| { | |
| "best_metric": 0.5939880609512329, | |
| "best_model_checkpoint": "/mnt/data1/sheshuaijie/Output/CoT/Trained/vicuna-13b_english-cot+auto-cot_0.0002/lora/checkpoint-1036", | |
| "epoch": 9.929896907216495, | |
| "global_step": 1505, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.7208857536315918, | |
| "eval_runtime": 39.046, | |
| "eval_samples_per_second": 76.832, | |
| "eval_steps_per_second": 2.407, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.3302656412124634, | |
| "eval_runtime": 39.1446, | |
| "eval_samples_per_second": 76.639, | |
| "eval_steps_per_second": 2.401, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019933110367892977, | |
| "loss": 1.607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.0993696451187134, | |
| "eval_runtime": 39.2624, | |
| "eval_samples_per_second": 76.409, | |
| "eval_steps_per_second": 2.394, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.9883869886398315, | |
| "eval_runtime": 39.2607, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.9121341109275818, | |
| "eval_runtime": 39.2818, | |
| "eval_samples_per_second": 76.371, | |
| "eval_steps_per_second": 2.393, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019665551839464883, | |
| "loss": 1.0077, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.8665392398834229, | |
| "eval_runtime": 39.261, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.8299428820610046, | |
| "eval_runtime": 39.2723, | |
| "eval_samples_per_second": 76.39, | |
| "eval_steps_per_second": 2.394, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.7965301275253296, | |
| "eval_runtime": 39.2718, | |
| "eval_samples_per_second": 76.391, | |
| "eval_steps_per_second": 2.394, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001939799331103679, | |
| "loss": 0.8626, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.7661889791488647, | |
| "eval_runtime": 39.2752, | |
| "eval_samples_per_second": 76.384, | |
| "eval_steps_per_second": 2.393, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.744417130947113, | |
| "eval_runtime": 39.2899, | |
| "eval_samples_per_second": 76.355, | |
| "eval_steps_per_second": 2.392, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.728394627571106, | |
| "eval_runtime": 39.298, | |
| "eval_samples_per_second": 76.34, | |
| "eval_steps_per_second": 2.392, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00019130434782608697, | |
| "loss": 0.7683, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.7151542901992798, | |
| "eval_runtime": 39.272, | |
| "eval_samples_per_second": 76.39, | |
| "eval_steps_per_second": 2.394, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.7049417495727539, | |
| "eval_runtime": 39.2657, | |
| "eval_samples_per_second": 76.403, | |
| "eval_steps_per_second": 2.394, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.6961150765419006, | |
| "eval_runtime": 39.2274, | |
| "eval_samples_per_second": 76.477, | |
| "eval_steps_per_second": 2.396, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00018862876254180605, | |
| "loss": 0.7346, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.6891586780548096, | |
| "eval_runtime": 39.2698, | |
| "eval_samples_per_second": 76.395, | |
| "eval_steps_per_second": 2.394, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.6833620667457581, | |
| "eval_runtime": 39.2474, | |
| "eval_samples_per_second": 76.438, | |
| "eval_steps_per_second": 2.395, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.678981602191925, | |
| "eval_runtime": 39.2363, | |
| "eval_samples_per_second": 76.46, | |
| "eval_steps_per_second": 2.396, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001859531772575251, | |
| "loss": 0.7095, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.6739740967750549, | |
| "eval_runtime": 39.2467, | |
| "eval_samples_per_second": 76.439, | |
| "eval_steps_per_second": 2.395, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.6704814434051514, | |
| "eval_runtime": 39.2828, | |
| "eval_samples_per_second": 76.369, | |
| "eval_steps_per_second": 2.393, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00018327759197324413, | |
| "loss": 0.6989, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.6668062210083008, | |
| "eval_runtime": 39.1861, | |
| "eval_samples_per_second": 76.558, | |
| "eval_steps_per_second": 2.399, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.6635003089904785, | |
| "eval_runtime": 39.2627, | |
| "eval_samples_per_second": 76.408, | |
| "eval_steps_per_second": 2.394, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.6594184637069702, | |
| "eval_runtime": 39.2634, | |
| "eval_samples_per_second": 76.407, | |
| "eval_steps_per_second": 2.394, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00018060200668896322, | |
| "loss": 0.6753, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.656818151473999, | |
| "eval_runtime": 39.2093, | |
| "eval_samples_per_second": 76.513, | |
| "eval_steps_per_second": 2.397, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.6542237401008606, | |
| "eval_runtime": 39.2619, | |
| "eval_samples_per_second": 76.41, | |
| "eval_steps_per_second": 2.394, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.6509793400764465, | |
| "eval_runtime": 39.2795, | |
| "eval_samples_per_second": 76.376, | |
| "eval_steps_per_second": 2.393, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00017792642140468227, | |
| "loss": 0.6742, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.6501123905181885, | |
| "eval_runtime": 39.2889, | |
| "eval_samples_per_second": 76.357, | |
| "eval_steps_per_second": 2.393, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.6488311290740967, | |
| "eval_runtime": 39.2821, | |
| "eval_samples_per_second": 76.371, | |
| "eval_steps_per_second": 2.393, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.6458473205566406, | |
| "eval_runtime": 39.2749, | |
| "eval_samples_per_second": 76.385, | |
| "eval_steps_per_second": 2.393, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00017525083612040135, | |
| "loss": 0.6727, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.6445983648300171, | |
| "eval_runtime": 39.2655, | |
| "eval_samples_per_second": 76.403, | |
| "eval_steps_per_second": 2.394, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.6414983868598938, | |
| "eval_runtime": 39.2575, | |
| "eval_samples_per_second": 76.418, | |
| "eval_steps_per_second": 2.394, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.6403743624687195, | |
| "eval_runtime": 39.2601, | |
| "eval_samples_per_second": 76.413, | |
| "eval_steps_per_second": 2.394, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0001725752508361204, | |
| "loss": 0.6651, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.6375772953033447, | |
| "eval_runtime": 39.2616, | |
| "eval_samples_per_second": 76.411, | |
| "eval_steps_per_second": 2.394, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.6363030076026917, | |
| "eval_runtime": 39.2685, | |
| "eval_samples_per_second": 76.397, | |
| "eval_steps_per_second": 2.394, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.6365154981613159, | |
| "eval_runtime": 39.2615, | |
| "eval_samples_per_second": 76.411, | |
| "eval_steps_per_second": 2.394, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00016989966555183946, | |
| "loss": 0.6569, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.6351213455200195, | |
| "eval_runtime": 39.2374, | |
| "eval_samples_per_second": 76.458, | |
| "eval_steps_per_second": 2.396, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.633696436882019, | |
| "eval_runtime": 39.2576, | |
| "eval_samples_per_second": 76.418, | |
| "eval_steps_per_second": 2.394, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.6320024132728577, | |
| "eval_runtime": 39.2456, | |
| "eval_samples_per_second": 76.442, | |
| "eval_steps_per_second": 2.395, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00016722408026755855, | |
| "loss": 0.6535, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.6302981972694397, | |
| "eval_runtime": 39.2723, | |
| "eval_samples_per_second": 76.39, | |
| "eval_steps_per_second": 2.394, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.6285908818244934, | |
| "eval_runtime": 39.2745, | |
| "eval_samples_per_second": 76.385, | |
| "eval_steps_per_second": 2.393, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001645484949832776, | |
| "loss": 0.6504, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.6279519200325012, | |
| "eval_runtime": 39.1978, | |
| "eval_samples_per_second": 76.535, | |
| "eval_steps_per_second": 2.398, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.6275761723518372, | |
| "eval_runtime": 39.2574, | |
| "eval_samples_per_second": 76.419, | |
| "eval_steps_per_second": 2.394, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.6262693405151367, | |
| "eval_runtime": 39.2587, | |
| "eval_samples_per_second": 76.416, | |
| "eval_steps_per_second": 2.394, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00016187290969899666, | |
| "loss": 0.6447, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.6255723237991333, | |
| "eval_runtime": 39.2593, | |
| "eval_samples_per_second": 76.415, | |
| "eval_steps_per_second": 2.394, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.624893307685852, | |
| "eval_runtime": 39.2732, | |
| "eval_samples_per_second": 76.388, | |
| "eval_steps_per_second": 2.393, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.6238787174224854, | |
| "eval_runtime": 39.2648, | |
| "eval_samples_per_second": 76.404, | |
| "eval_steps_per_second": 2.394, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00015919732441471574, | |
| "loss": 0.6418, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.6227560043334961, | |
| "eval_runtime": 39.2517, | |
| "eval_samples_per_second": 76.43, | |
| "eval_steps_per_second": 2.395, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.621408998966217, | |
| "eval_runtime": 39.2673, | |
| "eval_samples_per_second": 76.4, | |
| "eval_steps_per_second": 2.394, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.6207154989242554, | |
| "eval_runtime": 39.2707, | |
| "eval_samples_per_second": 76.393, | |
| "eval_steps_per_second": 2.394, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0001565217391304348, | |
| "loss": 0.6294, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.6207785606384277, | |
| "eval_runtime": 39.2687, | |
| "eval_samples_per_second": 76.397, | |
| "eval_steps_per_second": 2.394, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.619699239730835, | |
| "eval_runtime": 39.2528, | |
| "eval_samples_per_second": 76.428, | |
| "eval_steps_per_second": 2.395, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.6189907789230347, | |
| "eval_runtime": 39.2383, | |
| "eval_samples_per_second": 76.456, | |
| "eval_steps_per_second": 2.396, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.6323, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.6188793182373047, | |
| "eval_runtime": 39.2507, | |
| "eval_samples_per_second": 76.432, | |
| "eval_steps_per_second": 2.395, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.6180170774459839, | |
| "eval_runtime": 39.2506, | |
| "eval_samples_per_second": 76.432, | |
| "eval_steps_per_second": 2.395, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.6175986528396606, | |
| "eval_runtime": 39.2493, | |
| "eval_samples_per_second": 76.434, | |
| "eval_steps_per_second": 2.395, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00015117056856187293, | |
| "loss": 0.6194, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.6155608296394348, | |
| "eval_runtime": 39.2549, | |
| "eval_samples_per_second": 76.424, | |
| "eval_steps_per_second": 2.395, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.6149768829345703, | |
| "eval_runtime": 39.2507, | |
| "eval_samples_per_second": 76.432, | |
| "eval_steps_per_second": 2.395, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.614321768283844, | |
| "eval_runtime": 39.2607, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00014849498327759196, | |
| "loss": 0.6165, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.6136913299560547, | |
| "eval_runtime": 39.256, | |
| "eval_samples_per_second": 76.422, | |
| "eval_steps_per_second": 2.395, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.6127980351448059, | |
| "eval_runtime": 39.2695, | |
| "eval_samples_per_second": 76.395, | |
| "eval_steps_per_second": 2.394, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00014581939799331104, | |
| "loss": 0.6202, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.6126558780670166, | |
| "eval_runtime": 39.2344, | |
| "eval_samples_per_second": 76.464, | |
| "eval_steps_per_second": 2.396, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.6126319766044617, | |
| "eval_runtime": 39.2692, | |
| "eval_samples_per_second": 76.396, | |
| "eval_steps_per_second": 2.394, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.6124591827392578, | |
| "eval_runtime": 39.2771, | |
| "eval_samples_per_second": 76.38, | |
| "eval_steps_per_second": 2.393, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0001431438127090301, | |
| "loss": 0.6186, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.6117784976959229, | |
| "eval_runtime": 39.2494, | |
| "eval_samples_per_second": 76.434, | |
| "eval_steps_per_second": 2.395, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.6105948090553284, | |
| "eval_runtime": 39.2716, | |
| "eval_samples_per_second": 76.391, | |
| "eval_steps_per_second": 2.394, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6107361912727356, | |
| "eval_runtime": 39.2828, | |
| "eval_samples_per_second": 76.369, | |
| "eval_steps_per_second": 2.393, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.00014046822742474916, | |
| "loss": 0.6165, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.6106633543968201, | |
| "eval_runtime": 39.2701, | |
| "eval_samples_per_second": 76.394, | |
| "eval_steps_per_second": 2.394, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.6104211807250977, | |
| "eval_runtime": 39.2794, | |
| "eval_samples_per_second": 76.376, | |
| "eval_steps_per_second": 2.393, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 0.611173152923584, | |
| "eval_runtime": 39.2596, | |
| "eval_samples_per_second": 76.415, | |
| "eval_steps_per_second": 2.394, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00013779264214046824, | |
| "loss": 0.6021, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_loss": 0.6094884276390076, | |
| "eval_runtime": 39.2429, | |
| "eval_samples_per_second": 76.447, | |
| "eval_steps_per_second": 2.395, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_loss": 0.6093204617500305, | |
| "eval_runtime": 39.278, | |
| "eval_samples_per_second": 76.379, | |
| "eval_steps_per_second": 2.393, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 0.60869961977005, | |
| "eval_runtime": 39.269, | |
| "eval_samples_per_second": 76.396, | |
| "eval_steps_per_second": 2.394, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.0001351170568561873, | |
| "loss": 0.6057, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 0.6093556880950928, | |
| "eval_runtime": 39.2597, | |
| "eval_samples_per_second": 76.414, | |
| "eval_steps_per_second": 2.394, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "eval_loss": 0.6078519821166992, | |
| "eval_runtime": 39.2561, | |
| "eval_samples_per_second": 76.421, | |
| "eval_steps_per_second": 2.395, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "eval_loss": 0.6079010367393494, | |
| "eval_runtime": 39.2536, | |
| "eval_samples_per_second": 76.426, | |
| "eval_steps_per_second": 2.395, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.00013244147157190635, | |
| "loss": 0.598, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_loss": 0.6074483394622803, | |
| "eval_runtime": 39.2832, | |
| "eval_samples_per_second": 76.369, | |
| "eval_steps_per_second": 2.393, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 0.6073596477508545, | |
| "eval_runtime": 39.2701, | |
| "eval_samples_per_second": 76.394, | |
| "eval_steps_per_second": 2.394, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_loss": 0.606430172920227, | |
| "eval_runtime": 39.2546, | |
| "eval_samples_per_second": 76.424, | |
| "eval_steps_per_second": 2.395, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.00012976588628762543, | |
| "loss": 0.5948, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.6060574650764465, | |
| "eval_runtime": 39.2503, | |
| "eval_samples_per_second": 76.433, | |
| "eval_steps_per_second": 2.395, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 0.6067923307418823, | |
| "eval_runtime": 39.2654, | |
| "eval_samples_per_second": 76.403, | |
| "eval_steps_per_second": 2.394, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0001270903010033445, | |
| "loss": 0.5962, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 0.6042212843894958, | |
| "eval_runtime": 39.2032, | |
| "eval_samples_per_second": 76.524, | |
| "eval_steps_per_second": 2.398, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_loss": 0.6041299700737, | |
| "eval_runtime": 39.2396, | |
| "eval_samples_per_second": 76.453, | |
| "eval_steps_per_second": 2.396, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 0.6047356128692627, | |
| "eval_runtime": 39.274, | |
| "eval_samples_per_second": 76.386, | |
| "eval_steps_per_second": 2.393, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00012441471571906357, | |
| "loss": 0.5977, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_loss": 0.6040154099464417, | |
| "eval_runtime": 39.2677, | |
| "eval_samples_per_second": 76.399, | |
| "eval_steps_per_second": 2.394, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.603416383266449, | |
| "eval_runtime": 39.2621, | |
| "eval_samples_per_second": 76.41, | |
| "eval_steps_per_second": 2.394, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_loss": 0.6036480069160461, | |
| "eval_runtime": 39.2609, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 0.00012173913043478263, | |
| "loss": 0.5903, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 0.6035267114639282, | |
| "eval_runtime": 39.2828, | |
| "eval_samples_per_second": 76.369, | |
| "eval_steps_per_second": 2.393, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_loss": 0.6025964617729187, | |
| "eval_runtime": 39.2634, | |
| "eval_samples_per_second": 76.407, | |
| "eval_steps_per_second": 2.394, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 0.6028868556022644, | |
| "eval_runtime": 39.2591, | |
| "eval_samples_per_second": 76.415, | |
| "eval_steps_per_second": 2.394, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0001190635451505017, | |
| "loss": 0.5927, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.6027114391326904, | |
| "eval_runtime": 39.2648, | |
| "eval_samples_per_second": 76.404, | |
| "eval_steps_per_second": 2.394, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_loss": 0.6030986905097961, | |
| "eval_runtime": 39.2746, | |
| "eval_samples_per_second": 76.385, | |
| "eval_steps_per_second": 2.393, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_loss": 0.6026434898376465, | |
| "eval_runtime": 39.2646, | |
| "eval_samples_per_second": 76.405, | |
| "eval_steps_per_second": 2.394, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00011638795986622074, | |
| "loss": 0.581, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "eval_loss": 0.6008206009864807, | |
| "eval_runtime": 39.2718, | |
| "eval_samples_per_second": 76.391, | |
| "eval_steps_per_second": 2.394, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_loss": 0.6018855571746826, | |
| "eval_runtime": 39.2587, | |
| "eval_samples_per_second": 76.416, | |
| "eval_steps_per_second": 2.394, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "eval_loss": 0.6018174886703491, | |
| "eval_runtime": 39.2445, | |
| "eval_samples_per_second": 76.444, | |
| "eval_steps_per_second": 2.395, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.00011371237458193979, | |
| "loss": 0.5965, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 0.6006762981414795, | |
| "eval_runtime": 39.2498, | |
| "eval_samples_per_second": 76.433, | |
| "eval_steps_per_second": 2.395, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 0.6006374359130859, | |
| "eval_runtime": 39.2758, | |
| "eval_samples_per_second": 76.383, | |
| "eval_steps_per_second": 2.393, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.5997828245162964, | |
| "eval_runtime": 39.2794, | |
| "eval_samples_per_second": 76.376, | |
| "eval_steps_per_second": 2.393, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00011103678929765886, | |
| "loss": 0.5896, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "eval_loss": 0.6000981330871582, | |
| "eval_runtime": 39.2629, | |
| "eval_samples_per_second": 76.408, | |
| "eval_steps_per_second": 2.394, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 0.5991115570068359, | |
| "eval_runtime": 39.2774, | |
| "eval_samples_per_second": 76.38, | |
| "eval_steps_per_second": 2.393, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.00010836120401337793, | |
| "loss": 0.5854, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "eval_loss": 0.6001954674720764, | |
| "eval_runtime": 39.2333, | |
| "eval_samples_per_second": 76.466, | |
| "eval_steps_per_second": 2.396, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "eval_loss": 0.6007575988769531, | |
| "eval_runtime": 39.2801, | |
| "eval_samples_per_second": 76.374, | |
| "eval_steps_per_second": 2.393, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "eval_loss": 0.5983864068984985, | |
| "eval_runtime": 39.2469, | |
| "eval_samples_per_second": 76.439, | |
| "eval_steps_per_second": 2.395, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.00010568561872909698, | |
| "loss": 0.5844, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_loss": 0.5985506772994995, | |
| "eval_runtime": 39.2426, | |
| "eval_samples_per_second": 76.448, | |
| "eval_steps_per_second": 2.395, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 0.5978309512138367, | |
| "eval_runtime": 39.2604, | |
| "eval_samples_per_second": 76.413, | |
| "eval_steps_per_second": 2.394, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_loss": 0.5981310606002808, | |
| "eval_runtime": 39.2686, | |
| "eval_samples_per_second": 76.397, | |
| "eval_steps_per_second": 2.394, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.00010301003344481605, | |
| "loss": 0.5784, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_loss": 0.5985335111618042, | |
| "eval_runtime": 39.2557, | |
| "eval_samples_per_second": 76.422, | |
| "eval_steps_per_second": 2.395, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_loss": 0.5975944995880127, | |
| "eval_runtime": 39.2644, | |
| "eval_samples_per_second": 76.405, | |
| "eval_steps_per_second": 2.394, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.596754252910614, | |
| "eval_runtime": 39.2365, | |
| "eval_samples_per_second": 76.459, | |
| "eval_steps_per_second": 2.396, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.00010033444816053512, | |
| "loss": 0.5825, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 0.5977214574813843, | |
| "eval_runtime": 39.235, | |
| "eval_samples_per_second": 76.462, | |
| "eval_steps_per_second": 2.396, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 0.5982287526130676, | |
| "eval_runtime": 39.2483, | |
| "eval_samples_per_second": 76.436, | |
| "eval_steps_per_second": 2.395, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_loss": 0.5973477959632874, | |
| "eval_runtime": 39.2692, | |
| "eval_samples_per_second": 76.396, | |
| "eval_steps_per_second": 2.394, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 9.765886287625419e-05, | |
| "loss": 0.5724, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_loss": 0.598833441734314, | |
| "eval_runtime": 39.2608, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_loss": 0.5973609089851379, | |
| "eval_runtime": 39.2557, | |
| "eval_samples_per_second": 76.422, | |
| "eval_steps_per_second": 2.395, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_loss": 0.5983055233955383, | |
| "eval_runtime": 39.2613, | |
| "eval_samples_per_second": 76.411, | |
| "eval_steps_per_second": 2.394, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 9.498327759197325e-05, | |
| "loss": 0.5765, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "eval_loss": 0.597219705581665, | |
| "eval_runtime": 39.2532, | |
| "eval_samples_per_second": 76.427, | |
| "eval_steps_per_second": 2.395, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "eval_loss": 0.5974920392036438, | |
| "eval_runtime": 39.2428, | |
| "eval_samples_per_second": 76.447, | |
| "eval_steps_per_second": 2.395, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "eval_loss": 0.5970295667648315, | |
| "eval_runtime": 39.2255, | |
| "eval_samples_per_second": 76.481, | |
| "eval_steps_per_second": 2.396, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.5662, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 0.5995200872421265, | |
| "eval_runtime": 39.2763, | |
| "eval_samples_per_second": 76.382, | |
| "eval_steps_per_second": 2.393, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "eval_loss": 0.5961365699768066, | |
| "eval_runtime": 39.2442, | |
| "eval_samples_per_second": 76.444, | |
| "eval_steps_per_second": 2.395, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 8.963210702341137e-05, | |
| "loss": 0.5594, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_loss": 0.5958811640739441, | |
| "eval_runtime": 39.224, | |
| "eval_samples_per_second": 76.484, | |
| "eval_steps_per_second": 2.396, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_loss": 0.5974062085151672, | |
| "eval_runtime": 39.2479, | |
| "eval_samples_per_second": 76.437, | |
| "eval_steps_per_second": 2.395, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "eval_loss": 0.5959305167198181, | |
| "eval_runtime": 39.1122, | |
| "eval_samples_per_second": 76.702, | |
| "eval_steps_per_second": 2.403, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 8.695652173913044e-05, | |
| "loss": 0.5569, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "eval_loss": 0.597082257270813, | |
| "eval_runtime": 39.2419, | |
| "eval_samples_per_second": 76.449, | |
| "eval_steps_per_second": 2.395, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 0.5964935421943665, | |
| "eval_runtime": 39.2482, | |
| "eval_samples_per_second": 76.437, | |
| "eval_steps_per_second": 2.395, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 0.596628725528717, | |
| "eval_runtime": 39.2684, | |
| "eval_samples_per_second": 76.397, | |
| "eval_steps_per_second": 2.394, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 8.42809364548495e-05, | |
| "loss": 0.5711, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "eval_loss": 0.596688449382782, | |
| "eval_runtime": 39.262, | |
| "eval_samples_per_second": 76.41, | |
| "eval_steps_per_second": 2.394, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "eval_loss": 0.5974501967430115, | |
| "eval_runtime": 39.2621, | |
| "eval_samples_per_second": 76.409, | |
| "eval_steps_per_second": 2.394, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_loss": 0.5951861143112183, | |
| "eval_runtime": 39.2622, | |
| "eval_samples_per_second": 76.409, | |
| "eval_steps_per_second": 2.394, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 8.160535117056857e-05, | |
| "loss": 0.5703, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_loss": 0.5963322520256042, | |
| "eval_runtime": 39.2656, | |
| "eval_samples_per_second": 76.403, | |
| "eval_steps_per_second": 2.394, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.5958115458488464, | |
| "eval_runtime": 39.2804, | |
| "eval_samples_per_second": 76.374, | |
| "eval_steps_per_second": 2.393, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_loss": 0.5968443155288696, | |
| "eval_runtime": 39.2618, | |
| "eval_samples_per_second": 76.41, | |
| "eval_steps_per_second": 2.394, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 7.892976588628763e-05, | |
| "loss": 0.5551, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_loss": 0.5958288311958313, | |
| "eval_runtime": 39.2648, | |
| "eval_samples_per_second": 76.404, | |
| "eval_steps_per_second": 2.394, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_loss": 0.5968209505081177, | |
| "eval_runtime": 39.2563, | |
| "eval_samples_per_second": 76.421, | |
| "eval_steps_per_second": 2.395, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "eval_loss": 0.5957658886909485, | |
| "eval_runtime": 39.2499, | |
| "eval_samples_per_second": 76.433, | |
| "eval_steps_per_second": 2.395, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 7.62541806020067e-05, | |
| "loss": 0.5636, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "eval_loss": 0.5955784916877747, | |
| "eval_runtime": 39.279, | |
| "eval_samples_per_second": 76.377, | |
| "eval_steps_per_second": 2.393, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "eval_loss": 0.5963084101676941, | |
| "eval_runtime": 39.2656, | |
| "eval_samples_per_second": 76.403, | |
| "eval_steps_per_second": 2.394, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_loss": 0.595792829990387, | |
| "eval_runtime": 39.2577, | |
| "eval_samples_per_second": 76.418, | |
| "eval_steps_per_second": 2.394, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 7.357859531772575e-05, | |
| "loss": 0.5676, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "eval_loss": 0.5953949093818665, | |
| "eval_runtime": 39.2554, | |
| "eval_samples_per_second": 76.423, | |
| "eval_steps_per_second": 2.395, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "eval_loss": 0.595146894454956, | |
| "eval_runtime": 39.2386, | |
| "eval_samples_per_second": 76.455, | |
| "eval_steps_per_second": 2.396, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 7.090301003344481e-05, | |
| "loss": 0.5551, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 0.5957517027854919, | |
| "eval_runtime": 39.197, | |
| "eval_samples_per_second": 76.536, | |
| "eval_steps_per_second": 2.398, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_loss": 0.596603512763977, | |
| "eval_runtime": 39.2315, | |
| "eval_samples_per_second": 76.469, | |
| "eval_steps_per_second": 2.396, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 0.5952173471450806, | |
| "eval_runtime": 39.2393, | |
| "eval_samples_per_second": 76.454, | |
| "eval_steps_per_second": 2.396, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 6.822742474916388e-05, | |
| "loss": 0.5539, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_loss": 0.5954132676124573, | |
| "eval_runtime": 39.2213, | |
| "eval_samples_per_second": 76.489, | |
| "eval_steps_per_second": 2.397, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "eval_loss": 0.5956953167915344, | |
| "eval_runtime": 39.2503, | |
| "eval_samples_per_second": 76.432, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_loss": 0.5959665775299072, | |
| "eval_runtime": 39.2657, | |
| "eval_samples_per_second": 76.403, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 6.555183946488295e-05, | |
| "loss": 0.5607, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_loss": 0.5952425003051758, | |
| "eval_runtime": 39.2705, | |
| "eval_samples_per_second": 76.393, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "eval_loss": 0.5953785181045532, | |
| "eval_runtime": 39.2403, | |
| "eval_samples_per_second": 76.452, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "eval_loss": 0.5939880609512329, | |
| "eval_runtime": 39.2586, | |
| "eval_samples_per_second": 76.416, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 6.287625418060201e-05, | |
| "loss": 0.5535, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_loss": 0.5965318083763123, | |
| "eval_runtime": 39.2698, | |
| "eval_samples_per_second": 76.395, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "eval_loss": 0.5945996642112732, | |
| "eval_runtime": 39.2883, | |
| "eval_samples_per_second": 76.359, | |
| "eval_steps_per_second": 2.393, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 0.5955180525779724, | |
| "eval_runtime": 39.2482, | |
| "eval_samples_per_second": 76.437, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 6.0200668896321076e-05, | |
| "loss": 0.5488, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_loss": 0.5957381725311279, | |
| "eval_runtime": 39.2638, | |
| "eval_samples_per_second": 76.406, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 0.595982551574707, | |
| "eval_runtime": 39.2492, | |
| "eval_samples_per_second": 76.435, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 0.5966017842292786, | |
| "eval_runtime": 39.2599, | |
| "eval_samples_per_second": 76.414, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 5.752508361204013e-05, | |
| "loss": 0.5397, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "eval_loss": 0.5957372784614563, | |
| "eval_runtime": 39.2429, | |
| "eval_samples_per_second": 76.447, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_loss": 0.5966220498085022, | |
| "eval_runtime": 39.2131, | |
| "eval_samples_per_second": 76.505, | |
| "eval_steps_per_second": 2.397, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "eval_loss": 0.5961087346076965, | |
| "eval_runtime": 39.2548, | |
| "eval_samples_per_second": 76.424, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 5.4849498327759194e-05, | |
| "loss": 0.5478, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "eval_loss": 0.5953994393348694, | |
| "eval_runtime": 39.2497, | |
| "eval_samples_per_second": 76.434, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 0.5952059626579285, | |
| "eval_runtime": 39.2593, | |
| "eval_samples_per_second": 76.415, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 5.217391304347826e-05, | |
| "loss": 0.5443, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_loss": 0.5956901907920837, | |
| "eval_runtime": 39.2077, | |
| "eval_samples_per_second": 76.516, | |
| "eval_steps_per_second": 2.397, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "eval_loss": 0.595130980014801, | |
| "eval_runtime": 39.2681, | |
| "eval_samples_per_second": 76.398, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_loss": 0.5952557921409607, | |
| "eval_runtime": 39.2635, | |
| "eval_samples_per_second": 76.407, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.9498327759197325e-05, | |
| "loss": 0.5482, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "eval_loss": 0.5957027077674866, | |
| "eval_runtime": 39.2636, | |
| "eval_samples_per_second": 76.407, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_loss": 0.5959120988845825, | |
| "eval_runtime": 39.2726, | |
| "eval_samples_per_second": 76.389, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "eval_loss": 0.5966920852661133, | |
| "eval_runtime": 39.2671, | |
| "eval_samples_per_second": 76.4, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 4.6822742474916394e-05, | |
| "loss": 0.5398, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_loss": 0.5955999493598938, | |
| "eval_runtime": 39.2344, | |
| "eval_samples_per_second": 76.464, | |
| "eval_steps_per_second": 2.396, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_loss": 0.5959904193878174, | |
| "eval_runtime": 39.2449, | |
| "eval_samples_per_second": 76.443, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "eval_loss": 0.595309853553772, | |
| "eval_runtime": 39.2603, | |
| "eval_samples_per_second": 76.413, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 4.414715719063545e-05, | |
| "loss": 0.5405, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": 0.5953694581985474, | |
| "eval_runtime": 39.25, | |
| "eval_samples_per_second": 76.433, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "eval_loss": 0.5948453545570374, | |
| "eval_runtime": 39.2551, | |
| "eval_samples_per_second": 76.423, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "eval_loss": 0.596403956413269, | |
| "eval_runtime": 39.2502, | |
| "eval_samples_per_second": 76.433, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 4.147157190635452e-05, | |
| "loss": 0.5454, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_loss": 0.594862699508667, | |
| "eval_runtime": 39.2569, | |
| "eval_samples_per_second": 76.42, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_loss": 0.5970881581306458, | |
| "eval_runtime": 39.2602, | |
| "eval_samples_per_second": 76.413, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_loss": 0.595177173614502, | |
| "eval_runtime": 39.2663, | |
| "eval_samples_per_second": 76.401, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 3.879598662207358e-05, | |
| "loss": 0.5407, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 0.5961460471153259, | |
| "eval_runtime": 39.2651, | |
| "eval_samples_per_second": 76.404, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "eval_loss": 0.5952489972114563, | |
| "eval_runtime": 39.2417, | |
| "eval_samples_per_second": 76.449, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "eval_loss": 0.5965322852134705, | |
| "eval_runtime": 39.244, | |
| "eval_samples_per_second": 76.445, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 3.612040133779264e-05, | |
| "loss": 0.5397, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_loss": 0.5953331589698792, | |
| "eval_runtime": 39.242, | |
| "eval_samples_per_second": 76.449, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "eval_loss": 0.5962971448898315, | |
| "eval_runtime": 39.2251, | |
| "eval_samples_per_second": 76.482, | |
| "eval_steps_per_second": 2.396, | |
| "step": 1253 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 3.3444816053511705e-05, | |
| "loss": 0.5456, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "eval_loss": 0.5961341261863708, | |
| "eval_runtime": 39.2121, | |
| "eval_samples_per_second": 76.507, | |
| "eval_steps_per_second": 2.397, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_loss": 0.595777153968811, | |
| "eval_runtime": 39.2544, | |
| "eval_samples_per_second": 76.425, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "eval_loss": 0.5961927771568298, | |
| "eval_runtime": 39.2566, | |
| "eval_samples_per_second": 76.42, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.5361, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_loss": 0.5967215895652771, | |
| "eval_runtime": 39.251, | |
| "eval_samples_per_second": 76.431, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "eval_loss": 0.5971426367759705, | |
| "eval_runtime": 39.1956, | |
| "eval_samples_per_second": 76.539, | |
| "eval_steps_per_second": 2.398, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "eval_loss": 0.5957850217819214, | |
| "eval_runtime": 39.1348, | |
| "eval_samples_per_second": 76.658, | |
| "eval_steps_per_second": 2.402, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 2.8093645484949833e-05, | |
| "loss": 0.5299, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 0.5976316928863525, | |
| "eval_runtime": 39.248, | |
| "eval_samples_per_second": 76.437, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "eval_loss": 0.5961042642593384, | |
| "eval_runtime": 39.2812, | |
| "eval_samples_per_second": 76.372, | |
| "eval_steps_per_second": 2.393, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "eval_loss": 0.5960709452629089, | |
| "eval_runtime": 39.1595, | |
| "eval_samples_per_second": 76.61, | |
| "eval_steps_per_second": 2.4, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 2.54180602006689e-05, | |
| "loss": 0.5352, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "eval_loss": 0.5965536236763, | |
| "eval_runtime": 39.2514, | |
| "eval_samples_per_second": 76.43, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "eval_loss": 0.5955998301506042, | |
| "eval_runtime": 39.2608, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_loss": 0.5966908931732178, | |
| "eval_runtime": 39.2659, | |
| "eval_samples_per_second": 76.402, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1337 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 2.274247491638796e-05, | |
| "loss": 0.5287, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "eval_loss": 0.5965719223022461, | |
| "eval_runtime": 39.2743, | |
| "eval_samples_per_second": 76.386, | |
| "eval_steps_per_second": 2.393, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "eval_loss": 0.5965744853019714, | |
| "eval_runtime": 39.2692, | |
| "eval_samples_per_second": 76.396, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1351 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 0.5964776277542114, | |
| "eval_runtime": 39.2476, | |
| "eval_samples_per_second": 76.438, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 2.0066889632107023e-05, | |
| "loss": 0.5349, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_loss": 0.5952075719833374, | |
| "eval_runtime": 39.2647, | |
| "eval_samples_per_second": 76.404, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "eval_loss": 0.5961645841598511, | |
| "eval_runtime": 39.268, | |
| "eval_samples_per_second": 76.398, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 0.5963994264602661, | |
| "eval_runtime": 39.2348, | |
| "eval_samples_per_second": 76.463, | |
| "eval_steps_per_second": 2.396, | |
| "step": 1379 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 1.739130434782609e-05, | |
| "loss": 0.5325, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_loss": 0.5961940884590149, | |
| "eval_runtime": 39.2561, | |
| "eval_samples_per_second": 76.421, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "eval_loss": 0.5965219140052795, | |
| "eval_runtime": 39.211, | |
| "eval_samples_per_second": 76.509, | |
| "eval_steps_per_second": 2.397, | |
| "step": 1393 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 1.4715719063545153e-05, | |
| "loss": 0.5337, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "eval_loss": 0.5960851311683655, | |
| "eval_runtime": 39.1812, | |
| "eval_samples_per_second": 76.567, | |
| "eval_steps_per_second": 2.399, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "eval_loss": 0.5964084267616272, | |
| "eval_runtime": 39.2326, | |
| "eval_samples_per_second": 76.467, | |
| "eval_steps_per_second": 2.396, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_loss": 0.596020519733429, | |
| "eval_runtime": 39.2491, | |
| "eval_samples_per_second": 76.435, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 1.2040133779264215e-05, | |
| "loss": 0.5304, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_loss": 0.5962061285972595, | |
| "eval_runtime": 39.2549, | |
| "eval_samples_per_second": 76.424, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1421 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "eval_loss": 0.5967465043067932, | |
| "eval_runtime": 39.2538, | |
| "eval_samples_per_second": 76.426, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_loss": 0.5967243909835815, | |
| "eval_runtime": 39.2606, | |
| "eval_samples_per_second": 76.412, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 9.364548494983277e-06, | |
| "loss": 0.5326, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "eval_loss": 0.5967350602149963, | |
| "eval_runtime": 39.2525, | |
| "eval_samples_per_second": 76.428, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "eval_loss": 0.5968228578567505, | |
| "eval_runtime": 39.236, | |
| "eval_samples_per_second": 76.46, | |
| "eval_steps_per_second": 2.396, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "eval_loss": 0.5971869230270386, | |
| "eval_runtime": 39.2598, | |
| "eval_samples_per_second": 76.414, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 6.688963210702341e-06, | |
| "loss": 0.527, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "eval_loss": 0.5972290635108948, | |
| "eval_runtime": 39.2414, | |
| "eval_samples_per_second": 76.45, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1463 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 0.5970906019210815, | |
| "eval_runtime": 39.2764, | |
| "eval_samples_per_second": 76.382, | |
| "eval_steps_per_second": 2.393, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "eval_loss": 0.5970170497894287, | |
| "eval_runtime": 39.2685, | |
| "eval_samples_per_second": 76.397, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1477 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 4.013377926421405e-06, | |
| "loss": 0.5276, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_loss": 0.5967093110084534, | |
| "eval_runtime": 39.2546, | |
| "eval_samples_per_second": 76.424, | |
| "eval_steps_per_second": 2.395, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_loss": 0.5967251658439636, | |
| "eval_runtime": 39.276, | |
| "eval_samples_per_second": 76.382, | |
| "eval_steps_per_second": 2.393, | |
| "step": 1491 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "eval_loss": 0.5968044996261597, | |
| "eval_runtime": 39.2838, | |
| "eval_samples_per_second": 76.367, | |
| "eval_steps_per_second": 2.393, | |
| "step": 1498 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 1.3377926421404683e-06, | |
| "loss": 0.5222, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "eval_loss": 0.5967151522636414, | |
| "eval_runtime": 39.2673, | |
| "eval_samples_per_second": 76.399, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1505 | |
| } | |
| ], | |
| "max_steps": 1510, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.3117762030029242e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |