| { | |
| "best_metric": 23.7361, | |
| "best_model_checkpoint": "drive/MyDrive/AraT5_FT_title_generation/checkpoint-64000", | |
| "epoch": 6.963494408102975, | |
| "global_step": 66000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 35.638, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 18.823, | |
| "eval_loss": 8.983467102050781, | |
| "eval_runtime": 261.594, | |
| "eval_samples_per_second": 3.823, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 8.3857, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_bleu": 0.198, | |
| "eval_gen_len": 12.74, | |
| "eval_loss": 7.130731105804443, | |
| "eval_runtime": 245.9993, | |
| "eval_samples_per_second": 4.065, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9885, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_bleu": 0.8955, | |
| "eval_gen_len": 14.538, | |
| "eval_loss": 5.843496799468994, | |
| "eval_runtime": 253.3806, | |
| "eval_samples_per_second": 3.947, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.97567099398587e-05, | |
| "loss": 5.9845, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_bleu": 2.1258, | |
| "eval_gen_len": 12.856, | |
| "eval_loss": 4.96659517288208, | |
| "eval_runtime": 239.9357, | |
| "eval_samples_per_second": 4.168, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.95134198797174e-05, | |
| "loss": 5.3511, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_bleu": 4.529, | |
| "eval_gen_len": 13.551, | |
| "eval_loss": 4.428027153015137, | |
| "eval_runtime": 244.6554, | |
| "eval_samples_per_second": 4.087, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.92701298195761e-05, | |
| "loss": 4.8601, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_bleu": 7.2219, | |
| "eval_gen_len": 12.194, | |
| "eval_loss": 4.005715370178223, | |
| "eval_runtime": 190.607, | |
| "eval_samples_per_second": 5.246, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.902683975943479e-05, | |
| "loss": 4.4955, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_bleu": 9.4889, | |
| "eval_gen_len": 12.137, | |
| "eval_loss": 3.741957664489746, | |
| "eval_runtime": 185.7078, | |
| "eval_samples_per_second": 5.385, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.878354969929349e-05, | |
| "loss": 4.2481, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_bleu": 11.3848, | |
| "eval_gen_len": 11.773, | |
| "eval_loss": 3.5194664001464844, | |
| "eval_runtime": 180.2345, | |
| "eval_samples_per_second": 5.548, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.8540259639152185e-05, | |
| "loss": 4.0054, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_bleu": 13.8757, | |
| "eval_gen_len": 11.671, | |
| "eval_loss": 3.378380298614502, | |
| "eval_runtime": 179.378, | |
| "eval_samples_per_second": 5.575, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.829696957901088e-05, | |
| "loss": 3.8032, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_bleu": 15.1716, | |
| "eval_gen_len": 11.402, | |
| "eval_loss": 3.2721943855285645, | |
| "eval_runtime": 176.9812, | |
| "eval_samples_per_second": 5.65, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.805367951886958e-05, | |
| "loss": 3.6668, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_bleu": 15.1204, | |
| "eval_gen_len": 11.792, | |
| "eval_loss": 3.1800124645233154, | |
| "eval_runtime": 179.9992, | |
| "eval_samples_per_second": 5.556, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.781038945872828e-05, | |
| "loss": 3.5526, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_bleu": 15.4619, | |
| "eval_gen_len": 12.077, | |
| "eval_loss": 3.103393077850342, | |
| "eval_runtime": 183.5811, | |
| "eval_samples_per_second": 5.447, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.756709939858697e-05, | |
| "loss": 3.4665, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_bleu": 16.7979, | |
| "eval_gen_len": 11.766, | |
| "eval_loss": 3.0600805282592773, | |
| "eval_runtime": 183.4473, | |
| "eval_samples_per_second": 5.451, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.732380933844567e-05, | |
| "loss": 3.3754, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_bleu": 17.5953, | |
| "eval_gen_len": 11.554, | |
| "eval_loss": 2.9892418384552, | |
| "eval_runtime": 183.2148, | |
| "eval_samples_per_second": 5.458, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.708051927830437e-05, | |
| "loss": 3.3243, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_bleu": 18.2111, | |
| "eval_gen_len": 11.962, | |
| "eval_loss": 2.9837777614593506, | |
| "eval_runtime": 180.3526, | |
| "eval_samples_per_second": 5.545, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.6837229218163065e-05, | |
| "loss": 3.2794, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_bleu": 18.227, | |
| "eval_gen_len": 11.463, | |
| "eval_loss": 2.898597240447998, | |
| "eval_runtime": 178.1798, | |
| "eval_samples_per_second": 5.612, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.659393915802176e-05, | |
| "loss": 3.203, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_bleu": 19.2324, | |
| "eval_gen_len": 11.34, | |
| "eval_loss": 2.8416123390197754, | |
| "eval_runtime": 176.1105, | |
| "eval_samples_per_second": 5.678, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.635064909788046e-05, | |
| "loss": 3.1658, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_bleu": 19.0493, | |
| "eval_gen_len": 11.414, | |
| "eval_loss": 2.8081586360931396, | |
| "eval_runtime": 178.4234, | |
| "eval_samples_per_second": 5.605, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.610735903773916e-05, | |
| "loss": 3.0979, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 19.4019, | |
| "eval_gen_len": 11.815, | |
| "eval_loss": 2.801037311553955, | |
| "eval_runtime": 184.5402, | |
| "eval_samples_per_second": 5.419, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 4.586406897759785e-05, | |
| "loss": 2.963, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_bleu": 20.4101, | |
| "eval_gen_len": 10.937, | |
| "eval_loss": 2.7728490829467773, | |
| "eval_runtime": 216.7393, | |
| "eval_samples_per_second": 4.614, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.5620778917456556e-05, | |
| "loss": 2.9022, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_bleu": 20.2568, | |
| "eval_gen_len": 11.498, | |
| "eval_loss": 2.748673439025879, | |
| "eval_runtime": 222.8526, | |
| "eval_samples_per_second": 4.487, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.537748885731525e-05, | |
| "loss": 2.9113, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_bleu": 20.7867, | |
| "eval_gen_len": 11.143, | |
| "eval_loss": 2.714132308959961, | |
| "eval_runtime": 237.849, | |
| "eval_samples_per_second": 4.204, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 4.5134198797173945e-05, | |
| "loss": 2.9026, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_bleu": 20.6776, | |
| "eval_gen_len": 11.403, | |
| "eval_loss": 2.681997060775757, | |
| "eval_runtime": 245.0406, | |
| "eval_samples_per_second": 4.081, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.4890908737032644e-05, | |
| "loss": 2.8522, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_bleu": 21.2223, | |
| "eval_gen_len": 11.345, | |
| "eval_loss": 2.6821537017822266, | |
| "eval_runtime": 234.0719, | |
| "eval_samples_per_second": 4.272, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 4.464761867689134e-05, | |
| "loss": 2.8177, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_bleu": 21.1983, | |
| "eval_gen_len": 11.272, | |
| "eval_loss": 2.6571996212005615, | |
| "eval_runtime": 244.6544, | |
| "eval_samples_per_second": 4.087, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.440432861675003e-05, | |
| "loss": 2.8178, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_bleu": 21.0805, | |
| "eval_gen_len": 11.569, | |
| "eval_loss": 2.647949695587158, | |
| "eval_runtime": 246.8942, | |
| "eval_samples_per_second": 4.05, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 4.416103855660874e-05, | |
| "loss": 2.7526, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_bleu": 20.354, | |
| "eval_gen_len": 11.81, | |
| "eval_loss": 2.6451191902160645, | |
| "eval_runtime": 254.1274, | |
| "eval_samples_per_second": 3.935, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 4.391774849646743e-05, | |
| "loss": 2.783, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_bleu": 21.1215, | |
| "eval_gen_len": 11.437, | |
| "eval_loss": 2.60164213180542, | |
| "eval_runtime": 229.9337, | |
| "eval_samples_per_second": 4.349, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.367445843632613e-05, | |
| "loss": 2.6665, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_bleu": 20.9631, | |
| "eval_gen_len": 11.499, | |
| "eval_loss": 2.6079459190368652, | |
| "eval_runtime": 230.5689, | |
| "eval_samples_per_second": 4.337, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.343116837618482e-05, | |
| "loss": 2.6233, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_bleu": 21.332, | |
| "eval_gen_len": 11.468, | |
| "eval_loss": 2.613509178161621, | |
| "eval_runtime": 201.795, | |
| "eval_samples_per_second": 4.956, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 4.3187878316043524e-05, | |
| "loss": 2.5983, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_bleu": 21.0944, | |
| "eval_gen_len": 11.603, | |
| "eval_loss": 2.5642783641815186, | |
| "eval_runtime": 201.0993, | |
| "eval_samples_per_second": 4.973, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 4.2944588255902215e-05, | |
| "loss": 2.5912, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_bleu": 21.6143, | |
| "eval_gen_len": 11.104, | |
| "eval_loss": 2.5584685802459717, | |
| "eval_runtime": 198.7529, | |
| "eval_samples_per_second": 5.031, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 4.2701298195760914e-05, | |
| "loss": 2.5681, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_bleu": 21.8716, | |
| "eval_gen_len": 10.987, | |
| "eval_loss": 2.541090726852417, | |
| "eval_runtime": 208.1375, | |
| "eval_samples_per_second": 4.805, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 4.245800813561961e-05, | |
| "loss": 2.5657, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "eval_bleu": 21.7373, | |
| "eval_gen_len": 11.364, | |
| "eval_loss": 2.51957368850708, | |
| "eval_runtime": 220.5477, | |
| "eval_samples_per_second": 4.534, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 4.221471807547831e-05, | |
| "loss": 2.5639, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_bleu": 21.9015, | |
| "eval_gen_len": 11.395, | |
| "eval_loss": 2.516514539718628, | |
| "eval_runtime": 224.7434, | |
| "eval_samples_per_second": 4.45, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 4.197142801533701e-05, | |
| "loss": 2.5257, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_bleu": 21.7659, | |
| "eval_gen_len": 11.47, | |
| "eval_loss": 2.5282981395721436, | |
| "eval_runtime": 248.968, | |
| "eval_samples_per_second": 4.017, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 4.1728137955195706e-05, | |
| "loss": 2.5278, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "eval_bleu": 22.3318, | |
| "eval_gen_len": 11.31, | |
| "eval_loss": 2.5119266510009766, | |
| "eval_runtime": 201.5867, | |
| "eval_samples_per_second": 4.961, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.1484847895054404e-05, | |
| "loss": 2.5164, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_bleu": 21.6403, | |
| "eval_gen_len": 11.544, | |
| "eval_loss": 2.5127675533294678, | |
| "eval_runtime": 222.4942, | |
| "eval_samples_per_second": 4.494, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.1241557834913096e-05, | |
| "loss": 2.3804, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_bleu": 21.88, | |
| "eval_gen_len": 11.368, | |
| "eval_loss": 2.5173442363739014, | |
| "eval_runtime": 231.6469, | |
| "eval_samples_per_second": 4.317, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 4.09982677747718e-05, | |
| "loss": 2.4065, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "eval_bleu": 21.6251, | |
| "eval_gen_len": 11.596, | |
| "eval_loss": 2.481987714767456, | |
| "eval_runtime": 224.3387, | |
| "eval_samples_per_second": 4.458, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 4.075497771463049e-05, | |
| "loss": 2.3876, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_bleu": 22.5464, | |
| "eval_gen_len": 11.385, | |
| "eval_loss": 2.49714994430542, | |
| "eval_runtime": 204.1448, | |
| "eval_samples_per_second": 4.898, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 4.051168765448919e-05, | |
| "loss": 2.3339, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_bleu": 22.9928, | |
| "eval_gen_len": 11.032, | |
| "eval_loss": 2.4970240592956543, | |
| "eval_runtime": 207.9008, | |
| "eval_samples_per_second": 4.81, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 4.026839759434789e-05, | |
| "loss": 2.3397, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_bleu": 22.1443, | |
| "eval_gen_len": 11.523, | |
| "eval_loss": 2.476402759552002, | |
| "eval_runtime": 206.0363, | |
| "eval_samples_per_second": 4.854, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.0025107534206587e-05, | |
| "loss": 2.3629, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_bleu": 22.8804, | |
| "eval_gen_len": 11.271, | |
| "eval_loss": 2.455251455307007, | |
| "eval_runtime": 206.5896, | |
| "eval_samples_per_second": 4.841, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 3.978181747406528e-05, | |
| "loss": 2.3749, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_bleu": 21.9768, | |
| "eval_gen_len": 11.698, | |
| "eval_loss": 2.4702677726745605, | |
| "eval_runtime": 201.4429, | |
| "eval_samples_per_second": 4.964, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 3.9538527413923976e-05, | |
| "loss": 2.3341, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "eval_bleu": 23.3467, | |
| "eval_gen_len": 11.481, | |
| "eval_loss": 2.4574341773986816, | |
| "eval_runtime": 219.555, | |
| "eval_samples_per_second": 4.555, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 3.9295237353782674e-05, | |
| "loss": 2.3405, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_bleu": 22.2318, | |
| "eval_gen_len": 11.215, | |
| "eval_loss": 2.416428327560425, | |
| "eval_runtime": 219.9781, | |
| "eval_samples_per_second": 4.546, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 3.905194729364137e-05, | |
| "loss": 2.2188, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_bleu": 22.4174, | |
| "eval_gen_len": 11.296, | |
| "eval_loss": 2.478271007537842, | |
| "eval_runtime": 207.2586, | |
| "eval_samples_per_second": 4.825, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 3.880865723350007e-05, | |
| "loss": 2.1582, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "eval_bleu": 22.9358, | |
| "eval_gen_len": 11.209, | |
| "eval_loss": 2.478005886077881, | |
| "eval_runtime": 218.3957, | |
| "eval_samples_per_second": 4.579, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 3.856536717335877e-05, | |
| "loss": 2.2462, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_bleu": 22.4676, | |
| "eval_gen_len": 11.412, | |
| "eval_loss": 2.4692862033843994, | |
| "eval_runtime": 129.2452, | |
| "eval_samples_per_second": 7.737, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 3.832207711321747e-05, | |
| "loss": 2.2293, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "eval_bleu": 22.8528, | |
| "eval_gen_len": 11.306, | |
| "eval_loss": 2.4192593097686768, | |
| "eval_runtime": 131.8082, | |
| "eval_samples_per_second": 7.587, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 3.807878705307616e-05, | |
| "loss": 2.2323, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_bleu": 23.4254, | |
| "eval_gen_len": 11.5, | |
| "eval_loss": 2.436190605163574, | |
| "eval_runtime": 129.6391, | |
| "eval_samples_per_second": 7.714, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 3.783549699293486e-05, | |
| "loss": 2.2434, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_bleu": 23.0953, | |
| "eval_gen_len": 11.579, | |
| "eval_loss": 2.434554100036621, | |
| "eval_runtime": 129.6268, | |
| "eval_samples_per_second": 7.714, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 3.7592206932793555e-05, | |
| "loss": 2.2106, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "eval_bleu": 22.5385, | |
| "eval_gen_len": 11.793, | |
| "eval_loss": 2.4267661571502686, | |
| "eval_runtime": 133.564, | |
| "eval_samples_per_second": 7.487, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 3.734891687265225e-05, | |
| "loss": 2.2152, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_bleu": 22.6911, | |
| "eval_gen_len": 11.479, | |
| "eval_loss": 2.4134082794189453, | |
| "eval_runtime": 133.7203, | |
| "eval_samples_per_second": 7.478, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 3.710562681251095e-05, | |
| "loss": 2.2198, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_bleu": 22.5865, | |
| "eval_gen_len": 11.59, | |
| "eval_loss": 2.433336019515991, | |
| "eval_runtime": 173.431, | |
| "eval_samples_per_second": 5.766, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.686233675236965e-05, | |
| "loss": 2.2326, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_bleu": 23.0494, | |
| "eval_gen_len": 11.487, | |
| "eval_loss": 2.4282305240631104, | |
| "eval_runtime": 145.1447, | |
| "eval_samples_per_second": 6.89, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 3.661904669222834e-05, | |
| "loss": 2.1317, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "eval_bleu": 23.1905, | |
| "eval_gen_len": 11.478, | |
| "eval_loss": 2.4288105964660645, | |
| "eval_runtime": 136.8723, | |
| "eval_samples_per_second": 7.306, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 3.6375756632087045e-05, | |
| "loss": 2.1239, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_bleu": 23.0939, | |
| "eval_gen_len": 11.375, | |
| "eval_loss": 2.4191648960113525, | |
| "eval_runtime": 136.6994, | |
| "eval_samples_per_second": 7.315, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 3.613246657194574e-05, | |
| "loss": 2.1326, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "eval_bleu": 23.3522, | |
| "eval_gen_len": 11.23, | |
| "eval_loss": 2.4099223613739014, | |
| "eval_runtime": 144.7238, | |
| "eval_samples_per_second": 6.91, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 3.5889176511804435e-05, | |
| "loss": 2.1159, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "eval_bleu": 22.748, | |
| "eval_gen_len": 11.572, | |
| "eval_loss": 2.419100284576416, | |
| "eval_runtime": 148.7046, | |
| "eval_samples_per_second": 6.725, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 3.564588645166313e-05, | |
| "loss": 2.1308, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_bleu": 23.2816, | |
| "eval_gen_len": 11.449, | |
| "eval_loss": 2.397722005844116, | |
| "eval_runtime": 132.2002, | |
| "eval_samples_per_second": 7.564, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 3.540259639152183e-05, | |
| "loss": 2.1094, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "eval_bleu": 23.3833, | |
| "eval_gen_len": 11.243, | |
| "eval_loss": 2.4132864475250244, | |
| "eval_runtime": 145.191, | |
| "eval_samples_per_second": 6.887, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 3.515930633138052e-05, | |
| "loss": 2.1184, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "eval_bleu": 23.7361, | |
| "eval_gen_len": 11.172, | |
| "eval_loss": 2.3724682331085205, | |
| "eval_runtime": 131.0274, | |
| "eval_samples_per_second": 7.632, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 3.491601627123922e-05, | |
| "loss": 2.1308, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_bleu": 22.8591, | |
| "eval_gen_len": 11.63, | |
| "eval_loss": 2.3898813724517822, | |
| "eval_runtime": 146.2565, | |
| "eval_samples_per_second": 6.837, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 3.467272621109792e-05, | |
| "loss": 2.1292, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_bleu": 22.8675, | |
| "eval_gen_len": 11.667, | |
| "eval_loss": 2.3850231170654297, | |
| "eval_runtime": 130.3031, | |
| "eval_samples_per_second": 7.674, | |
| "step": 66000 | |
| } | |
| ], | |
| "max_steps": 208516, | |
| "num_train_epochs": 22, | |
| "total_flos": 8.109412878134016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |