| { | |
| "best_metric": 0.04876178875565529, | |
| "best_model_checkpoint": "/content/train/Qwen2-VL-7B-Instruct-unsloth-r4-rslora-bf16-tuned/checkpoint-220", | |
| "epoch": 1.6629001883239172, | |
| "eval_steps": 10, | |
| "global_step": 220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007532956685499058, | |
| "grad_norm": 0.29860490560531616, | |
| "learning_rate": 1e-05, | |
| "loss": 1.462, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015065913370998116, | |
| "grad_norm": 0.5057499408721924, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5835, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 0.32325854897499084, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4388, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.030131826741996232, | |
| "grad_norm": 0.357746422290802, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5551, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03766478342749529, | |
| "grad_norm": 0.6203590035438538, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6868, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 0.3148535192012787, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2584, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05273069679849341, | |
| "grad_norm": 0.8858975768089294, | |
| "learning_rate": 7e-05, | |
| "loss": 1.4839, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.060263653483992465, | |
| "grad_norm": 0.41307175159454346, | |
| "learning_rate": 8e-05, | |
| "loss": 1.465, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 0.711910605430603, | |
| "learning_rate": 9e-05, | |
| "loss": 1.4146, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07532956685499058, | |
| "grad_norm": 0.6907219886779785, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5244, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07532956685499058, | |
| "eval_loss": 1.4021275043487549, | |
| "eval_runtime": 60.9671, | |
| "eval_samples_per_second": 1.23, | |
| "eval_steps_per_second": 0.623, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08286252354048965, | |
| "grad_norm": 0.6071083545684814, | |
| "learning_rate": 9.999834399079165e-05, | |
| "loss": 1.5861, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 0.4335213601589203, | |
| "learning_rate": 9.99933760728612e-05, | |
| "loss": 1.3366, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09792843691148775, | |
| "grad_norm": 0.43898504972457886, | |
| "learning_rate": 9.99850965752854e-05, | |
| "loss": 1.2906, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10546139359698682, | |
| "grad_norm": 0.400079607963562, | |
| "learning_rate": 9.997350604650123e-05, | |
| "loss": 1.2677, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 0.41405242681503296, | |
| "learning_rate": 9.995860525426954e-05, | |
| "loss": 1.285, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12052730696798493, | |
| "grad_norm": 0.7896008491516113, | |
| "learning_rate": 9.994039518562432e-05, | |
| "loss": 1.1366, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.128060263653484, | |
| "grad_norm": 0.45816895365715027, | |
| "learning_rate": 9.991887704680724e-05, | |
| "loss": 1.2656, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.5465638637542725, | |
| "learning_rate": 9.989405226318772e-05, | |
| "loss": 1.362, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1431261770244821, | |
| "grad_norm": 0.46899810433387756, | |
| "learning_rate": 9.986592247916858e-05, | |
| "loss": 1.1479, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15065913370998116, | |
| "grad_norm": 0.5480923056602478, | |
| "learning_rate": 9.983448955807708e-05, | |
| "loss": 1.1834, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15065913370998116, | |
| "eval_loss": 1.1339441537857056, | |
| "eval_runtime": 50.1262, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15819209039548024, | |
| "grad_norm": 0.6135687232017517, | |
| "learning_rate": 9.979975558204147e-05, | |
| "loss": 1.1895, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1657250470809793, | |
| "grad_norm": 0.6562265753746033, | |
| "learning_rate": 9.976172285185314e-05, | |
| "loss": 1.1213, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17325800376647835, | |
| "grad_norm": 0.7003594040870667, | |
| "learning_rate": 9.972039388681413e-05, | |
| "loss": 1.1117, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 0.6009169220924377, | |
| "learning_rate": 9.967577142457032e-05, | |
| "loss": 1.0146, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18832391713747645, | |
| "grad_norm": 0.9375618696212769, | |
| "learning_rate": 9.962785842093003e-05, | |
| "loss": 1.0485, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1958568738229755, | |
| "grad_norm": 0.7120280861854553, | |
| "learning_rate": 9.957665804966829e-05, | |
| "loss": 0.8638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 0.9676161408424377, | |
| "learning_rate": 9.952217370231653e-05, | |
| "loss": 0.9569, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21092278719397364, | |
| "grad_norm": 0.8478333353996277, | |
| "learning_rate": 9.946440898793801e-05, | |
| "loss": 0.8989, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2184557438794727, | |
| "grad_norm": 0.9060878753662109, | |
| "learning_rate": 9.940336773288865e-05, | |
| "loss": 0.8083, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 0.9778569936752319, | |
| "learning_rate": 9.933905398056372e-05, | |
| "loss": 0.7268, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": 0.7190647125244141, | |
| "eval_runtime": 50.1226, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2335216572504708, | |
| "grad_norm": 0.9858911633491516, | |
| "learning_rate": 9.92714719911298e-05, | |
| "loss": 0.6885, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.24105461393596986, | |
| "grad_norm": 1.0453399419784546, | |
| "learning_rate": 9.920062624124282e-05, | |
| "loss": 0.6971, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.24858757062146894, | |
| "grad_norm": 0.9439508318901062, | |
| "learning_rate": 9.912652142375132e-05, | |
| "loss": 0.7523, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.256120527306968, | |
| "grad_norm": 0.8011656999588013, | |
| "learning_rate": 9.904916244738571e-05, | |
| "loss": 0.6094, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.263653483992467, | |
| "grad_norm": 0.8053231835365295, | |
| "learning_rate": 9.896855443643308e-05, | |
| "loss": 0.5719, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.7347720265388489, | |
| "learning_rate": 9.888470273039775e-05, | |
| "loss": 0.5913, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2787193973634652, | |
| "grad_norm": 0.8015826344490051, | |
| "learning_rate": 9.879761288364766e-05, | |
| "loss": 0.5636, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2862523540489642, | |
| "grad_norm": 0.4674820303916931, | |
| "learning_rate": 9.870729066504629e-05, | |
| "loss": 0.4962, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2937853107344633, | |
| "grad_norm": 0.3237204849720001, | |
| "learning_rate": 9.861374205757068e-05, | |
| "loss": 0.5201, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "grad_norm": 0.3314957320690155, | |
| "learning_rate": 9.851697325791505e-05, | |
| "loss": 0.5162, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "eval_loss": 0.4833310544490814, | |
| "eval_runtime": 50.1791, | |
| "eval_samples_per_second": 1.495, | |
| "eval_steps_per_second": 0.757, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3088512241054614, | |
| "grad_norm": 0.44042736291885376, | |
| "learning_rate": 9.841699067608033e-05, | |
| "loss": 0.4832, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3163841807909605, | |
| "grad_norm": 0.5744893550872803, | |
| "learning_rate": 9.831380093494957e-05, | |
| "loss": 0.4676, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3239171374764595, | |
| "grad_norm": 0.6231745481491089, | |
| "learning_rate": 9.820741086984924e-05, | |
| "loss": 0.4778, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3314500941619586, | |
| "grad_norm": 0.652641773223877, | |
| "learning_rate": 9.809782752809644e-05, | |
| "loss": 0.4618, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 0.34044504165649414, | |
| "learning_rate": 9.798505816853208e-05, | |
| "loss": 0.5053, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3465160075329567, | |
| "grad_norm": 0.3873239755630493, | |
| "learning_rate": 9.786911026104007e-05, | |
| "loss": 0.4319, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3540489642184557, | |
| "grad_norm": 0.34049129486083984, | |
| "learning_rate": 9.774999148605251e-05, | |
| "loss": 0.4713, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 0.39110735058784485, | |
| "learning_rate": 9.762770973404094e-05, | |
| "loss": 0.4605, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3691148775894539, | |
| "grad_norm": 0.3248206675052643, | |
| "learning_rate": 9.750227310499366e-05, | |
| "loss": 0.4259, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3766478342749529, | |
| "grad_norm": 0.624284029006958, | |
| "learning_rate": 9.737368990787916e-05, | |
| "loss": 0.3921, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3766478342749529, | |
| "eval_loss": 0.42401236295700073, | |
| "eval_runtime": 50.1482, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.384180790960452, | |
| "grad_norm": 0.3228764533996582, | |
| "learning_rate": 9.72419686600958e-05, | |
| "loss": 0.4269, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.391713747645951, | |
| "grad_norm": 0.2958717346191406, | |
| "learning_rate": 9.710711808690754e-05, | |
| "loss": 0.4804, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3992467043314501, | |
| "grad_norm": 0.5469731092453003, | |
| "learning_rate": 9.696914712086603e-05, | |
| "loss": 0.4463, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 0.35308223962783813, | |
| "learning_rate": 9.682806490121885e-05, | |
| "loss": 0.3708, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4143126177024482, | |
| "grad_norm": 0.4369649589061737, | |
| "learning_rate": 9.668388077330421e-05, | |
| "loss": 0.4226, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4218455743879473, | |
| "grad_norm": 0.7406517863273621, | |
| "learning_rate": 9.653660428793188e-05, | |
| "loss": 0.4082, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4293785310734463, | |
| "grad_norm": 0.4191276729106903, | |
| "learning_rate": 9.638624520075046e-05, | |
| "loss": 0.3736, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4369114877589454, | |
| "grad_norm": 0.3738877475261688, | |
| "learning_rate": 9.623281347160127e-05, | |
| "loss": 0.3987, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.3371034562587738, | |
| "learning_rate": 9.607631926385859e-05, | |
| "loss": 0.4276, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 0.3625945746898651, | |
| "learning_rate": 9.591677294375636e-05, | |
| "loss": 0.3952, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "eval_loss": 0.3758457601070404, | |
| "eval_runtime": 50.0723, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4595103578154426, | |
| "grad_norm": 0.4314848780632019, | |
| "learning_rate": 9.575418507970161e-05, | |
| "loss": 0.4264, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4670433145009416, | |
| "grad_norm": 0.3458515703678131, | |
| "learning_rate": 9.558856644157432e-05, | |
| "loss": 0.3845, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": 0.30270910263061523, | |
| "learning_rate": 9.541992800001409e-05, | |
| "loss": 0.3984, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4821092278719397, | |
| "grad_norm": 0.3931046426296234, | |
| "learning_rate": 9.52482809256934e-05, | |
| "loss": 0.4019, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4896421845574388, | |
| "grad_norm": 0.49052339792251587, | |
| "learning_rate": 9.507363658857768e-05, | |
| "loss": 0.4353, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4971751412429379, | |
| "grad_norm": 0.3206973075866699, | |
| "learning_rate": 9.489600655717217e-05, | |
| "loss": 0.4599, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.504708097928437, | |
| "grad_norm": 0.36185964941978455, | |
| "learning_rate": 9.471540259775554e-05, | |
| "loss": 0.3684, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.512241054613936, | |
| "grad_norm": 0.4438144266605377, | |
| "learning_rate": 9.453183667360062e-05, | |
| "loss": 0.3924, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.519774011299435, | |
| "grad_norm": 0.408000111579895, | |
| "learning_rate": 9.43453209441818e-05, | |
| "loss": 0.3165, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.527306967984934, | |
| "grad_norm": 0.5293291211128235, | |
| "learning_rate": 9.415586776436973e-05, | |
| "loss": 0.3696, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.527306967984934, | |
| "eval_loss": 0.3250181972980499, | |
| "eval_runtime": 50.0681, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5348399246704332, | |
| "grad_norm": 0.7923517227172852, | |
| "learning_rate": 9.396348968361281e-05, | |
| "loss": 0.388, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.5696645975112915, | |
| "learning_rate": 9.376819944510598e-05, | |
| "loss": 0.3383, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5499058380414312, | |
| "grad_norm": 0.8812904357910156, | |
| "learning_rate": 9.357000998494656e-05, | |
| "loss": 0.2872, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5574387947269304, | |
| "grad_norm": 0.4949493110179901, | |
| "learning_rate": 9.336893443127738e-05, | |
| "loss": 0.3039, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5649717514124294, | |
| "grad_norm": 0.40088051557540894, | |
| "learning_rate": 9.31649861034172e-05, | |
| "loss": 0.3246, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5725047080979284, | |
| "grad_norm": 0.40099695324897766, | |
| "learning_rate": 9.295817851097837e-05, | |
| "loss": 0.3544, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5800376647834274, | |
| "grad_norm": 0.4039609432220459, | |
| "learning_rate": 9.274852535297198e-05, | |
| "loss": 0.333, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5875706214689266, | |
| "grad_norm": 0.46073368191719055, | |
| "learning_rate": 9.253604051690046e-05, | |
| "loss": 0.2505, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5951035781544256, | |
| "grad_norm": 0.3831747770309448, | |
| "learning_rate": 9.232073807783759e-05, | |
| "loss": 0.2545, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6026365348399246, | |
| "grad_norm": 0.668875515460968, | |
| "learning_rate": 9.210263229749626e-05, | |
| "loss": 0.2892, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6026365348399246, | |
| "eval_loss": 0.25938624143600464, | |
| "eval_runtime": 50.0589, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": 0.4702552556991577, | |
| "learning_rate": 9.188173762328367e-05, | |
| "loss": 0.259, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.6177024482109228, | |
| "grad_norm": 0.6220546364784241, | |
| "learning_rate": 9.165806868734444e-05, | |
| "loss": 0.2636, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.6252354048964218, | |
| "grad_norm": 0.526050329208374, | |
| "learning_rate": 9.143164030559122e-05, | |
| "loss": 0.2903, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 0.48076707124710083, | |
| "learning_rate": 9.120246747672347e-05, | |
| "loss": 0.2847, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.64030131826742, | |
| "grad_norm": 0.5487018823623657, | |
| "learning_rate": 9.097056538123376e-05, | |
| "loss": 0.2625, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.647834274952919, | |
| "grad_norm": 0.6256678700447083, | |
| "learning_rate": 9.073594938040231e-05, | |
| "loss": 0.267, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.655367231638418, | |
| "grad_norm": 0.6361900568008423, | |
| "learning_rate": 9.049863501527947e-05, | |
| "loss": 0.2927, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6629001883239172, | |
| "grad_norm": 0.5942044258117676, | |
| "learning_rate": 9.025863800565613e-05, | |
| "loss": 0.2995, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.6704331450094162, | |
| "grad_norm": 0.5061842203140259, | |
| "learning_rate": 9.001597424902267e-05, | |
| "loss": 0.232, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.826519250869751, | |
| "learning_rate": 8.977065981951566e-05, | |
| "loss": 0.2039, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "eval_loss": 0.2045535147190094, | |
| "eval_runtime": 50.1117, | |
| "eval_samples_per_second": 1.497, | |
| "eval_steps_per_second": 0.758, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6854990583804144, | |
| "grad_norm": 0.5888376832008362, | |
| "learning_rate": 8.952271096685332e-05, | |
| "loss": 0.1997, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6930320150659134, | |
| "grad_norm": 0.7269095182418823, | |
| "learning_rate": 8.927214411525895e-05, | |
| "loss": 0.2589, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.7005649717514124, | |
| "grad_norm": 0.8657869696617126, | |
| "learning_rate": 8.90189758623731e-05, | |
| "loss": 0.1956, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.7080979284369114, | |
| "grad_norm": 0.7702244520187378, | |
| "learning_rate": 8.876322297815405e-05, | |
| "loss": 0.2218, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.7156308851224106, | |
| "grad_norm": 0.6147786974906921, | |
| "learning_rate": 8.850490240376711e-05, | |
| "loss": 0.212, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 0.5774387717247009, | |
| "learning_rate": 8.824403125046225e-05, | |
| "loss": 0.1908, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.7306967984934086, | |
| "grad_norm": 0.75771164894104, | |
| "learning_rate": 8.798062679844077e-05, | |
| "loss": 0.1696, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.7382297551789078, | |
| "grad_norm": 0.6371806859970093, | |
| "learning_rate": 8.771470649571056e-05, | |
| "loss": 0.2085, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.7457627118644068, | |
| "grad_norm": 0.5286451578140259, | |
| "learning_rate": 8.744628795693047e-05, | |
| "loss": 0.1982, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.7532956685499058, | |
| "grad_norm": 0.5060010552406311, | |
| "learning_rate": 8.717538896224332e-05, | |
| "loss": 0.2027, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7532956685499058, | |
| "eval_loss": 0.1616896241903305, | |
| "eval_runtime": 50.0794, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7608286252354048, | |
| "grad_norm": 0.7836325764656067, | |
| "learning_rate": 8.690202745609835e-05, | |
| "loss": 0.1358, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.768361581920904, | |
| "grad_norm": 0.675710141658783, | |
| "learning_rate": 8.662622154606237e-05, | |
| "loss": 0.1846, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.775894538606403, | |
| "grad_norm": 0.8798868656158447, | |
| "learning_rate": 8.634798950162048e-05, | |
| "loss": 0.1966, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.783427495291902, | |
| "grad_norm": 0.5943530201911926, | |
| "learning_rate": 8.606734975296578e-05, | |
| "loss": 0.1632, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.7909604519774012, | |
| "grad_norm": 0.4987153708934784, | |
| "learning_rate": 8.578432088977859e-05, | |
| "loss": 0.1113, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7984934086629002, | |
| "grad_norm": 0.7684951424598694, | |
| "learning_rate": 8.549892165999505e-05, | |
| "loss": 0.1434, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.8060263653483992, | |
| "grad_norm": 0.624474823474884, | |
| "learning_rate": 8.521117096856528e-05, | |
| "loss": 0.1754, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 1.0357481241226196, | |
| "learning_rate": 8.492108787620105e-05, | |
| "loss": 0.1761, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.8210922787193974, | |
| "grad_norm": 0.7299608588218689, | |
| "learning_rate": 8.462869159811327e-05, | |
| "loss": 0.1145, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.8286252354048964, | |
| "grad_norm": 0.7747260332107544, | |
| "learning_rate": 8.433400150273906e-05, | |
| "loss": 0.1494, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8286252354048964, | |
| "eval_loss": 0.12168504297733307, | |
| "eval_runtime": 50.0938, | |
| "eval_samples_per_second": 1.497, | |
| "eval_steps_per_second": 0.759, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8361581920903954, | |
| "grad_norm": 0.7779563665390015, | |
| "learning_rate": 8.403703711045892e-05, | |
| "loss": 0.159, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.8436911487758946, | |
| "grad_norm": 1.1017848253250122, | |
| "learning_rate": 8.373781809230355e-05, | |
| "loss": 0.2012, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.8512241054613936, | |
| "grad_norm": 0.4848591983318329, | |
| "learning_rate": 8.343636426865096e-05, | |
| "loss": 0.1215, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.8587570621468926, | |
| "grad_norm": 0.8865452408790588, | |
| "learning_rate": 8.313269560791342e-05, | |
| "loss": 0.0923, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.8662900188323918, | |
| "grad_norm": 0.699765145778656, | |
| "learning_rate": 8.28268322252149e-05, | |
| "loss": 0.1587, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8738229755178908, | |
| "grad_norm": 0.5934118628501892, | |
| "learning_rate": 8.251879438105854e-05, | |
| "loss": 0.1288, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.8813559322033898, | |
| "grad_norm": 0.7120998501777649, | |
| "learning_rate": 8.220860247998456e-05, | |
| "loss": 0.101, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.0435795783996582, | |
| "learning_rate": 8.189627706921877e-05, | |
| "loss": 0.1067, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.896421845574388, | |
| "grad_norm": 1.4066674709320068, | |
| "learning_rate": 8.15818388373114e-05, | |
| "loss": 0.1313, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 0.7823694348335266, | |
| "learning_rate": 8.126530861276677e-05, | |
| "loss": 0.0863, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "eval_loss": 0.09002000838518143, | |
| "eval_runtime": 50.1325, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.911487758945386, | |
| "grad_norm": 0.617436945438385, | |
| "learning_rate": 8.094670736266353e-05, | |
| "loss": 0.0868, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.9190207156308852, | |
| "grad_norm": 0.602743923664093, | |
| "learning_rate": 8.062605619126584e-05, | |
| "loss": 0.0983, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.9265536723163842, | |
| "grad_norm": 1.1149927377700806, | |
| "learning_rate": 8.030337633862542e-05, | |
| "loss": 0.1078, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.9340866290018832, | |
| "grad_norm": 0.688164472579956, | |
| "learning_rate": 7.997868917917453e-05, | |
| "loss": 0.0722, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.9416195856873822, | |
| "grad_norm": 0.6507720351219177, | |
| "learning_rate": 7.965201622031021e-05, | |
| "loss": 0.0824, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.5873366594314575, | |
| "learning_rate": 7.932337910096961e-05, | |
| "loss": 0.0633, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.9566854990583804, | |
| "grad_norm": 0.48810163140296936, | |
| "learning_rate": 7.899279959019654e-05, | |
| "loss": 0.0579, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.9642184557438794, | |
| "grad_norm": 0.7808175086975098, | |
| "learning_rate": 7.866029958569956e-05, | |
| "loss": 0.0959, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.9717514124293786, | |
| "grad_norm": 0.7213129997253418, | |
| "learning_rate": 7.832590111240145e-05, | |
| "loss": 0.1074, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.9792843691148776, | |
| "grad_norm": 0.7429501414299011, | |
| "learning_rate": 7.798962632098024e-05, | |
| "loss": 0.0883, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9792843691148776, | |
| "eval_loss": 0.07171642780303955, | |
| "eval_runtime": 50.1218, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9868173258003766, | |
| "grad_norm": 1.2204382419586182, | |
| "learning_rate": 7.765149748640197e-05, | |
| "loss": 0.0543, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.9943502824858758, | |
| "grad_norm": 0.4847294092178345, | |
| "learning_rate": 7.73115370064452e-05, | |
| "loss": 0.0646, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.0075329566854991, | |
| "grad_norm": 0.7584130764007568, | |
| "learning_rate": 7.696976740021733e-05, | |
| "loss": 0.1122, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.015065913370998, | |
| "grad_norm": 0.4241285026073456, | |
| "learning_rate": 7.6626211306663e-05, | |
| "loss": 0.0382, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.0225988700564972, | |
| "grad_norm": 0.6364421844482422, | |
| "learning_rate": 7.628089148306434e-05, | |
| "loss": 0.0707, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0301318267419963, | |
| "grad_norm": 0.6198002099990845, | |
| "learning_rate": 7.59338308035337e-05, | |
| "loss": 0.0942, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.0376647834274952, | |
| "grad_norm": 0.43464764952659607, | |
| "learning_rate": 7.558505225749827e-05, | |
| "loss": 0.086, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.0451977401129944, | |
| "grad_norm": 0.3746040463447571, | |
| "learning_rate": 7.523457894817745e-05, | |
| "loss": 0.0426, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.0527306967984935, | |
| "grad_norm": 0.4349992573261261, | |
| "learning_rate": 7.488243409105233e-05, | |
| "loss": 0.0665, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.0602636534839924, | |
| "grad_norm": 0.44264963269233704, | |
| "learning_rate": 7.452864101232798e-05, | |
| "loss": 0.0854, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0602636534839924, | |
| "eval_loss": 0.061161428689956665, | |
| "eval_runtime": 50.0795, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0677966101694916, | |
| "grad_norm": 0.535400390625, | |
| "learning_rate": 7.417322314738822e-05, | |
| "loss": 0.0502, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.0753295668549905, | |
| "grad_norm": 0.4334566295146942, | |
| "learning_rate": 7.381620403924333e-05, | |
| "loss": 0.0547, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.0828625235404896, | |
| "grad_norm": 0.6763977408409119, | |
| "learning_rate": 7.345760733697055e-05, | |
| "loss": 0.0576, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.0903954802259888, | |
| "grad_norm": 0.6230652928352356, | |
| "learning_rate": 7.30974567941475e-05, | |
| "loss": 0.0746, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.0979284369114877, | |
| "grad_norm": 0.5115144848823547, | |
| "learning_rate": 7.273577626727884e-05, | |
| "loss": 0.0707, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.1054613935969868, | |
| "grad_norm": 0.4081382751464844, | |
| "learning_rate": 7.237258971421587e-05, | |
| "loss": 0.0417, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.112994350282486, | |
| "grad_norm": 0.45929810404777527, | |
| "learning_rate": 7.20079211925696e-05, | |
| "loss": 0.0402, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.1205273069679849, | |
| "grad_norm": 0.41027042269706726, | |
| "learning_rate": 7.164179485811727e-05, | |
| "loss": 0.057, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.128060263653484, | |
| "grad_norm": 0.732723593711853, | |
| "learning_rate": 7.127423496320212e-05, | |
| "loss": 0.0686, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.1355932203389831, | |
| "grad_norm": 0.4201294481754303, | |
| "learning_rate": 7.090526585512696e-05, | |
| "loss": 0.075, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1355932203389831, | |
| "eval_loss": 0.056692853569984436, | |
| "eval_runtime": 50.061, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.143126177024482, | |
| "grad_norm": 0.3101370930671692, | |
| "learning_rate": 7.053491197454142e-05, | |
| "loss": 0.0366, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.1506591337099812, | |
| "grad_norm": 0.4567885100841522, | |
| "learning_rate": 7.016319785382296e-05, | |
| "loss": 0.0778, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.1581920903954803, | |
| "grad_norm": 0.3678460419178009, | |
| "learning_rate": 6.979014811545189e-05, | |
| "loss": 0.0495, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.1657250470809792, | |
| "grad_norm": 0.5862255096435547, | |
| "learning_rate": 6.941578747038023e-05, | |
| "loss": 0.0735, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.1732580037664784, | |
| "grad_norm": 0.5297702550888062, | |
| "learning_rate": 6.904014071639503e-05, | |
| "loss": 0.034, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.1807909604519775, | |
| "grad_norm": 0.3692375123500824, | |
| "learning_rate": 6.866323273647563e-05, | |
| "loss": 0.0587, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.1883239171374764, | |
| "grad_norm": 0.3478219509124756, | |
| "learning_rate": 6.828508849714546e-05, | |
| "loss": 0.0676, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.1958568738229756, | |
| "grad_norm": 0.5066402554512024, | |
| "learning_rate": 6.79057330468182e-05, | |
| "loss": 0.0362, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.2033898305084745, | |
| "grad_norm": 0.38956108689308167, | |
| "learning_rate": 6.752519151413861e-05, | |
| "loss": 0.0475, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.2109227871939736, | |
| "grad_norm": 0.3372087776660919, | |
| "learning_rate": 6.7143489106318e-05, | |
| "loss": 0.0835, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2109227871939736, | |
| "eval_loss": 0.054186370223760605, | |
| "eval_runtime": 50.1057, | |
| "eval_samples_per_second": 1.497, | |
| "eval_steps_per_second": 0.758, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2184557438794728, | |
| "grad_norm": 0.4884163737297058, | |
| "learning_rate": 6.676065110746444e-05, | |
| "loss": 0.057, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.2259887005649717, | |
| "grad_norm": 0.42741522192955017, | |
| "learning_rate": 6.637670287690799e-05, | |
| "loss": 0.0493, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.2335216572504708, | |
| "grad_norm": 0.37808606028556824, | |
| "learning_rate": 6.599166984752087e-05, | |
| "loss": 0.0324, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.24105461393597, | |
| "grad_norm": 0.6114926934242249, | |
| "learning_rate": 6.560557752403277e-05, | |
| "loss": 0.0975, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.2485875706214689, | |
| "grad_norm": 0.2513774633407593, | |
| "learning_rate": 6.52184514813414e-05, | |
| "loss": 0.0323, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.256120527306968, | |
| "grad_norm": 0.319553941488266, | |
| "learning_rate": 6.483031736281843e-05, | |
| "loss": 0.0246, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.2636534839924671, | |
| "grad_norm": 0.6170870661735535, | |
| "learning_rate": 6.444120087861081e-05, | |
| "loss": 0.05, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.271186440677966, | |
| "grad_norm": 0.4168320596218109, | |
| "learning_rate": 6.40511278039378e-05, | |
| "loss": 0.0586, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.2787193973634652, | |
| "grad_norm": 0.3265027403831482, | |
| "learning_rate": 6.366012397738355e-05, | |
| "loss": 0.0666, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.286252354048964, | |
| "grad_norm": 0.609319806098938, | |
| "learning_rate": 6.326821529918553e-05, | |
| "loss": 0.085, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.286252354048964, | |
| "eval_loss": 0.053176406770944595, | |
| "eval_runtime": 50.1048, | |
| "eval_samples_per_second": 1.497, | |
| "eval_steps_per_second": 0.758, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2937853107344632, | |
| "grad_norm": 0.5599777698516846, | |
| "learning_rate": 6.287542772951897e-05, | |
| "loss": 0.0723, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.3013182674199624, | |
| "grad_norm": 0.4176930785179138, | |
| "learning_rate": 6.248178728677711e-05, | |
| "loss": 0.0728, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.3088512241054615, | |
| "grad_norm": 0.3369368314743042, | |
| "learning_rate": 6.208732004584791e-05, | |
| "loss": 0.0499, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.3163841807909604, | |
| "grad_norm": 0.45373421907424927, | |
| "learning_rate": 6.16920521363867e-05, | |
| "loss": 0.0792, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.3239171374764596, | |
| "grad_norm": 0.3415266275405884, | |
| "learning_rate": 6.129600974108538e-05, | |
| "loss": 0.048, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3314500941619585, | |
| "grad_norm": 0.5422535538673401, | |
| "learning_rate": 6.089921909393812e-05, | |
| "loss": 0.0883, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.3389830508474576, | |
| "grad_norm": 0.25546208024024963, | |
| "learning_rate": 6.050170647850351e-05, | |
| "loss": 0.0473, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.3465160075329567, | |
| "grad_norm": 0.5453774929046631, | |
| "learning_rate": 6.0103498226163603e-05, | |
| "loss": 0.0984, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.3540489642184557, | |
| "grad_norm": 0.340578556060791, | |
| "learning_rate": 5.970462071437973e-05, | |
| "loss": 0.0354, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.3615819209039548, | |
| "grad_norm": 0.4705830216407776, | |
| "learning_rate": 5.93051003649452e-05, | |
| "loss": 0.054, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3615819209039548, | |
| "eval_loss": 0.051415782421827316, | |
| "eval_runtime": 50.1031, | |
| "eval_samples_per_second": 1.497, | |
| "eval_steps_per_second": 0.758, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.369114877589454, | |
| "grad_norm": 0.5732293128967285, | |
| "learning_rate": 5.890496364223509e-05, | |
| "loss": 0.0626, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.3766478342749529, | |
| "grad_norm": 0.4315062463283539, | |
| "learning_rate": 5.850423705145334e-05, | |
| "loss": 0.0613, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.384180790960452, | |
| "grad_norm": 0.5873361825942993, | |
| "learning_rate": 5.8102947136876876e-05, | |
| "loss": 0.0915, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.3917137476459511, | |
| "grad_norm": 0.2784740626811981, | |
| "learning_rate": 5.770112048009747e-05, | |
| "loss": 0.0259, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.39924670433145, | |
| "grad_norm": 0.36659327149391174, | |
| "learning_rate": 5.7298783698260874e-05, | |
| "loss": 0.0643, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.4067796610169492, | |
| "grad_norm": 0.31498560309410095, | |
| "learning_rate": 5.68959634423037e-05, | |
| "loss": 0.0345, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.414312617702448, | |
| "grad_norm": 0.4332311451435089, | |
| "learning_rate": 5.64926863951881e-05, | |
| "loss": 0.0461, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.4218455743879472, | |
| "grad_norm": 0.35596826672554016, | |
| "learning_rate": 5.60889792701342e-05, | |
| "loss": 0.032, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.4293785310734464, | |
| "grad_norm": 0.43455907702445984, | |
| "learning_rate": 5.568486880885068e-05, | |
| "loss": 0.0283, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.4369114877589455, | |
| "grad_norm": 2.2231392860412598, | |
| "learning_rate": 5.52803817797633e-05, | |
| "loss": 0.0337, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4369114877589455, | |
| "eval_loss": 0.050475846976041794, | |
| "eval_runtime": 50.1291, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 0.3397436738014221, | |
| "learning_rate": 5.487554497624189e-05, | |
| "loss": 0.0481, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.4519774011299436, | |
| "grad_norm": 0.3190496265888214, | |
| "learning_rate": 5.4470385214825416e-05, | |
| "loss": 0.0606, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.4595103578154425, | |
| "grad_norm": 0.3939787447452545, | |
| "learning_rate": 5.406492933344571e-05, | |
| "loss": 0.1776, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.4670433145009416, | |
| "grad_norm": 0.33525291085243225, | |
| "learning_rate": 5.365920418964973e-05, | |
| "loss": 0.0516, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.4745762711864407, | |
| "grad_norm": 0.32538145780563354, | |
| "learning_rate": 5.3253236658820396e-05, | |
| "loss": 0.0465, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.4821092278719397, | |
| "grad_norm": 0.3278179466724396, | |
| "learning_rate": 5.28470536323965e-05, | |
| "loss": 0.067, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.4896421845574388, | |
| "grad_norm": 0.41677576303482056, | |
| "learning_rate": 5.244068201609133e-05, | |
| "loss": 0.0519, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.497175141242938, | |
| "grad_norm": 0.44194525480270386, | |
| "learning_rate": 5.2034148728110424e-05, | |
| "loss": 0.0686, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.5047080979284368, | |
| "grad_norm": 0.3261134922504425, | |
| "learning_rate": 5.162748069736851e-05, | |
| "loss": 0.0534, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.512241054613936, | |
| "grad_norm": 0.4644230008125305, | |
| "learning_rate": 5.1220704861705774e-05, | |
| "loss": 0.0421, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.512241054613936, | |
| "eval_loss": 0.04965050518512726, | |
| "eval_runtime": 50.0829, | |
| "eval_samples_per_second": 1.498, | |
| "eval_steps_per_second": 0.759, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5197740112994351, | |
| "grad_norm": 0.3440283238887787, | |
| "learning_rate": 5.081384816610336e-05, | |
| "loss": 0.0621, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.527306967984934, | |
| "grad_norm": 0.2635885179042816, | |
| "learning_rate": 5.0406937560898646e-05, | |
| "loss": 0.0443, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.5348399246704332, | |
| "grad_norm": 0.6189826726913452, | |
| "learning_rate": 5e-05, | |
| "loss": 0.084, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.542372881355932, | |
| "grad_norm": 0.3221701383590698, | |
| "learning_rate": 4.9593062439101365e-05, | |
| "loss": 0.0348, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.5499058380414312, | |
| "grad_norm": 0.30998164415359497, | |
| "learning_rate": 4.918615183389665e-05, | |
| "loss": 0.0529, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.5574387947269304, | |
| "grad_norm": 0.47885751724243164, | |
| "learning_rate": 4.877929513829424e-05, | |
| "loss": 0.0454, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.5649717514124295, | |
| "grad_norm": 0.5070298910140991, | |
| "learning_rate": 4.8372519302631486e-05, | |
| "loss": 0.0473, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.5725047080979284, | |
| "grad_norm": 0.3871539533138275, | |
| "learning_rate": 4.796585127188958e-05, | |
| "loss": 0.056, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.5800376647834273, | |
| "grad_norm": 0.4367206394672394, | |
| "learning_rate": 4.755931798390867e-05, | |
| "loss": 0.0734, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.5875706214689265, | |
| "grad_norm": 0.2854059338569641, | |
| "learning_rate": 4.715294636760352e-05, | |
| "loss": 0.0563, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5875706214689265, | |
| "eval_loss": 0.04947199299931526, | |
| "eval_runtime": 50.1478, | |
| "eval_samples_per_second": 1.496, | |
| "eval_steps_per_second": 0.758, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5951035781544256, | |
| "grad_norm": 0.3172830641269684, | |
| "learning_rate": 4.674676334117962e-05, | |
| "loss": 0.0356, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.6026365348399247, | |
| "grad_norm": 0.5930951237678528, | |
| "learning_rate": 4.634079581035029e-05, | |
| "loss": 0.0687, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.6101694915254239, | |
| "grad_norm": 0.3214702010154724, | |
| "learning_rate": 4.59350706665543e-05, | |
| "loss": 0.0433, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.6177024482109228, | |
| "grad_norm": 0.3200390636920929, | |
| "learning_rate": 4.55296147851746e-05, | |
| "loss": 0.0518, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.6252354048964217, | |
| "grad_norm": 0.32656821608543396, | |
| "learning_rate": 4.512445502375813e-05, | |
| "loss": 0.0391, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.6327683615819208, | |
| "grad_norm": 0.45625510811805725, | |
| "learning_rate": 4.471961822023671e-05, | |
| "loss": 0.0244, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.64030131826742, | |
| "grad_norm": 0.32512399554252625, | |
| "learning_rate": 4.431513119114934e-05, | |
| "loss": 0.1139, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.6478342749529191, | |
| "grad_norm": 0.3270999491214752, | |
| "learning_rate": 4.391102072986581e-05, | |
| "loss": 0.0988, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.655367231638418, | |
| "grad_norm": 0.44575634598731995, | |
| "learning_rate": 4.350731360481191e-05, | |
| "loss": 0.0525, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.6629001883239172, | |
| "grad_norm": 0.3585101366043091, | |
| "learning_rate": 4.3104036557696295e-05, | |
| "loss": 0.186, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6629001883239172, | |
| "eval_loss": 0.04876178875565529, | |
| "eval_runtime": 50.0932, | |
| "eval_samples_per_second": 1.497, | |
| "eval_steps_per_second": 0.759, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6629001883239172, | |
| "step": 220, | |
| "total_flos": 6.808102961998848e+16, | |
| "train_loss": 0.33265126400034534, | |
| "train_runtime": 4751.8019, | |
| "train_samples_per_second": 0.67, | |
| "train_steps_per_second": 0.083 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 396, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "early_stopping_threshold": 0.0015 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 4 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.808102961998848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |