000000002e-05, | |
| "loss": 6.0594, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 2.04846, | |
| "grad_norm": 2.433408260345459, | |
| "learning_rate": 2.526e-05, | |
| "loss": 6.0317, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.04846, | |
| "eval_accuracy": 0.028621047841197345, | |
| "eval_loss": 5.987879276275635, | |
| "eval_runtime": 97.8847, | |
| "eval_samples_per_second": 36.706, | |
| "eval_steps_per_second": 2.299, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.05096, | |
| "grad_norm": 3.094221830368042, | |
| "learning_rate": 2.5135000000000002e-05, | |
| "loss": 6.0438, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 2.05346, | |
| "grad_norm": 2.064706802368164, | |
| "learning_rate": 2.501e-05, | |
| "loss": 6.0236, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.05346, | |
| "eval_accuracy": 0.028613837207008466, | |
| "eval_loss": 5.978915691375732, | |
| "eval_runtime": 116.882, | |
| "eval_samples_per_second": 30.74, | |
| "eval_steps_per_second": 1.925, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.05596, | |
| "grad_norm": 2.8103480339050293, | |
| "learning_rate": 2.488525e-05, | |
| "loss": 6.0153, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 2.05846, | |
| "grad_norm": 3.619741678237915, | |
| "learning_rate": 2.476025e-05, | |
| "loss": 6.0245, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.05846, | |
| "eval_accuracy": 0.028634244662260017, | |
| "eval_loss": 5.98130989074707, | |
| "eval_runtime": 100.1482, | |
| "eval_samples_per_second": 35.877, | |
| "eval_steps_per_second": 2.247, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.06096, | |
| "grad_norm": 2.7197930812835693, | |
| "learning_rate": 2.463525e-05, | |
| "loss": 6.0433, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 2.06346, | |
| "grad_norm": 2.0345962047576904, | |
| "learning_rate": 2.451025e-05, | |
| "loss": 6.0046, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.06346, | |
| "eval_accuracy": 0.02719443066941215, | |
| "eval_loss": 5.959959030151367, | |
| "eval_runtime": 99.9834, | |
| "eval_samples_per_second": 35.936, | |
| "eval_steps_per_second": 2.25, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.06596, | |
| "grad_norm": 3.054705858230591, | |
| "learning_rate": 2.43855e-05, | |
| "loss": 6.0308, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 2.06846, | |
| "grad_norm": 3.065950632095337, | |
| "learning_rate": 2.42605e-05, | |
| "loss": 6.0089, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.06846, | |
| "eval_accuracy": 0.028201470561225427, | |
| "eval_loss": 5.969558238983154, | |
| "eval_runtime": 91.0097, | |
| "eval_samples_per_second": 39.479, | |
| "eval_steps_per_second": 2.472, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.07096, | |
| "grad_norm": 2.385056495666504, | |
| "learning_rate": 2.413575e-05, | |
| "loss": 6.0279, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 2.07346, | |
| "grad_norm": 2.1604409217834473, | |
| "learning_rate": 2.401075e-05, | |
| "loss": 6.0268, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.07346, | |
| "eval_accuracy": 0.028443775079912192, | |
| "eval_loss": 5.9631242752075195, | |
| "eval_runtime": 95.1215, | |
| "eval_samples_per_second": 37.773, | |
| "eval_steps_per_second": 2.365, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.07596, | |
| "grad_norm": 2.4640963077545166, | |
| "learning_rate": 2.388575e-05, | |
| "loss": 6.0192, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 2.07846, | |
| "grad_norm": 3.9500372409820557, | |
| "learning_rate": 2.376075e-05, | |
| "loss": 6.015, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.07846, | |
| "eval_accuracy": 0.02789304588752363, | |
| "eval_loss": 5.986013412475586, | |
| "eval_runtime": 95.12, | |
| "eval_samples_per_second": 37.773, | |
| "eval_steps_per_second": 2.365, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.08096, | |
| "grad_norm": 2.237582206726074, | |
| "learning_rate": 2.363575e-05, | |
| "loss": 6.0236, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 2.08346, | |
| "grad_norm": 2.649489641189575, | |
| "learning_rate": 2.3511000000000002e-05, | |
| "loss": 5.9978, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.08346, | |
| "eval_accuracy": 0.02822813630275412, | |
| "eval_loss": 5.95936393737793, | |
| "eval_runtime": 93.2702, | |
| "eval_samples_per_second": 38.522, | |
| "eval_steps_per_second": 2.412, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.08596, | |
| "grad_norm": 2.1337761878967285, | |
| "learning_rate": 2.3386000000000003e-05, | |
| "loss": 6.0018, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 2.08846, | |
| "grad_norm": 3.1514151096343994, | |
| "learning_rate": 2.3261000000000003e-05, | |
| "loss": 6.0095, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.08846, | |
| "eval_accuracy": 0.028024197799940274, | |
| "eval_loss": 5.966735363006592, | |
| "eval_runtime": 105.6735, | |
| "eval_samples_per_second": 34.001, | |
| "eval_steps_per_second": 2.129, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.09096, | |
| "grad_norm": 2.5281171798706055, | |
| "learning_rate": 2.3136000000000003e-05, | |
| "loss": 5.9958, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 2.09346, | |
| "grad_norm": 2.90545392036438, | |
| "learning_rate": 2.3011e-05, | |
| "loss": 6.008, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.09346, | |
| "eval_accuracy": 0.02748897827354289, | |
| "eval_loss": 5.956141471862793, | |
| "eval_runtime": 104.8321, | |
| "eval_samples_per_second": 34.274, | |
| "eval_steps_per_second": 2.146, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.09596, | |
| "grad_norm": 2.385185956954956, | |
| "learning_rate": 2.2886e-05, | |
| "loss": 5.9762, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 2.09846, | |
| "grad_norm": 3.710510015487671, | |
| "learning_rate": 2.2761e-05, | |
| "loss": 5.9912, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.09846, | |
| "eval_accuracy": 0.027843251696709842, | |
| "eval_loss": 5.974761962890625, | |
| "eval_runtime": 92.291, | |
| "eval_samples_per_second": 38.931, | |
| "eval_steps_per_second": 2.438, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.10096, | |
| "grad_norm": 2.344508171081543, | |
| "learning_rate": 2.2636e-05, | |
| "loss": 6.007, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 2.10346, | |
| "grad_norm": 2.5263593196868896, | |
| "learning_rate": 2.251125e-05, | |
| "loss": 6.0, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.10346, | |
| "eval_accuracy": 0.027863114953154685, | |
| "eval_loss": 5.951306343078613, | |
| "eval_runtime": 107.5477, | |
| "eval_samples_per_second": 33.408, | |
| "eval_steps_per_second": 2.092, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.10596, | |
| "grad_norm": 4.0800981521606445, | |
| "learning_rate": 2.238625e-05, | |
| "loss": 6.0135, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 2.10846, | |
| "grad_norm": 2.456308126449585, | |
| "learning_rate": 2.226125e-05, | |
| "loss": 5.9981, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.10846, | |
| "eval_accuracy": 0.02768094440260916, | |
| "eval_loss": 5.935766220092773, | |
| "eval_runtime": 92.4942, | |
| "eval_samples_per_second": 38.846, | |
| "eval_steps_per_second": 2.433, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.11096, | |
| "grad_norm": 2.2109882831573486, | |
| "learning_rate": 2.213625e-05, | |
| "loss": 5.9899, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 2.11346, | |
| "grad_norm": 2.52247953414917, | |
| "learning_rate": 2.20115e-05, | |
| "loss": 5.9877, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.11346, | |
| "eval_accuracy": 0.02789957627320413, | |
| "eval_loss": 5.934952259063721, | |
| "eval_runtime": 107.9372, | |
| "eval_samples_per_second": 33.288, | |
| "eval_steps_per_second": 2.085, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.11596, | |
| "grad_norm": 1.6865503787994385, | |
| "learning_rate": 2.18865e-05, | |
| "loss": 5.9807, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 2.11846, | |
| "grad_norm": 2.4976794719696045, | |
| "learning_rate": 2.17615e-05, | |
| "loss": 5.9726, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 2.11846, | |
| "eval_accuracy": 0.027755091490023136, | |
| "eval_loss": 5.934043884277344, | |
| "eval_runtime": 98.7369, | |
| "eval_samples_per_second": 36.39, | |
| "eval_steps_per_second": 2.279, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 2.12096, | |
| "grad_norm": 2.376749038696289, | |
| "learning_rate": 2.1636500000000002e-05, | |
| "loss": 5.9716, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 2.12346, | |
| "grad_norm": 4.487443447113037, | |
| "learning_rate": 2.1511500000000002e-05, | |
| "loss": 5.9696, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 2.12346, | |
| "eval_accuracy": 0.027384900251759974, | |
| "eval_loss": 5.924759864807129, | |
| "eval_runtime": 92.999, | |
| "eval_samples_per_second": 38.635, | |
| "eval_steps_per_second": 2.419, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 2.12596, | |
| "grad_norm": 3.5680646896362305, | |
| "learning_rate": 2.138675e-05, | |
| "loss": 5.9932, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 2.12846, | |
| "grad_norm": 2.196323871612549, | |
| "learning_rate": 2.126175e-05, | |
| "loss": 5.9842, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 2.12846, | |
| "eval_accuracy": 0.027340003850206556, | |
| "eval_loss": 5.95149564743042, | |
| "eval_runtime": 101.0386, | |
| "eval_samples_per_second": 35.561, | |
| "eval_steps_per_second": 2.227, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 2.13096, | |
| "grad_norm": 2.3321759700775146, | |
| "learning_rate": 2.1136750000000004e-05, | |
| "loss": 5.9865, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 2.13346, | |
| "grad_norm": 2.0492184162139893, | |
| "learning_rate": 2.101175e-05, | |
| "loss": 5.9919, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 2.13346, | |
| "eval_accuracy": 0.027651693716748603, | |
| "eval_loss": 5.923666477203369, | |
| "eval_runtime": 106.1587, | |
| "eval_samples_per_second": 33.846, | |
| "eval_steps_per_second": 2.119, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 2.13596, | |
| "grad_norm": 2.516122817993164, | |
| "learning_rate": 2.088675e-05, | |
| "loss": 5.9827, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 2.13846, | |
| "grad_norm": 2.3729827404022217, | |
| "learning_rate": 2.0762000000000002e-05, | |
| "loss": 5.972, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 2.13846, | |
| "eval_accuracy": 0.02696409852447296, | |
| "eval_loss": 5.927760601043701, | |
| "eval_runtime": 122.2666, | |
| "eval_samples_per_second": 29.387, | |
| "eval_steps_per_second": 1.84, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 2.14096, | |
| "grad_norm": 2.6471846103668213, | |
| "learning_rate": 2.0637e-05, | |
| "loss": 5.9663, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 2.14346, | |
| "grad_norm": 4.273701190948486, | |
| "learning_rate": 2.0512e-05, | |
| "loss": 5.9715, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 2.14346, | |
| "eval_accuracy": 0.026757439027625573, | |
| "eval_loss": 5.910974502563477, | |
| "eval_runtime": 99.6535, | |
| "eval_samples_per_second": 36.055, | |
| "eval_steps_per_second": 2.258, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 2.14596, | |
| "grad_norm": 3.1654696464538574, | |
| "learning_rate": 2.0387e-05, | |
| "loss": 5.9718, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 2.14846, | |
| "grad_norm": 2.6283257007598877, | |
| "learning_rate": 2.026225e-05, | |
| "loss": 5.9727, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 2.14846, | |
| "eval_accuracy": 0.027529385034940963, | |
| "eval_loss": 5.913906574249268, | |
| "eval_runtime": 91.3308, | |
| "eval_samples_per_second": 39.341, | |
| "eval_steps_per_second": 2.464, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 2.15096, | |
| "grad_norm": 2.8760488033294678, | |
| "learning_rate": 2.013725e-05, | |
| "loss": 5.9587, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 2.15346, | |
| "grad_norm": 2.699265956878662, | |
| "learning_rate": 2.001225e-05, | |
| "loss": 5.9427, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 2.15346, | |
| "eval_accuracy": 0.02733360951422774, | |
| "eval_loss": 5.927834987640381, | |
| "eval_runtime": 91.7396, | |
| "eval_samples_per_second": 39.165, | |
| "eval_steps_per_second": 2.453, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 2.15596, | |
| "grad_norm": 2.398200511932373, | |
| "learning_rate": 1.9887250000000002e-05, | |
| "loss": 5.9724, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 2.15846, | |
| "grad_norm": 2.2844276428222656, | |
| "learning_rate": 1.9762250000000002e-05, | |
| "loss": 5.9514, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 2.15846, | |
| "eval_accuracy": 0.02694165032369625, | |
| "eval_loss": 5.9226508140563965, | |
| "eval_runtime": 92.7015, | |
| "eval_samples_per_second": 38.759, | |
| "eval_steps_per_second": 2.427, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 2.16096, | |
| "grad_norm": 3.6655936241149902, | |
| "learning_rate": 1.96375e-05, | |
| "loss": 5.9701, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 2.16346, | |
| "grad_norm": 2.5577406883239746, | |
| "learning_rate": 1.95125e-05, | |
| "loss": 5.9217, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 2.16346, | |
| "eval_accuracy": 0.02731524280450134, | |
| "eval_loss": 5.9304680824279785, | |
| "eval_runtime": 91.7545, | |
| "eval_samples_per_second": 39.159, | |
| "eval_steps_per_second": 2.452, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 2.16596, | |
| "grad_norm": 3.617988109588623, | |
| "learning_rate": 1.93875e-05, | |
| "loss": 5.9587, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 2.16846, | |
| "grad_norm": 2.8228862285614014, | |
| "learning_rate": 1.92625e-05, | |
| "loss": 5.9862, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 2.16846, | |
| "eval_accuracy": 0.02671240657637048, | |
| "eval_loss": 5.909170150756836, | |
| "eval_runtime": 92.8579, | |
| "eval_samples_per_second": 38.694, | |
| "eval_steps_per_second": 2.423, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 2.17096, | |
| "grad_norm": 5.492008209228516, | |
| "learning_rate": 1.91375e-05, | |
| "loss": 5.9472, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 2.17346, | |
| "grad_norm": 2.1293392181396484, | |
| "learning_rate": 1.9012750000000002e-05, | |
| "loss": 5.9388, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 2.17346, | |
| "eval_accuracy": 0.0270023284906442, | |
| "eval_loss": 5.889882564544678, | |
| "eval_runtime": 122.3828, | |
| "eval_samples_per_second": 29.359, | |
| "eval_steps_per_second": 1.838, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 2.17596, | |
| "grad_norm": 2.5894041061401367, | |
| "learning_rate": 1.8887750000000002e-05, | |
| "loss": 5.9259, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 2.17846, | |
| "grad_norm": 3.7750794887542725, | |
| "learning_rate": 1.8762750000000003e-05, | |
| "loss": 5.9429, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 2.17846, | |
| "eval_accuracy": 0.02674982024433166, | |
| "eval_loss": 5.895012855529785, | |
| "eval_runtime": 95.7852, | |
| "eval_samples_per_second": 37.511, | |
| "eval_steps_per_second": 2.349, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 2.18096, | |
| "grad_norm": 2.4733965396881104, | |
| "learning_rate": 1.8638e-05, | |
| "loss": 5.9506, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 2.18346, | |
| "grad_norm": 2.5394270420074463, | |
| "learning_rate": 1.8513e-05, | |
| "loss": 5.9317, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 2.18346, | |
| "eval_accuracy": 0.026840429345648554, | |
| "eval_loss": 5.910998344421387, | |
| "eval_runtime": 95.7395, | |
| "eval_samples_per_second": 37.529, | |
| "eval_steps_per_second": 2.35, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 2.18596, | |
| "grad_norm": 2.7636115550994873, | |
| "learning_rate": 1.8388e-05, | |
| "loss": 5.9325, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 2.18846, | |
| "grad_norm": 3.0258498191833496, | |
| "learning_rate": 1.8263e-05, | |
| "loss": 5.9367, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 2.18846, | |
| "eval_accuracy": 0.026817436946065136, | |
| "eval_loss": 5.86806583404541, | |
| "eval_runtime": 93.0877, | |
| "eval_samples_per_second": 38.598, | |
| "eval_steps_per_second": 2.417, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 2.19096, | |
| "grad_norm": 2.4709484577178955, | |
| "learning_rate": 1.8138e-05, | |
| "loss": 5.9368, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 2.19346, | |
| "grad_norm": 4.170524597167969, | |
| "learning_rate": 1.8013000000000002e-05, | |
| "loss": 5.9273, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.19346, | |
| "eval_accuracy": 0.027440544579745874, | |
| "eval_loss": 5.880221366882324, | |
| "eval_runtime": 92.6132, | |
| "eval_samples_per_second": 38.796, | |
| "eval_steps_per_second": 2.429, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.19596, | |
| "grad_norm": 3.9754855632781982, | |
| "learning_rate": 1.7888000000000002e-05, | |
| "loss": 5.9188, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 2.19846, | |
| "grad_norm": 2.676684856414795, | |
| "learning_rate": 1.7763000000000003e-05, | |
| "loss": 5.934, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 2.19846, | |
| "eval_accuracy": 0.026782064023629114, | |
| "eval_loss": 5.897346496582031, | |
| "eval_runtime": 92.8542, | |
| "eval_samples_per_second": 38.695, | |
| "eval_steps_per_second": 2.423, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 2.20096, | |
| "grad_norm": 3.0156376361846924, | |
| "learning_rate": 1.763825e-05, | |
| "loss": 5.9191, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 2.20346, | |
| "grad_norm": 2.913367509841919, | |
| "learning_rate": 1.751325e-05, | |
| "loss": 5.9229, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 2.20346, | |
| "eval_accuracy": 0.027015253212303518, | |
| "eval_loss": 5.891612529754639, | |
| "eval_runtime": 91.7301, | |
| "eval_samples_per_second": 39.169, | |
| "eval_steps_per_second": 2.453, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 2.20596, | |
| "grad_norm": 3.0923585891723633, | |
| "learning_rate": 1.738825e-05, | |
| "loss": 5.9225, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 2.20846, | |
| "grad_norm": 2.9327263832092285, | |
| "learning_rate": 1.726325e-05, | |
| "loss": 5.942, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 2.20846, | |
| "eval_accuracy": 0.026604791262343958, | |
| "eval_loss": 5.896469593048096, | |
| "eval_runtime": 97.1482, | |
| "eval_samples_per_second": 36.985, | |
| "eval_steps_per_second": 2.316, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 2.21096, | |
| "grad_norm": 2.434720993041992, | |
| "learning_rate": 1.7138500000000002e-05, | |
| "loss": 5.9244, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 2.21346, | |
| "grad_norm": 3.1938490867614746, | |
| "learning_rate": 1.7013500000000002e-05, | |
| "loss": 5.9224, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 2.21346, | |
| "eval_accuracy": 0.02676478571151613, | |
| "eval_loss": 5.8799638748168945, | |
| "eval_runtime": 101.684, | |
| "eval_samples_per_second": 35.335, | |
| "eval_steps_per_second": 2.213, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 2.21596, | |
| "grad_norm": 2.5575222969055176, | |
| "learning_rate": 1.6888500000000003e-05, | |
| "loss": 5.933, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 2.21846, | |
| "grad_norm": 2.610675573348999, | |
| "learning_rate": 1.6763500000000003e-05, | |
| "loss": 5.936, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 2.21846, | |
| "eval_accuracy": 0.026946139963851593, | |
| "eval_loss": 5.869258880615234, | |
| "eval_runtime": 94.0477, | |
| "eval_samples_per_second": 38.204, | |
| "eval_steps_per_second": 2.392, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 2.22096, | |
| "grad_norm": 2.5007147789001465, | |
| "learning_rate": 1.663875e-05, | |
| "loss": 5.9006, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 3.00019, | |
| "grad_norm": 2.4350554943084717, | |
| "learning_rate": 1.651375e-05, | |
| "loss": 5.9129, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 3.00019, | |
| "eval_accuracy": 0.02651254956460694, | |
| "eval_loss": 5.850106239318848, | |
| "eval_runtime": 90.9885, | |
| "eval_samples_per_second": 39.489, | |
| "eval_steps_per_second": 2.473, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 3.00269, | |
| "grad_norm": 2.9564504623413086, | |
| "learning_rate": 1.638875e-05, | |
| "loss": 5.8888, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 3.00519, | |
| "grad_norm": 3.2191567420959473, | |
| "learning_rate": 1.6263749999999998e-05, | |
| "loss": 5.8787, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 3.00519, | |
| "eval_accuracy": 0.0267069645883034, | |
| "eval_loss": 5.870194911956787, | |
| "eval_runtime": 93.5455, | |
| "eval_samples_per_second": 38.409, | |
| "eval_steps_per_second": 2.405, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 3.00769, | |
| "grad_norm": 3.1718389987945557, | |
| "learning_rate": 1.613875e-05, | |
| "loss": 5.8943, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 3.01019, | |
| "grad_norm": 3.5635807514190674, | |
| "learning_rate": 1.601425e-05, | |
| "loss": 5.9171, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 3.01019, | |
| "eval_accuracy": 0.0268892711885506, | |
| "eval_loss": 5.844875812530518, | |
| "eval_runtime": 92.3095, | |
| "eval_samples_per_second": 38.923, | |
| "eval_steps_per_second": 2.437, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 3.01269, | |
| "grad_norm": 4.3343305587768555, | |
| "learning_rate": 1.588925e-05, | |
| "loss": 5.9144, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 3.01519, | |
| "grad_norm": 2.6254384517669678, | |
| "learning_rate": 1.576425e-05, | |
| "loss": 5.8931, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 3.01519, | |
| "eval_accuracy": 0.026976070898220537, | |
| "eval_loss": 5.845653057098389, | |
| "eval_runtime": 92.0247, | |
| "eval_samples_per_second": 39.044, | |
| "eval_steps_per_second": 2.445, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 3.01769, | |
| "grad_norm": 3.994947910308838, | |
| "learning_rate": 1.563925e-05, | |
| "loss": 5.9248, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 3.02019, | |
| "grad_norm": 3.4500911235809326, | |
| "learning_rate": 1.5514249999999998e-05, | |
| "loss": 5.8612, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 3.02019, | |
| "eval_accuracy": 0.026333100008094957, | |
| "eval_loss": 5.863004684448242, | |
| "eval_runtime": 97.9674, | |
| "eval_samples_per_second": 36.675, | |
| "eval_steps_per_second": 2.297, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 3.02269, | |
| "grad_norm": 2.8210179805755615, | |
| "learning_rate": 1.538925e-05, | |
| "loss": 5.8873, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 3.02519, | |
| "grad_norm": 3.462085723876953, | |
| "learning_rate": 1.526425e-05, | |
| "loss": 5.8897, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 3.02519, | |
| "eval_accuracy": 0.02670546804158495, | |
| "eval_loss": 5.849697589874268, | |
| "eval_runtime": 91.473, | |
| "eval_samples_per_second": 39.279, | |
| "eval_steps_per_second": 2.46, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 3.02769, | |
| "grad_norm": 3.4429280757904053, | |
| "learning_rate": 1.5139250000000002e-05, | |
| "loss": 5.8915, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 3.03019, | |
| "grad_norm": 2.4032459259033203, | |
| "learning_rate": 1.50145e-05, | |
| "loss": 5.8772, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 3.03019, | |
| "eval_accuracy": 0.026319903187032288, | |
| "eval_loss": 5.817691802978516, | |
| "eval_runtime": 116.7881, | |
| "eval_samples_per_second": 30.765, | |
| "eval_steps_per_second": 1.927, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 3.03269, | |
| "grad_norm": 2.4531261920928955, | |
| "learning_rate": 1.48895e-05, | |
| "loss": 5.8735, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 3.03519, | |
| "grad_norm": 2.7715256214141846, | |
| "learning_rate": 1.47645e-05, | |
| "loss": 5.8774, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 3.03519, | |
| "eval_accuracy": 0.026607376206675824, | |
| "eval_loss": 5.821176052093506, | |
| "eval_runtime": 92.8442, | |
| "eval_samples_per_second": 38.699, | |
| "eval_steps_per_second": 2.423, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 3.03769, | |
| "grad_norm": 3.399043560028076, | |
| "learning_rate": 1.4639750000000002e-05, | |
| "loss": 5.8561, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 3.04019, | |
| "grad_norm": 3.1285316944122314, | |
| "learning_rate": 1.4514750000000002e-05, | |
| "loss": 5.8694, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 3.04019, | |
| "eval_accuracy": 0.026714855471000665, | |
| "eval_loss": 5.837355613708496, | |
| "eval_runtime": 98.834, | |
| "eval_samples_per_second": 36.354, | |
| "eval_steps_per_second": 2.277, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 3.04269, | |
| "grad_norm": 3.5642755031585693, | |
| "learning_rate": 1.4389750000000002e-05, | |
| "loss": 5.8642, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 3.04519, | |
| "grad_norm": 2.953099489212036, | |
| "learning_rate": 1.4264750000000001e-05, | |
| "loss": 5.8561, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 3.04519, | |
| "eval_accuracy": 0.02667281611318247, | |
| "eval_loss": 5.792807102203369, | |
| "eval_runtime": 93.9281, | |
| "eval_samples_per_second": 38.253, | |
| "eval_steps_per_second": 2.395, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 3.04769, | |
| "grad_norm": 2.8684558868408203, | |
| "learning_rate": 1.4139750000000001e-05, | |
| "loss": 5.8442, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 3.05019, | |
| "grad_norm": 2.2189698219299316, | |
| "learning_rate": 1.4014750000000002e-05, | |
| "loss": 5.8658, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.05019, | |
| "eval_accuracy": 0.02694872490818346, | |
| "eval_loss": 5.79358434677124, | |
| "eval_runtime": 93.4176, | |
| "eval_samples_per_second": 38.462, | |
| "eval_steps_per_second": 2.409, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.05269, | |
| "grad_norm": 2.659515619277954, | |
| "learning_rate": 1.3889750000000002e-05, | |
| "loss": 5.8347, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 3.05519, | |
| "grad_norm": 2.62570858001709, | |
| "learning_rate": 1.376475e-05, | |
| "loss": 5.8295, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 3.05519, | |
| "eval_accuracy": 0.026485203574569863, | |
| "eval_loss": 5.795611381530762, | |
| "eval_runtime": 94.2389, | |
| "eval_samples_per_second": 38.127, | |
| "eval_steps_per_second": 2.388, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 3.05769, | |
| "grad_norm": 3.243245840072632, | |
| "learning_rate": 1.364e-05, | |
| "loss": 5.8247, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 3.06019, | |
| "grad_norm": 3.164580821990967, | |
| "learning_rate": 1.3515e-05, | |
| "loss": 5.8444, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 3.06019, | |
| "eval_accuracy": 0.026442620017944955, | |
| "eval_loss": 5.792357444763184, | |
| "eval_runtime": 91.4103, | |
| "eval_samples_per_second": 39.306, | |
| "eval_steps_per_second": 2.461, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 3.06269, | |
| "grad_norm": 2.9992387294769287, | |
| "learning_rate": 1.339e-05, | |
| "loss": 5.8187, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 3.06519, | |
| "grad_norm": 2.9133353233337402, | |
| "learning_rate": 1.3265e-05, | |
| "loss": 5.8318, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 3.06519, | |
| "eval_accuracy": 0.026461258827074705, | |
| "eval_loss": 5.765110015869141, | |
| "eval_runtime": 93.7438, | |
| "eval_samples_per_second": 38.328, | |
| "eval_steps_per_second": 2.4, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 3.06769, | |
| "grad_norm": 3.1825642585754395, | |
| "learning_rate": 1.314e-05, | |
| "loss": 5.8185, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 3.07019, | |
| "grad_norm": 3.5604467391967773, | |
| "learning_rate": 1.3015e-05, | |
| "loss": 5.8323, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 3.07019, | |
| "eval_accuracy": 0.026824783629955697, | |
| "eval_loss": 5.770131587982178, | |
| "eval_runtime": 92.029, | |
| "eval_samples_per_second": 39.042, | |
| "eval_steps_per_second": 2.445, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 3.07269, | |
| "grad_norm": 3.883007049560547, | |
| "learning_rate": 1.2889999999999999e-05, | |
| "loss": 5.8111, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 3.07519, | |
| "grad_norm": 8.257863998413086, | |
| "learning_rate": 1.2765250000000001e-05, | |
| "loss": 5.8239, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 3.07519, | |
| "eval_accuracy": 0.026383438397715453, | |
| "eval_loss": 5.779338359832764, | |
| "eval_runtime": 92.1302, | |
| "eval_samples_per_second": 38.999, | |
| "eval_steps_per_second": 2.442, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 3.07769, | |
| "grad_norm": 2.9781956672668457, | |
| "learning_rate": 1.2640250000000002e-05, | |
| "loss": 5.8073, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 3.08019, | |
| "grad_norm": 3.369654893875122, | |
| "learning_rate": 1.251525e-05, | |
| "loss": 5.8057, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 3.08019, | |
| "eval_accuracy": 0.027368438237857055, | |
| "eval_loss": 5.7676262855529785, | |
| "eval_runtime": 94.7379, | |
| "eval_samples_per_second": 37.926, | |
| "eval_steps_per_second": 2.375, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 3.08269, | |
| "grad_norm": 2.6309428215026855, | |
| "learning_rate": 1.239025e-05, | |
| "loss": 5.798, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 3.08519, | |
| "grad_norm": 4.712452411651611, | |
| "learning_rate": 1.2265250000000001e-05, | |
| "loss": 5.7818, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 3.08519, | |
| "eval_accuracy": 0.026996750452875445, | |
| "eval_loss": 5.756935119628906, | |
| "eval_runtime": 93.4756, | |
| "eval_samples_per_second": 38.438, | |
| "eval_steps_per_second": 2.407, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 3.08769, | |
| "grad_norm": 3.6165318489074707, | |
| "learning_rate": 1.21405e-05, | |
| "loss": 5.7959, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 3.09019, | |
| "grad_norm": 3.728891134262085, | |
| "learning_rate": 1.20155e-05, | |
| "loss": 5.773, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 3.09019, | |
| "eval_accuracy": 0.026722338204592903, | |
| "eval_loss": 5.740837097167969, | |
| "eval_runtime": 94.7277, | |
| "eval_samples_per_second": 37.93, | |
| "eval_steps_per_second": 2.375, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 3.09269, | |
| "grad_norm": 3.545217990875244, | |
| "learning_rate": 1.18905e-05, | |
| "loss": 5.7891, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 3.09519, | |
| "grad_norm": 3.074216842651367, | |
| "learning_rate": 1.17655e-05, | |
| "loss": 5.7491, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 3.09519, | |
| "eval_accuracy": 0.027355241416794383, | |
| "eval_loss": 5.720602989196777, | |
| "eval_runtime": 97.4705, | |
| "eval_samples_per_second": 36.862, | |
| "eval_steps_per_second": 2.308, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 3.09769, | |
| "grad_norm": 4.110429763793945, | |
| "learning_rate": 1.16405e-05, | |
| "loss": 5.7724, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 3.10019, | |
| "grad_norm": 3.007507801055908, | |
| "learning_rate": 1.151575e-05, | |
| "loss": 5.7655, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 3.10019, | |
| "eval_accuracy": 0.026848184178644142, | |
| "eval_loss": 5.7095208168029785, | |
| "eval_runtime": 98.9114, | |
| "eval_samples_per_second": 36.325, | |
| "eval_steps_per_second": 2.275, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 3.10269, | |
| "grad_norm": 3.1194117069244385, | |
| "learning_rate": 1.139075e-05, | |
| "loss": 5.7622, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 3.10519, | |
| "grad_norm": 4.109334945678711, | |
| "learning_rate": 1.126575e-05, | |
| "loss": 5.7706, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 3.10519, | |
| "eval_accuracy": 0.02715552045473252, | |
| "eval_loss": 5.707860469818115, | |
| "eval_runtime": 126.3537, | |
| "eval_samples_per_second": 28.436, | |
| "eval_steps_per_second": 1.781, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 3.10769, | |
| "grad_norm": 3.767932415008545, | |
| "learning_rate": 1.1140750000000002e-05, | |
| "loss": 5.7639, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 3.11019, | |
| "grad_norm": 4.084874629974365, | |
| "learning_rate": 1.1016e-05, | |
| "loss": 5.7379, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 3.11019, | |
| "eval_accuracy": 0.027283815323413948, | |
| "eval_loss": 5.691872596740723, | |
| "eval_runtime": 93.2144, | |
| "eval_samples_per_second": 38.546, | |
| "eval_steps_per_second": 2.414, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 3.11269, | |
| "grad_norm": 6.118876934051514, | |
| "learning_rate": 1.0891000000000001e-05, | |
| "loss": 5.7411, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 3.11519, | |
| "grad_norm": 4.562450885772705, | |
| "learning_rate": 1.0766000000000002e-05, | |
| "loss": 5.7374, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 3.11519, | |
| "eval_accuracy": 0.027440680629447548, | |
| "eval_loss": 5.667840957641602, | |
| "eval_runtime": 91.1779, | |
| "eval_samples_per_second": 39.406, | |
| "eval_steps_per_second": 2.468, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 3.11769, | |
| "grad_norm": 3.47501277923584, | |
| "learning_rate": 1.0641e-05, | |
| "loss": 5.7177, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 3.12019, | |
| "grad_norm": 3.262887477874756, | |
| "learning_rate": 1.0516e-05, | |
| "loss": 5.7077, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 3.12019, | |
| "eval_accuracy": 0.026955663442968986, | |
| "eval_loss": 5.6481852531433105, | |
| "eval_runtime": 93.6492, | |
| "eval_samples_per_second": 38.367, | |
| "eval_steps_per_second": 2.403, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 3.12269, | |
| "grad_norm": 3.8364920616149902, | |
| "learning_rate": 1.0391250000000002e-05, | |
| "loss": 5.7026, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 3.12519, | |
| "grad_norm": 3.216892719268799, | |
| "learning_rate": 1.026625e-05, | |
| "loss": 5.7176, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 3.12519, | |
| "eval_accuracy": 0.027355649565899413, | |
| "eval_loss": 5.614231109619141, | |
| "eval_runtime": 128.5228, | |
| "eval_samples_per_second": 27.956, | |
| "eval_steps_per_second": 1.751, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 3.12769, | |
| "grad_norm": 3.7914490699768066, | |
| "learning_rate": 1.014125e-05, | |
| "loss": 5.7055, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 3.13019, | |
| "grad_norm": 3.515538215637207, | |
| "learning_rate": 1.0016250000000001e-05, | |
| "loss": 5.7077, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.13019, | |
| "eval_accuracy": 0.027464081178135997, | |
| "eval_loss": 5.629947185516357, | |
| "eval_runtime": 97.5707, | |
| "eval_samples_per_second": 36.825, | |
| "eval_steps_per_second": 2.306, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.13269, | |
| "grad_norm": 4.886687278747559, | |
| "learning_rate": 9.8915e-06, | |
| "loss": 5.6998, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 3.13519, | |
| "grad_norm": 3.584073305130005, | |
| "learning_rate": 9.7665e-06, | |
| "loss": 5.6882, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 3.13519, | |
| "eval_accuracy": 0.027459183388875624, | |
| "eval_loss": 5.591392993927002, | |
| "eval_runtime": 93.7876, | |
| "eval_samples_per_second": 38.31, | |
| "eval_steps_per_second": 2.399, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 3.13769, | |
| "grad_norm": 2.614473581314087, | |
| "learning_rate": 9.6415e-06, | |
| "loss": 5.6896, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 3.14019, | |
| "grad_norm": 3.612001419067383, | |
| "learning_rate": 9.516500000000001e-06, | |
| "loss": 5.6513, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 3.14019, | |
| "eval_accuracy": 0.02719810401135743, | |
| "eval_loss": 5.585655689239502, | |
| "eval_runtime": 127.1026, | |
| "eval_samples_per_second": 28.268, | |
| "eval_steps_per_second": 1.77, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 3.14269, | |
| "grad_norm": 3.9107935428619385, | |
| "learning_rate": 9.39175e-06, | |
| "loss": 5.657, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 3.14519, | |
| "grad_norm": 3.753208637237549, | |
| "learning_rate": 9.26675e-06, | |
| "loss": 5.6516, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 3.14519, | |
| "eval_accuracy": 0.027440544579745874, | |
| "eval_loss": 5.5584001541137695, | |
| "eval_runtime": 97.5764, | |
| "eval_samples_per_second": 36.822, | |
| "eval_steps_per_second": 2.306, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 3.14769, | |
| "grad_norm": 3.1370689868927, | |
| "learning_rate": 9.141750000000001e-06, | |
| "loss": 5.6678, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 3.15019, | |
| "grad_norm": 3.1537926197052, | |
| "learning_rate": 9.01675e-06, | |
| "loss": 5.6158, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 3.15019, | |
| "eval_accuracy": 0.028059434672674622, | |
| "eval_loss": 5.522320747375488, | |
| "eval_runtime": 92.5826, | |
| "eval_samples_per_second": 38.809, | |
| "eval_steps_per_second": 2.43, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 3.1526899999999998, | |
| "grad_norm": 3.2936768531799316, | |
| "learning_rate": 8.89175e-06, | |
| "loss": 5.6305, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 3.15519, | |
| "grad_norm": 5.041363716125488, | |
| "learning_rate": 8.767000000000001e-06, | |
| "loss": 5.6235, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 3.15519, | |
| "eval_accuracy": 0.027728289698792763, | |
| "eval_loss": 5.527610778808594, | |
| "eval_runtime": 92.1615, | |
| "eval_samples_per_second": 38.986, | |
| "eval_steps_per_second": 2.441, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 3.15769, | |
| "grad_norm": 4.752361297607422, | |
| "learning_rate": 8.642e-06, | |
| "loss": 5.5997, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 3.16019, | |
| "grad_norm": 4.261384963989258, | |
| "learning_rate": 8.517e-06, | |
| "loss": 5.6308, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 3.16019, | |
| "eval_accuracy": 0.02816977098073468, | |
| "eval_loss": 5.499186038970947, | |
| "eval_runtime": 92.5045, | |
| "eval_samples_per_second": 38.841, | |
| "eval_steps_per_second": 2.432, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 3.16269, | |
| "grad_norm": 4.297583103179932, | |
| "learning_rate": 8.392e-06, | |
| "loss": 5.5752, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 3.16519, | |
| "grad_norm": 7.3237624168396, | |
| "learning_rate": 8.26725e-06, | |
| "loss": 5.5782, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 3.16519, | |
| "eval_accuracy": 0.027606525215791832, | |
| "eval_loss": 5.48903226852417, | |
| "eval_runtime": 92.0464, | |
| "eval_samples_per_second": 39.035, | |
| "eval_steps_per_second": 2.444, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 3.16769, | |
| "grad_norm": 3.426760196685791, | |
| "learning_rate": 8.14225e-06, | |
| "loss": 5.6192, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 3.17019, | |
| "grad_norm": 3.8471386432647705, | |
| "learning_rate": 8.01725e-06, | |
| "loss": 5.5723, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 3.17019, | |
| "eval_accuracy": 0.027942976128039095, | |
| "eval_loss": 5.443605422973633, | |
| "eval_runtime": 90.8581, | |
| "eval_samples_per_second": 39.545, | |
| "eval_steps_per_second": 2.476, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 3.1726900000000002, | |
| "grad_norm": 3.767125368118286, | |
| "learning_rate": 7.89225e-06, | |
| "loss": 5.5569, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 3.17519, | |
| "grad_norm": 4.584527015686035, | |
| "learning_rate": 7.767250000000001e-06, | |
| "loss": 5.5417, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 3.17519, | |
| "eval_accuracy": 0.028352213630683562, | |
| "eval_loss": 5.416599750518799, | |
| "eval_runtime": 91.2582, | |
| "eval_samples_per_second": 39.372, | |
| "eval_steps_per_second": 2.466, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 3.17769, | |
| "grad_norm": 5.043390274047852, | |
| "learning_rate": 7.642500000000002e-06, | |
| "loss": 5.535, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 3.18019, | |
| "grad_norm": 7.203840732574463, | |
| "learning_rate": 7.517500000000001e-06, | |
| "loss": 5.5346, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 3.18019, | |
| "eval_accuracy": 0.028451802012311136, | |
| "eval_loss": 5.403586387634277, | |
| "eval_runtime": 96.555, | |
| "eval_samples_per_second": 37.212, | |
| "eval_steps_per_second": 2.33, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 3.18269, | |
| "grad_norm": 5.778980731964111, | |
| "learning_rate": 7.392500000000001e-06, | |
| "loss": 5.521, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 3.18519, | |
| "grad_norm": 3.5962352752685547, | |
| "learning_rate": 7.2675e-06, | |
| "loss": 5.5068, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 3.18519, | |
| "eval_accuracy": 0.028494929767742753, | |
| "eval_loss": 5.36637544631958, | |
| "eval_runtime": 92.7171, | |
| "eval_samples_per_second": 38.752, | |
| "eval_steps_per_second": 2.427, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 3.18769, | |
| "grad_norm": 3.231135606765747, | |
| "learning_rate": 7.142500000000001e-06, | |
| "loss": 5.5068, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 3.19019, | |
| "grad_norm": 4.50712776184082, | |
| "learning_rate": 7.017750000000001e-06, | |
| "loss": 5.5024, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 3.19019, | |
| "eval_accuracy": 0.0285840423223412, | |
| "eval_loss": 5.33723783493042, | |
| "eval_runtime": 91.3348, | |
| "eval_samples_per_second": 39.339, | |
| "eval_steps_per_second": 2.463, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 3.19269, | |
| "grad_norm": 5.674015522003174, | |
| "learning_rate": 6.89275e-06, | |
| "loss": 5.479, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 3.19519, | |
| "grad_norm": 5.207662582397461, | |
| "learning_rate": 6.7677500000000006e-06, | |
| "loss": 5.4611, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 3.19519, | |
| "eval_accuracy": 0.02859955198833238, | |
| "eval_loss": 5.306539058685303, | |
| "eval_runtime": 92.148, | |
| "eval_samples_per_second": 38.992, | |
| "eval_steps_per_second": 2.442, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 3.19769, | |
| "grad_norm": 4.15488338470459, | |
| "learning_rate": 6.64275e-06, | |
| "loss": 5.4725, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 3.20019, | |
| "grad_norm": 3.6545050144195557, | |
| "learning_rate": 6.51775e-06, | |
| "loss": 5.4352, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 3.20019, | |
| "eval_accuracy": 0.02851234412955741, | |
| "eval_loss": 5.30513858795166, | |
| "eval_runtime": 128.4128, | |
| "eval_samples_per_second": 27.98, | |
| "eval_steps_per_second": 1.752, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 3.20269, | |
| "grad_norm": 4.31083869934082, | |
| "learning_rate": 6.3930000000000005e-06, | |
| "loss": 5.4433, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 3.20519, | |
| "grad_norm": 5.675565719604492, | |
| "learning_rate": 6.268e-06, | |
| "loss": 5.4305, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 3.20519, | |
| "eval_accuracy": 0.02904035302176591, | |
| "eval_loss": 5.271829128265381, | |
| "eval_runtime": 91.0491, | |
| "eval_samples_per_second": 39.462, | |
| "eval_steps_per_second": 2.471, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 3.20769, | |
| "grad_norm": 4.5083231925964355, | |
| "learning_rate": 6.143e-06, | |
| "loss": 5.4444, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 3.21019, | |
| "grad_norm": 5.508623123168945, | |
| "learning_rate": 6.018e-06, | |
| "loss": 5.4244, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 3.21019, | |
| "eval_accuracy": 0.02856485931440474, | |
| "eval_loss": 5.234050750732422, | |
| "eval_runtime": 97.7428, | |
| "eval_samples_per_second": 36.76, | |
| "eval_steps_per_second": 2.302, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 3.21269, | |
| "grad_norm": 5.6364030838012695, | |
| "learning_rate": 5.893000000000001e-06, | |
| "loss": 5.3918, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 3.2151899999999998, | |
| "grad_norm": 4.249551773071289, | |
| "learning_rate": 5.76825e-06, | |
| "loss": 5.406, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 3.2151899999999998, | |
| "eval_accuracy": 0.028736417988219458, | |
| "eval_loss": 5.197048664093018, | |
| "eval_runtime": 101.4416, | |
| "eval_samples_per_second": 35.419, | |
| "eval_steps_per_second": 2.218, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 3.21769, | |
| "grad_norm": 6.131099224090576, | |
| "learning_rate": 5.64325e-06, | |
| "loss": 5.4104, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 3.22019, | |
| "grad_norm": 5.6621479988098145, | |
| "learning_rate": 5.518250000000001e-06, | |
| "loss": 5.3693, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 3.22019, | |
| "eval_accuracy": 0.028811245324141817, | |
| "eval_loss": 5.188289642333984, | |
| "eval_runtime": 93.1736, | |
| "eval_samples_per_second": 38.562, | |
| "eval_steps_per_second": 2.415, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 3.22269, | |
| "grad_norm": 6.5256242752075195, | |
| "learning_rate": 5.39325e-06, | |
| "loss": 5.3581, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 4.00192, | |
| "grad_norm": 4.139052867889404, | |
| "learning_rate": 5.2685000000000005e-06, | |
| "loss": 5.3414, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 4.00192, | |
| "eval_accuracy": 0.028710568544900825, | |
| "eval_loss": 5.1566362380981445, | |
| "eval_runtime": 128.5676, | |
| "eval_samples_per_second": 27.946, | |
| "eval_steps_per_second": 1.75, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 4.00442, | |
| "grad_norm": 5.124391078948975, | |
| "learning_rate": 5.143500000000001e-06, | |
| "loss": 5.3228, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 4.00692, | |
| "grad_norm": 4.564643859863281, | |
| "learning_rate": 5.0185e-06, | |
| "loss": 5.3252, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 4.00692, | |
| "eval_accuracy": 0.029084841274214297, | |
| "eval_loss": 5.121004104614258, | |
| "eval_runtime": 99.0466, | |
| "eval_samples_per_second": 36.276, | |
| "eval_steps_per_second": 2.272, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 4.00942, | |
| "grad_norm": 6.144300937652588, | |
| "learning_rate": 4.8935e-06, | |
| "loss": 5.326, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 4.01192, | |
| "grad_norm": 4.762115001678467, | |
| "learning_rate": 4.768750000000001e-06, | |
| "loss": 5.3302, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 4.01192, | |
| "eval_accuracy": 0.02900389170171647, | |
| "eval_loss": 5.1127095222473145, | |
| "eval_runtime": 93.1042, | |
| "eval_samples_per_second": 38.591, | |
| "eval_steps_per_second": 2.417, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 4.01442, | |
| "grad_norm": 4.9249420166015625, | |
| "learning_rate": 4.64375e-06, | |
| "loss": 5.322, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 4.01692, | |
| "grad_norm": 5.8505988121032715, | |
| "learning_rate": 4.519e-06, | |
| "loss": 5.3112, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 4.01692, | |
| "eval_accuracy": 0.028904303320088896, | |
| "eval_loss": 5.079184055328369, | |
| "eval_runtime": 92.4255, | |
| "eval_samples_per_second": 38.875, | |
| "eval_steps_per_second": 2.434, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 4.01942, | |
| "grad_norm": 5.5884599685668945, | |
| "learning_rate": 4.394000000000001e-06, | |
| "loss": 5.2634, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 4.02192, | |
| "grad_norm": 6.884908199310303, | |
| "learning_rate": 4.269e-06, | |
| "loss": 5.2651, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 4.02192, | |
| "eval_accuracy": 0.02909871834378535, | |
| "eval_loss": 5.043324947357178, | |
| "eval_runtime": 100.4033, | |
| "eval_samples_per_second": 35.786, | |
| "eval_steps_per_second": 2.241, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 4.02442, | |
| "grad_norm": 4.412216663360596, | |
| "learning_rate": 4.144e-06, | |
| "loss": 5.2793, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 4.02692, | |
| "grad_norm": 4.486749172210693, | |
| "learning_rate": 4.019e-06, | |
| "loss": 5.2623, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 4.02692, | |
| "eval_accuracy": 0.028819816455347466, | |
| "eval_loss": 5.025639533996582, | |
| "eval_runtime": 94.773, | |
| "eval_samples_per_second": 37.912, | |
| "eval_steps_per_second": 2.374, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 4.02942, | |
| "grad_norm": 5.047926425933838, | |
| "learning_rate": 3.894e-06, | |
| "loss": 5.2454, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 4.03192, | |
| "grad_norm": 7.453557968139648, | |
| "learning_rate": 3.7690000000000003e-06, | |
| "loss": 5.2297, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 4.03192, | |
| "eval_accuracy": 0.02869369838189287, | |
| "eval_loss": 5.029138565063477, | |
| "eval_runtime": 92.8613, | |
| "eval_samples_per_second": 38.692, | |
| "eval_steps_per_second": 2.423, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 4.03442, | |
| "grad_norm": 5.0118021965026855, | |
| "learning_rate": 3.644e-06, | |
| "loss": 5.2391, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 4.03692, | |
| "grad_norm": 5.173340320587158, | |
| "learning_rate": 3.5192500000000002e-06, | |
| "loss": 5.1991, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 4.03692, | |
| "eval_accuracy": 0.028796688006062374, | |
| "eval_loss": 4.970343589782715, | |
| "eval_runtime": 95.8003, | |
| "eval_samples_per_second": 37.505, | |
| "eval_steps_per_second": 2.349, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 4.03942, | |
| "grad_norm": 4.592197895050049, | |
| "learning_rate": 3.39425e-06, | |
| "loss": 5.203, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 4.04192, | |
| "grad_norm": 5.571292400360107, | |
| "learning_rate": 3.26925e-06, | |
| "loss": 5.1883, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 4.04192, | |
| "eval_accuracy": 0.02865968595647362, | |
| "eval_loss": 4.975839614868164, | |
| "eval_runtime": 92.6873, | |
| "eval_samples_per_second": 38.765, | |
| "eval_steps_per_second": 2.428, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 4.04442, | |
| "grad_norm": 4.220412731170654, | |
| "learning_rate": 3.14425e-06, | |
| "loss": 5.1943, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 4.04692, | |
| "grad_norm": 8.616243362426758, | |
| "learning_rate": 3.0195e-06, | |
| "loss": 5.1854, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 4.04692, | |
| "eval_accuracy": 0.028208953294817662, | |
| "eval_loss": 4.942821502685547, | |
| "eval_runtime": 94.4959, | |
| "eval_samples_per_second": 38.023, | |
| "eval_steps_per_second": 2.381, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 4.04942, | |
| "grad_norm": 5.9760894775390625, | |
| "learning_rate": 2.8945e-06, | |
| "loss": 5.1704, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 4.05192, | |
| "grad_norm": 6.06154203414917, | |
| "learning_rate": 2.7695000000000003e-06, | |
| "loss": 5.1636, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 4.05192, | |
| "eval_accuracy": 0.02843751679363505, | |
| "eval_loss": 4.911832332611084, | |
| "eval_runtime": 91.2834, | |
| "eval_samples_per_second": 39.361, | |
| "eval_steps_per_second": 2.465, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 4.05442, | |
| "grad_norm": 7.606237411499023, | |
| "learning_rate": 2.6445000000000003e-06, | |
| "loss": 5.1407, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 4.05692, | |
| "grad_norm": 4.682966709136963, | |
| "learning_rate": 2.5197500000000003e-06, | |
| "loss": 5.1356, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 4.05692, | |
| "eval_accuracy": 0.028226095557228967, | |
| "eval_loss": 4.904683589935303, | |
| "eval_runtime": 92.6319, | |
| "eval_samples_per_second": 38.788, | |
| "eval_steps_per_second": 2.429, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 4.05942, | |
| "grad_norm": 5.441736221313477, | |
| "learning_rate": 2.3947500000000002e-06, | |
| "loss": 5.1346, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 4.06192, | |
| "grad_norm": 4.829955101013184, | |
| "learning_rate": 2.26975e-06, | |
| "loss": 5.1329, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 4.06192, | |
| "eval_accuracy": 0.028335071368272256, | |
| "eval_loss": 4.874863147735596, | |
| "eval_runtime": 91.0476, | |
| "eval_samples_per_second": 39.463, | |
| "eval_steps_per_second": 2.471, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 4.06442, | |
| "grad_norm": 5.842422962188721, | |
| "learning_rate": 2.14475e-06, | |
| "loss": 5.1127, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 4.06692, | |
| "grad_norm": 5.372358322143555, | |
| "learning_rate": 2.01975e-06, | |
| "loss": 5.107, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 4.06692, | |
| "eval_accuracy": 0.02805358453550251, | |
| "eval_loss": 4.877078533172607, | |
| "eval_runtime": 92.2372, | |
| "eval_samples_per_second": 38.954, | |
| "eval_steps_per_second": 2.439, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 4.06942, | |
| "grad_norm": 5.863542556762695, | |
| "learning_rate": 1.8950000000000003e-06, | |
| "loss": 5.1301, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 4.07192, | |
| "grad_norm": 8.768465042114258, | |
| "learning_rate": 1.7700000000000002e-06, | |
| "loss": 5.1159, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 4.07192, | |
| "eval_accuracy": 0.027984607336752263, | |
| "eval_loss": 4.856239318847656, | |
| "eval_runtime": 100.1894, | |
| "eval_samples_per_second": 35.862, | |
| "eval_steps_per_second": 2.246, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 4.07442, | |
| "grad_norm": 4.413668632507324, | |
| "learning_rate": 1.645e-06, | |
| "loss": 5.1087, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 4.07692, | |
| "grad_norm": 7.255640983581543, | |
| "learning_rate": 1.52e-06, | |
| "loss": 5.0892, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 4.07692, | |
| "eval_accuracy": 0.027881481662881083, | |
| "eval_loss": 4.846496105194092, | |
| "eval_runtime": 95.8083, | |
| "eval_samples_per_second": 37.502, | |
| "eval_steps_per_second": 2.348, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 4.07942, | |
| "grad_norm": 5.159695148468018, | |
| "learning_rate": 1.3952500000000001e-06, | |
| "loss": 5.0909, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 4.08192, | |
| "grad_norm": 4.329514026641846, | |
| "learning_rate": 1.27025e-06, | |
| "loss": 5.083, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 4.08192, | |
| "eval_accuracy": 0.02791671853561543, | |
| "eval_loss": 4.825800895690918, | |
| "eval_runtime": 92.6653, | |
| "eval_samples_per_second": 38.774, | |
| "eval_steps_per_second": 2.428, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 4.08442, | |
| "grad_norm": 6.477020263671875, | |
| "learning_rate": 1.14525e-06, | |
| "loss": 5.0699, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 4.08692, | |
| "grad_norm": 4.648099899291992, | |
| "learning_rate": 1.02025e-06, | |
| "loss": 5.0824, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 4.08692, | |
| "eval_accuracy": 0.028006647388423938, | |
| "eval_loss": 4.821605682373047, | |
| "eval_runtime": 103.4797, | |
| "eval_samples_per_second": 34.722, | |
| "eval_steps_per_second": 2.174, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 4.08942, | |
| "grad_norm": 5.26840877532959, | |
| "learning_rate": 8.952500000000001e-07, | |
| "loss": 5.0674, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 4.09192, | |
| "grad_norm": 5.00206184387207, | |
| "learning_rate": 7.7075e-07, | |
| "loss": 5.0774, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 4.09192, | |
| "eval_accuracy": 0.027867604593310027, | |
| "eval_loss": 4.817193984985352, | |
| "eval_runtime": 103.2721, | |
| "eval_samples_per_second": 34.792, | |
| "eval_steps_per_second": 2.179, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 4.09442, | |
| "grad_norm": 8.953470230102539, | |
| "learning_rate": 6.4575e-07, | |
| "loss": 5.0661, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 4.09692, | |
| "grad_norm": 4.821086406707764, | |
| "learning_rate": 5.207500000000001e-07, | |
| "loss": 5.0567, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 4.09692, | |
| "eval_accuracy": 0.027846652939251766, | |
| "eval_loss": 4.811811923980713, | |
| "eval_runtime": 129.0966, | |
| "eval_samples_per_second": 27.832, | |
| "eval_steps_per_second": 1.743, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 4.09942, | |
| "grad_norm": 5.411968231201172, | |
| "learning_rate": 3.9575000000000003e-07, | |
| "loss": 5.0657, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 4.10192, | |
| "grad_norm": 5.903570652008057, | |
| "learning_rate": 2.7075e-07, | |
| "loss": 5.0657, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 4.10192, | |
| "eval_accuracy": 0.02782066744623146, | |
| "eval_loss": 4.807706832885742, | |
| "eval_runtime": 126.5816, | |
| "eval_samples_per_second": 28.385, | |
| "eval_steps_per_second": 1.778, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 4.10442, | |
| "grad_norm": 4.718256950378418, | |
| "learning_rate": 1.4575000000000002e-07, | |
| "loss": 5.0755, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 4.10692, | |
| "grad_norm": 5.640545845031738, | |
| "learning_rate": 2.075e-08, | |
| "loss": 5.0751, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 4.10692, | |
| "eval_accuracy": 0.02785753691538593, | |
| "eval_loss": 4.805818557739258, | |
| "eval_runtime": 112.4779, | |
| "eval_samples_per_second": 31.944, | |
| "eval_steps_per_second": 2.0, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 4.10692, | |
| "step": 200000, | |
| "total_flos": 1.1895955925447475e+18, | |
| "train_loss": 6.0653790368652345, | |
| "train_runtime": 98053.9397, | |
| "train_samples_per_second": 32.635, | |
| "train_steps_per_second": 2.04 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 200000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1895955925447475e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |