| { | |
| "best_metric": 2.141591787338257, | |
| "best_model_checkpoint": "experiments/qa2d/google/mt5-large_all/checkpoint-156000", | |
| "epoch": 2.569593147751606, | |
| "global_step": 156000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3e-05, | |
| "loss": 11.6929, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.9975354434553247e-05, | |
| "loss": 3.2221, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.6418206691741943, | |
| "eval_runtime": 1565.2313, | |
| "eval_samples_per_second": 25.555, | |
| "eval_steps_per_second": 25.555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.9950708869106497e-05, | |
| "loss": 2.8153, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9926063303659743e-05, | |
| "loss": 2.6697, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.4854109287261963, | |
| "eval_runtime": 1558.2706, | |
| "eval_samples_per_second": 25.669, | |
| "eval_steps_per_second": 25.669, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.990141773821299e-05, | |
| "loss": 2.6416, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.987677217276624e-05, | |
| "loss": 2.6305, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 2.4116737842559814, | |
| "eval_runtime": 1557.0077, | |
| "eval_samples_per_second": 25.69, | |
| "eval_steps_per_second": 25.69, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.9852126607319485e-05, | |
| "loss": 2.5755, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.9827481041872735e-05, | |
| "loss": 2.5568, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.395322561264038, | |
| "eval_runtime": 1559.3248, | |
| "eval_samples_per_second": 25.652, | |
| "eval_steps_per_second": 25.652, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.980283547642598e-05, | |
| "loss": 2.5352, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.977818991097923e-05, | |
| "loss": 2.501, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.3722634315490723, | |
| "eval_runtime": 1560.8236, | |
| "eval_samples_per_second": 25.627, | |
| "eval_steps_per_second": 25.627, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.9753544345532477e-05, | |
| "loss": 2.5226, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.9728898780085723e-05, | |
| "loss": 2.5234, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 2.3681018352508545, | |
| "eval_runtime": 1556.6002, | |
| "eval_samples_per_second": 25.697, | |
| "eval_steps_per_second": 25.697, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.9704253214638973e-05, | |
| "loss": 2.4771, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.967960764919222e-05, | |
| "loss": 2.461, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 2.3373661041259766, | |
| "eval_runtime": 1557.5651, | |
| "eval_samples_per_second": 25.681, | |
| "eval_steps_per_second": 25.681, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.9654962083745466e-05, | |
| "loss": 2.4578, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.9630316518298715e-05, | |
| "loss": 2.4421, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.3323025703430176, | |
| "eval_runtime": 1562.2934, | |
| "eval_samples_per_second": 25.603, | |
| "eval_steps_per_second": 25.603, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.960567095285196e-05, | |
| "loss": 2.4323, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.9581025387405208e-05, | |
| "loss": 2.4347, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.3352105617523193, | |
| "eval_runtime": 1554.7815, | |
| "eval_samples_per_second": 25.727, | |
| "eval_steps_per_second": 25.727, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.9556379821958458e-05, | |
| "loss": 2.4114, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.9531734256511704e-05, | |
| "loss": 2.4128, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.310478448867798, | |
| "eval_runtime": 1531.4425, | |
| "eval_samples_per_second": 26.119, | |
| "eval_steps_per_second": 26.119, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.9507088691064954e-05, | |
| "loss": 2.4011, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.9482443125618203e-05, | |
| "loss": 2.4146, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 2.299036979675293, | |
| "eval_runtime": 1528.7138, | |
| "eval_samples_per_second": 26.166, | |
| "eval_steps_per_second": 26.166, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.945779756017145e-05, | |
| "loss": 2.3943, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.9433151994724696e-05, | |
| "loss": 2.4149, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.2903053760528564, | |
| "eval_runtime": 1529.473, | |
| "eval_samples_per_second": 26.153, | |
| "eval_steps_per_second": 26.153, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9408506429277945e-05, | |
| "loss": 2.3832, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.9383860863831192e-05, | |
| "loss": 2.4014, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 2.2913293838500977, | |
| "eval_runtime": 1532.1216, | |
| "eval_samples_per_second": 26.108, | |
| "eval_steps_per_second": 26.108, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.9359215298384438e-05, | |
| "loss": 2.3717, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.9334569732937684e-05, | |
| "loss": 2.4076, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 2.2880167961120605, | |
| "eval_runtime": 1529.4251, | |
| "eval_samples_per_second": 26.154, | |
| "eval_steps_per_second": 26.154, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.9309924167490934e-05, | |
| "loss": 2.3883, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.928527860204418e-05, | |
| "loss": 2.3683, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 2.282928228378296, | |
| "eval_runtime": 1530.4125, | |
| "eval_samples_per_second": 26.137, | |
| "eval_steps_per_second": 26.137, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.9260633036597427e-05, | |
| "loss": 2.3794, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.9235987471150676e-05, | |
| "loss": 2.3711, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 2.2699029445648193, | |
| "eval_runtime": 1529.1971, | |
| "eval_samples_per_second": 26.158, | |
| "eval_steps_per_second": 26.158, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.9211341905703926e-05, | |
| "loss": 2.3701, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.9186696340257172e-05, | |
| "loss": 2.348, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.27140736579895, | |
| "eval_runtime": 1529.6771, | |
| "eval_samples_per_second": 26.149, | |
| "eval_steps_per_second": 26.149, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.9162050774810422e-05, | |
| "loss": 2.3521, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.9137405209363668e-05, | |
| "loss": 2.3649, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 2.2581582069396973, | |
| "eval_runtime": 1528.5087, | |
| "eval_samples_per_second": 26.169, | |
| "eval_steps_per_second": 26.169, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.9112759643916914e-05, | |
| "loss": 2.3625, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.9088114078470164e-05, | |
| "loss": 2.3413, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 2.2619144916534424, | |
| "eval_runtime": 1529.952, | |
| "eval_samples_per_second": 26.145, | |
| "eval_steps_per_second": 26.145, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.906346851302341e-05, | |
| "loss": 2.3399, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.9038822947576657e-05, | |
| "loss": 2.3123, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.249448299407959, | |
| "eval_runtime": 1530.0932, | |
| "eval_samples_per_second": 26.142, | |
| "eval_steps_per_second": 26.142, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.9014177382129903e-05, | |
| "loss": 2.343, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.8989531816683153e-05, | |
| "loss": 2.3207, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 2.2527272701263428, | |
| "eval_runtime": 1529.3921, | |
| "eval_samples_per_second": 26.154, | |
| "eval_steps_per_second": 26.154, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.89648862512364e-05, | |
| "loss": 2.3328, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.8940240685789645e-05, | |
| "loss": 2.3277, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.252654552459717, | |
| "eval_runtime": 1529.3372, | |
| "eval_samples_per_second": 26.155, | |
| "eval_steps_per_second": 26.155, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.8915595120342895e-05, | |
| "loss": 2.3279, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.8890949554896145e-05, | |
| "loss": 2.3539, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 2.2401123046875, | |
| "eval_runtime": 1530.6138, | |
| "eval_samples_per_second": 26.133, | |
| "eval_steps_per_second": 26.133, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.886630398944939e-05, | |
| "loss": 2.3201, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.884165842400264e-05, | |
| "loss": 2.3245, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.2426249980926514, | |
| "eval_runtime": 1530.4589, | |
| "eval_samples_per_second": 26.136, | |
| "eval_steps_per_second": 26.136, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.8817012858555887e-05, | |
| "loss": 2.3039, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.8792367293109133e-05, | |
| "loss": 2.3077, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 2.243065118789673, | |
| "eval_runtime": 1532.734, | |
| "eval_samples_per_second": 26.097, | |
| "eval_steps_per_second": 26.097, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.8767721727662383e-05, | |
| "loss": 2.313, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.874307616221563e-05, | |
| "loss": 2.3275, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 2.23547101020813, | |
| "eval_runtime": 1532.1284, | |
| "eval_samples_per_second": 26.107, | |
| "eval_steps_per_second": 26.107, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8718430596768875e-05, | |
| "loss": 2.3099, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.869378503132212e-05, | |
| "loss": 2.293, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.2356772422790527, | |
| "eval_runtime": 1529.3039, | |
| "eval_samples_per_second": 26.156, | |
| "eval_steps_per_second": 26.156, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.866913946587537e-05, | |
| "loss": 2.2986, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.8644493900428618e-05, | |
| "loss": 2.2894, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 2.2366623878479004, | |
| "eval_runtime": 1530.364, | |
| "eval_samples_per_second": 26.138, | |
| "eval_steps_per_second": 26.138, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.8619848334981864e-05, | |
| "loss": 2.3039, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8595202769535114e-05, | |
| "loss": 2.291, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 2.2369134426116943, | |
| "eval_runtime": 1531.5039, | |
| "eval_samples_per_second": 26.118, | |
| "eval_steps_per_second": 26.118, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.8570557204088363e-05, | |
| "loss": 2.2991, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.854591163864161e-05, | |
| "loss": 2.3012, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 2.2239012718200684, | |
| "eval_runtime": 1541.2582, | |
| "eval_samples_per_second": 25.953, | |
| "eval_steps_per_second": 25.953, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.852126607319486e-05, | |
| "loss": 2.2986, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.8496620507748105e-05, | |
| "loss": 2.307, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.22198748588562, | |
| "eval_runtime": 1529.6638, | |
| "eval_samples_per_second": 26.15, | |
| "eval_steps_per_second": 26.15, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.8471974942301352e-05, | |
| "loss": 2.2983, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.84473293768546e-05, | |
| "loss": 2.292, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 2.2306456565856934, | |
| "eval_runtime": 1530.562, | |
| "eval_samples_per_second": 26.134, | |
| "eval_steps_per_second": 26.134, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.8422683811407848e-05, | |
| "loss": 2.3024, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.8398038245961094e-05, | |
| "loss": 2.3136, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 2.2240662574768066, | |
| "eval_runtime": 1528.9582, | |
| "eval_samples_per_second": 26.162, | |
| "eval_steps_per_second": 26.162, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.8373392680514344e-05, | |
| "loss": 2.2743, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.834874711506759e-05, | |
| "loss": 2.2795, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 2.2316462993621826, | |
| "eval_runtime": 1529.0092, | |
| "eval_samples_per_second": 26.161, | |
| "eval_steps_per_second": 26.161, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.8324101549620836e-05, | |
| "loss": 2.284, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.8299455984174086e-05, | |
| "loss": 2.267, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 2.2221341133117676, | |
| "eval_runtime": 1538.4633, | |
| "eval_samples_per_second": 26.0, | |
| "eval_steps_per_second": 26.0, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.8274810418727336e-05, | |
| "loss": 2.2607, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.8250164853280582e-05, | |
| "loss": 2.2925, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 2.2153666019439697, | |
| "eval_runtime": 1535.3695, | |
| "eval_samples_per_second": 26.052, | |
| "eval_steps_per_second": 26.052, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.8225519287833828e-05, | |
| "loss": 2.2807, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.8200873722387078e-05, | |
| "loss": 2.2668, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.2268478870391846, | |
| "eval_runtime": 1531.1735, | |
| "eval_samples_per_second": 26.124, | |
| "eval_steps_per_second": 26.124, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.8176228156940324e-05, | |
| "loss": 2.2737, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.815158259149357e-05, | |
| "loss": 2.2593, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 2.210831642150879, | |
| "eval_runtime": 1534.412, | |
| "eval_samples_per_second": 26.069, | |
| "eval_steps_per_second": 26.069, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.812693702604682e-05, | |
| "loss": 2.263, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8102291460600066e-05, | |
| "loss": 2.2773, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 2.2057864665985107, | |
| "eval_runtime": 1540.629, | |
| "eval_samples_per_second": 25.963, | |
| "eval_steps_per_second": 25.963, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.8077645895153313e-05, | |
| "loss": 2.2744, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.8053000329706562e-05, | |
| "loss": 2.2523, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 2.2129907608032227, | |
| "eval_runtime": 1528.9572, | |
| "eval_samples_per_second": 26.162, | |
| "eval_steps_per_second": 26.162, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.802835476425981e-05, | |
| "loss": 2.2854, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.8003709198813055e-05, | |
| "loss": 2.2641, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 2.211035966873169, | |
| "eval_runtime": 1530.9184, | |
| "eval_samples_per_second": 26.128, | |
| "eval_steps_per_second": 26.128, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.7979063633366305e-05, | |
| "loss": 2.2852, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.7954418067919554e-05, | |
| "loss": 2.2677, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 2.215862989425659, | |
| "eval_runtime": 1532.4939, | |
| "eval_samples_per_second": 26.101, | |
| "eval_steps_per_second": 26.101, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.79297725024728e-05, | |
| "loss": 2.2726, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.7905126937026047e-05, | |
| "loss": 2.2552, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 2.2060205936431885, | |
| "eval_runtime": 1528.9721, | |
| "eval_samples_per_second": 26.161, | |
| "eval_steps_per_second": 26.161, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.7880481371579296e-05, | |
| "loss": 2.2636, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.7855835806132543e-05, | |
| "loss": 2.2523, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 2.2027759552001953, | |
| "eval_runtime": 1654.4814, | |
| "eval_samples_per_second": 24.177, | |
| "eval_steps_per_second": 24.177, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.7831190240685792e-05, | |
| "loss": 2.2571, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.780654467523904e-05, | |
| "loss": 2.2631, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 2.203402042388916, | |
| "eval_runtime": 1646.7085, | |
| "eval_samples_per_second": 24.291, | |
| "eval_steps_per_second": 24.291, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.7781899109792285e-05, | |
| "loss": 2.2625, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.775725354434553e-05, | |
| "loss": 2.2526, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 2.2011003494262695, | |
| "eval_runtime": 1646.5268, | |
| "eval_samples_per_second": 24.294, | |
| "eval_steps_per_second": 24.294, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.773260797889878e-05, | |
| "loss": 2.2292, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.7707962413452027e-05, | |
| "loss": 2.233, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 2.195323944091797, | |
| "eval_runtime": 1654.3578, | |
| "eval_samples_per_second": 24.179, | |
| "eval_steps_per_second": 24.179, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.7683316848005273e-05, | |
| "loss": 2.2354, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.7658671282558523e-05, | |
| "loss": 2.2694, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 2.197169542312622, | |
| "eval_runtime": 1644.6807, | |
| "eval_samples_per_second": 24.321, | |
| "eval_steps_per_second": 24.321, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.7634025717111773e-05, | |
| "loss": 2.2419, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.760938015166502e-05, | |
| "loss": 2.2524, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 2.1981358528137207, | |
| "eval_runtime": 1641.1537, | |
| "eval_samples_per_second": 24.373, | |
| "eval_steps_per_second": 24.373, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.758473458621827e-05, | |
| "loss": 2.2496, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.7560089020771515e-05, | |
| "loss": 2.2361, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 2.1948020458221436, | |
| "eval_runtime": 1641.8374, | |
| "eval_samples_per_second": 24.363, | |
| "eval_steps_per_second": 24.363, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.753544345532476e-05, | |
| "loss": 2.2394, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.751079788987801e-05, | |
| "loss": 2.2415, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 2.201873540878296, | |
| "eval_runtime": 1644.4006, | |
| "eval_samples_per_second": 24.325, | |
| "eval_steps_per_second": 24.325, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.7486152324431257e-05, | |
| "loss": 2.2422, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.7461506758984504e-05, | |
| "loss": 2.2319, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 2.1902756690979004, | |
| "eval_runtime": 1640.1219, | |
| "eval_samples_per_second": 24.388, | |
| "eval_steps_per_second": 24.388, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.743686119353775e-05, | |
| "loss": 2.2421, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.7412215628091e-05, | |
| "loss": 2.2425, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 2.193206787109375, | |
| "eval_runtime": 1645.0368, | |
| "eval_samples_per_second": 24.316, | |
| "eval_steps_per_second": 24.316, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.7387570062644246e-05, | |
| "loss": 2.2464, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.7362924497197492e-05, | |
| "loss": 2.2113, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 2.1928114891052246, | |
| "eval_runtime": 1645.7517, | |
| "eval_samples_per_second": 24.305, | |
| "eval_steps_per_second": 24.305, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.7338278931750745e-05, | |
| "loss": 2.2371, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.731363336630399e-05, | |
| "loss": 2.2384, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 2.1923627853393555, | |
| "eval_runtime": 1645.6809, | |
| "eval_samples_per_second": 24.306, | |
| "eval_steps_per_second": 24.306, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.7288987800857238e-05, | |
| "loss": 2.2285, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.7264342235410487e-05, | |
| "loss": 2.2246, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 2.1856086254119873, | |
| "eval_runtime": 1644.6784, | |
| "eval_samples_per_second": 24.321, | |
| "eval_steps_per_second": 24.321, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.7239696669963734e-05, | |
| "loss": 2.2268, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.721505110451698e-05, | |
| "loss": 2.2098, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 2.1881797313690186, | |
| "eval_runtime": 1649.0436, | |
| "eval_samples_per_second": 24.256, | |
| "eval_steps_per_second": 24.256, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.719040553907023e-05, | |
| "loss": 2.2294, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.7165759973623476e-05, | |
| "loss": 2.2166, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.1920626163482666, | |
| "eval_runtime": 1641.5349, | |
| "eval_samples_per_second": 24.367, | |
| "eval_steps_per_second": 24.367, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.7141114408176722e-05, | |
| "loss": 2.233, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.711646884272997e-05, | |
| "loss": 2.2292, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 2.182201862335205, | |
| "eval_runtime": 1643.6909, | |
| "eval_samples_per_second": 24.335, | |
| "eval_steps_per_second": 24.335, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.7091823277283218e-05, | |
| "loss": 2.2104, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.7067177711836464e-05, | |
| "loss": 2.2322, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 2.186232089996338, | |
| "eval_runtime": 1642.8864, | |
| "eval_samples_per_second": 24.347, | |
| "eval_steps_per_second": 24.347, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.704253214638971e-05, | |
| "loss": 2.2059, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.7017886580942964e-05, | |
| "loss": 2.1856, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.1843557357788086, | |
| "eval_runtime": 1645.6389, | |
| "eval_samples_per_second": 24.307, | |
| "eval_steps_per_second": 24.307, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.699324101549621e-05, | |
| "loss": 2.1659, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.6968595450049456e-05, | |
| "loss": 2.177, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 2.1830549240112305, | |
| "eval_runtime": 1640.3296, | |
| "eval_samples_per_second": 24.385, | |
| "eval_steps_per_second": 24.385, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.6943949884602706e-05, | |
| "loss": 2.1659, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.6919304319155952e-05, | |
| "loss": 2.1708, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 2.1878035068511963, | |
| "eval_runtime": 1647.1232, | |
| "eval_samples_per_second": 24.285, | |
| "eval_steps_per_second": 24.285, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.68946587537092e-05, | |
| "loss": 2.1672, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.6870013188262448e-05, | |
| "loss": 2.162, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 2.184495210647583, | |
| "eval_runtime": 1647.5833, | |
| "eval_samples_per_second": 24.278, | |
| "eval_steps_per_second": 24.278, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.6845367622815695e-05, | |
| "loss": 2.157, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.682072205736894e-05, | |
| "loss": 2.1928, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 2.177741050720215, | |
| "eval_runtime": 1681.8483, | |
| "eval_samples_per_second": 23.783, | |
| "eval_steps_per_second": 23.783, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.6796076491922187e-05, | |
| "loss": 2.1747, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 2.6771430926475437e-05, | |
| "loss": 2.1839, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.1771292686462402, | |
| "eval_runtime": 1698.416, | |
| "eval_samples_per_second": 23.551, | |
| "eval_steps_per_second": 23.551, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.6746785361028683e-05, | |
| "loss": 2.1704, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.6722139795581933e-05, | |
| "loss": 2.1627, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 2.176990509033203, | |
| "eval_runtime": 1663.2499, | |
| "eval_samples_per_second": 24.049, | |
| "eval_steps_per_second": 24.049, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.6697494230135182e-05, | |
| "loss": 2.1672, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 2.667284866468843e-05, | |
| "loss": 2.1613, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 2.178516387939453, | |
| "eval_runtime": 1655.5689, | |
| "eval_samples_per_second": 24.161, | |
| "eval_steps_per_second": 24.161, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.6648203099241675e-05, | |
| "loss": 2.1681, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.6623557533794925e-05, | |
| "loss": 2.1664, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 2.1790318489074707, | |
| "eval_runtime": 1664.8312, | |
| "eval_samples_per_second": 24.026, | |
| "eval_steps_per_second": 24.026, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.659891196834817e-05, | |
| "loss": 2.1627, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.6574266402901417e-05, | |
| "loss": 2.1651, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 2.1793885231018066, | |
| "eval_runtime": 1658.525, | |
| "eval_samples_per_second": 24.118, | |
| "eval_steps_per_second": 24.118, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.6549620837454667e-05, | |
| "loss": 2.1489, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.6524975272007913e-05, | |
| "loss": 2.1548, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 2.1826231479644775, | |
| "eval_runtime": 1662.4548, | |
| "eval_samples_per_second": 24.061, | |
| "eval_steps_per_second": 24.061, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.650032970656116e-05, | |
| "loss": 2.156, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.647568414111441e-05, | |
| "loss": 2.1651, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 2.1709914207458496, | |
| "eval_runtime": 1673.5968, | |
| "eval_samples_per_second": 23.901, | |
| "eval_steps_per_second": 23.901, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 2.6451038575667655e-05, | |
| "loss": 2.1621, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.6426393010220902e-05, | |
| "loss": 2.1837, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 2.176527261734009, | |
| "eval_runtime": 1669.4555, | |
| "eval_samples_per_second": 23.96, | |
| "eval_steps_per_second": 23.96, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.640174744477415e-05, | |
| "loss": 2.1728, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.63771018793274e-05, | |
| "loss": 2.1521, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 2.1770825386047363, | |
| "eval_runtime": 1646.6769, | |
| "eval_samples_per_second": 24.291, | |
| "eval_steps_per_second": 24.291, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.6352456313880647e-05, | |
| "loss": 2.1571, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.6327810748433894e-05, | |
| "loss": 2.1474, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 2.183932304382324, | |
| "eval_runtime": 1639.8623, | |
| "eval_samples_per_second": 24.392, | |
| "eval_steps_per_second": 24.392, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.6303165182987143e-05, | |
| "loss": 2.165, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.627851961754039e-05, | |
| "loss": 2.1581, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 2.1714603900909424, | |
| "eval_runtime": 1639.9709, | |
| "eval_samples_per_second": 24.391, | |
| "eval_steps_per_second": 24.391, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.625387405209364e-05, | |
| "loss": 2.1739, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.6229228486646886e-05, | |
| "loss": 2.1539, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 2.1725363731384277, | |
| "eval_runtime": 1638.1954, | |
| "eval_samples_per_second": 24.417, | |
| "eval_steps_per_second": 24.417, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.6204582921200132e-05, | |
| "loss": 2.1458, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.6179937355753378e-05, | |
| "loss": 2.1755, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 2.176203727722168, | |
| "eval_runtime": 1640.2646, | |
| "eval_samples_per_second": 24.386, | |
| "eval_steps_per_second": 24.386, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 2.6155291790306628e-05, | |
| "loss": 2.1372, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.6130646224859874e-05, | |
| "loss": 2.1556, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 2.1716091632843018, | |
| "eval_runtime": 1640.0168, | |
| "eval_samples_per_second": 24.39, | |
| "eval_steps_per_second": 24.39, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.610600065941312e-05, | |
| "loss": 2.1467, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.6081355093966373e-05, | |
| "loss": 2.1613, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 2.1746010780334473, | |
| "eval_runtime": 1640.7934, | |
| "eval_samples_per_second": 24.378, | |
| "eval_steps_per_second": 24.378, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.605670952851962e-05, | |
| "loss": 2.1964, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6032063963072866e-05, | |
| "loss": 2.16, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 2.170952558517456, | |
| "eval_runtime": 1636.9866, | |
| "eval_samples_per_second": 24.435, | |
| "eval_steps_per_second": 24.435, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.6007418397626112e-05, | |
| "loss": 2.1573, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.5982772832179362e-05, | |
| "loss": 2.1615, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 2.1753742694854736, | |
| "eval_runtime": 1641.4118, | |
| "eval_samples_per_second": 24.369, | |
| "eval_steps_per_second": 24.369, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.5958127266732608e-05, | |
| "loss": 2.1389, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.5933481701285858e-05, | |
| "loss": 2.162, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 2.1643452644348145, | |
| "eval_runtime": 1631.9127, | |
| "eval_samples_per_second": 24.511, | |
| "eval_steps_per_second": 24.511, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.5908836135839104e-05, | |
| "loss": 2.1261, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.588419057039235e-05, | |
| "loss": 2.1397, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.16678786277771, | |
| "eval_runtime": 1670.9426, | |
| "eval_samples_per_second": 23.939, | |
| "eval_steps_per_second": 23.939, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.5859545004945597e-05, | |
| "loss": 2.1437, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.5834899439498846e-05, | |
| "loss": 2.1385, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 2.1743927001953125, | |
| "eval_runtime": 1630.9596, | |
| "eval_samples_per_second": 24.525, | |
| "eval_steps_per_second": 24.525, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.5810253874052093e-05, | |
| "loss": 2.131, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.578560830860534e-05, | |
| "loss": 2.1457, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 2.1709821224212646, | |
| "eval_runtime": 1641.5418, | |
| "eval_samples_per_second": 24.367, | |
| "eval_steps_per_second": 24.367, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.5760962743158592e-05, | |
| "loss": 2.1115, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.573631717771184e-05, | |
| "loss": 2.1394, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 2.169813871383667, | |
| "eval_runtime": 1633.6854, | |
| "eval_samples_per_second": 24.485, | |
| "eval_steps_per_second": 24.485, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.5711671612265085e-05, | |
| "loss": 2.1397, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.568702604681833e-05, | |
| "loss": 2.1359, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 2.1732752323150635, | |
| "eval_runtime": 1802.3943, | |
| "eval_samples_per_second": 22.193, | |
| "eval_steps_per_second": 22.193, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.566238048137158e-05, | |
| "loss": 2.1412, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5637734915924827e-05, | |
| "loss": 2.1248, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 2.1696412563323975, | |
| "eval_runtime": 1651.1875, | |
| "eval_samples_per_second": 24.225, | |
| "eval_steps_per_second": 24.225, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5613089350478077e-05, | |
| "loss": 2.1184, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5588443785031323e-05, | |
| "loss": 2.1352, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 2.1655664443969727, | |
| "eval_runtime": 1639.9406, | |
| "eval_samples_per_second": 24.391, | |
| "eval_steps_per_second": 24.391, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.556379821958457e-05, | |
| "loss": 2.1329, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5539152654137815e-05, | |
| "loss": 2.1304, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 2.171034574508667, | |
| "eval_runtime": 1644.883, | |
| "eval_samples_per_second": 24.318, | |
| "eval_steps_per_second": 24.318, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.5514507088691065e-05, | |
| "loss": 2.134, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.548986152324431e-05, | |
| "loss": 2.1417, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 2.164717674255371, | |
| "eval_runtime": 1627.0004, | |
| "eval_samples_per_second": 24.585, | |
| "eval_steps_per_second": 24.585, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.546521595779756e-05, | |
| "loss": 2.1519, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.544057039235081e-05, | |
| "loss": 2.1321, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 2.164560317993164, | |
| "eval_runtime": 1620.161, | |
| "eval_samples_per_second": 24.689, | |
| "eval_steps_per_second": 24.689, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.5415924826904057e-05, | |
| "loss": 2.1395, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.5391279261457303e-05, | |
| "loss": 2.1364, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 2.1626968383789062, | |
| "eval_runtime": 1698.7469, | |
| "eval_samples_per_second": 23.547, | |
| "eval_steps_per_second": 23.547, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.5366633696010553e-05, | |
| "loss": 2.1361, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.53419881305638e-05, | |
| "loss": 2.1207, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 2.169800281524658, | |
| "eval_runtime": 1698.1462, | |
| "eval_samples_per_second": 23.555, | |
| "eval_steps_per_second": 23.555, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.5317342565117046e-05, | |
| "loss": 2.1177, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.5292696999670295e-05, | |
| "loss": 2.1159, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 2.1711175441741943, | |
| "eval_runtime": 1693.0388, | |
| "eval_samples_per_second": 23.626, | |
| "eval_steps_per_second": 23.626, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.526805143422354e-05, | |
| "loss": 2.132, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.5243405868776788e-05, | |
| "loss": 2.1211, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 2.162254571914673, | |
| "eval_runtime": 1696.8798, | |
| "eval_samples_per_second": 23.573, | |
| "eval_steps_per_second": 23.573, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5218760303330034e-05, | |
| "loss": 2.1106, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5194114737883284e-05, | |
| "loss": 2.1324, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 2.160202980041504, | |
| "eval_runtime": 1693.2743, | |
| "eval_samples_per_second": 23.623, | |
| "eval_steps_per_second": 23.623, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.516946917243653e-05, | |
| "loss": 2.1137, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.5144823606989783e-05, | |
| "loss": 2.1332, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 2.1663293838500977, | |
| "eval_runtime": 1689.4982, | |
| "eval_samples_per_second": 23.676, | |
| "eval_steps_per_second": 23.676, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.512017804154303e-05, | |
| "loss": 2.1319, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5095532476096276e-05, | |
| "loss": 2.1189, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 2.1696457862854004, | |
| "eval_runtime": 1699.5766, | |
| "eval_samples_per_second": 23.535, | |
| "eval_steps_per_second": 23.535, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.5070886910649522e-05, | |
| "loss": 2.1304, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.504624134520277e-05, | |
| "loss": 2.1117, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 2.1668128967285156, | |
| "eval_runtime": 1687.1022, | |
| "eval_samples_per_second": 23.709, | |
| "eval_steps_per_second": 23.709, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.5021595779756018e-05, | |
| "loss": 2.1354, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.4996950214309264e-05, | |
| "loss": 2.1229, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 2.1560218334198, | |
| "eval_runtime": 1690.1223, | |
| "eval_samples_per_second": 23.667, | |
| "eval_steps_per_second": 23.667, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.4972304648862514e-05, | |
| "loss": 2.1299, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.494765908341576e-05, | |
| "loss": 2.1263, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 2.1626064777374268, | |
| "eval_runtime": 1689.2429, | |
| "eval_samples_per_second": 23.679, | |
| "eval_steps_per_second": 23.679, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4923013517969006e-05, | |
| "loss": 2.1201, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.4898367952522253e-05, | |
| "loss": 2.1187, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 2.1653449535369873, | |
| "eval_runtime": 1718.044, | |
| "eval_samples_per_second": 23.282, | |
| "eval_steps_per_second": 23.282, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.4873722387075502e-05, | |
| "loss": 2.1355, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.484907682162875e-05, | |
| "loss": 2.1306, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 2.161628007888794, | |
| "eval_runtime": 1732.448, | |
| "eval_samples_per_second": 23.089, | |
| "eval_steps_per_second": 23.089, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.4824431256182002e-05, | |
| "loss": 2.1256, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.4799785690735248e-05, | |
| "loss": 2.1253, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 2.162022113800049, | |
| "eval_runtime": 1750.94, | |
| "eval_samples_per_second": 22.845, | |
| "eval_steps_per_second": 22.845, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.4775140125288494e-05, | |
| "loss": 2.1164, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.475049455984174e-05, | |
| "loss": 2.1124, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 2.1629226207733154, | |
| "eval_runtime": 1747.2545, | |
| "eval_samples_per_second": 22.893, | |
| "eval_steps_per_second": 22.893, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.472584899439499e-05, | |
| "loss": 2.112, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.4701203428948237e-05, | |
| "loss": 2.1165, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 2.162862777709961, | |
| "eval_runtime": 1722.8861, | |
| "eval_samples_per_second": 23.217, | |
| "eval_steps_per_second": 23.217, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.4676557863501483e-05, | |
| "loss": 2.1258, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.4651912298054732e-05, | |
| "loss": 2.1283, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 2.1554527282714844, | |
| "eval_runtime": 1701.7426, | |
| "eval_samples_per_second": 23.505, | |
| "eval_steps_per_second": 23.505, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.462726673260798e-05, | |
| "loss": 2.1258, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.4602621167161225e-05, | |
| "loss": 2.1099, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 2.164123296737671, | |
| "eval_runtime": 1700.6722, | |
| "eval_samples_per_second": 23.52, | |
| "eval_steps_per_second": 23.52, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.457797560171447e-05, | |
| "loss": 2.1196, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.455333003626772e-05, | |
| "loss": 2.1165, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 2.1557888984680176, | |
| "eval_runtime": 1698.5145, | |
| "eval_samples_per_second": 23.55, | |
| "eval_steps_per_second": 23.55, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.4528684470820967e-05, | |
| "loss": 2.1125, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.450403890537422e-05, | |
| "loss": 2.1103, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 2.1602911949157715, | |
| "eval_runtime": 1693.809, | |
| "eval_samples_per_second": 23.615, | |
| "eval_steps_per_second": 23.615, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.4479393339927467e-05, | |
| "loss": 2.1217, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.4454747774480713e-05, | |
| "loss": 2.1136, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 2.159860134124756, | |
| "eval_runtime": 1688.1816, | |
| "eval_samples_per_second": 23.694, | |
| "eval_steps_per_second": 23.694, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.443010220903396e-05, | |
| "loss": 2.1218, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.440545664358721e-05, | |
| "loss": 2.101, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 2.161252498626709, | |
| "eval_runtime": 1707.6279, | |
| "eval_samples_per_second": 23.424, | |
| "eval_steps_per_second": 23.424, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.4380811078140455e-05, | |
| "loss": 2.0981, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.4356165512693705e-05, | |
| "loss": 2.1231, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 2.1558616161346436, | |
| "eval_runtime": 1696.8618, | |
| "eval_samples_per_second": 23.573, | |
| "eval_steps_per_second": 23.573, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.433151994724695e-05, | |
| "loss": 2.0957, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.4306874381800197e-05, | |
| "loss": 2.1368, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 2.154006242752075, | |
| "eval_runtime": 1697.1277, | |
| "eval_samples_per_second": 23.569, | |
| "eval_steps_per_second": 23.569, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.4282228816353444e-05, | |
| "loss": 2.1311, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.4257583250906693e-05, | |
| "loss": 2.1325, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 2.1554782390594482, | |
| "eval_runtime": 1697.9442, | |
| "eval_samples_per_second": 23.558, | |
| "eval_steps_per_second": 23.558, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.423293768545994e-05, | |
| "loss": 2.12, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.420829212001319e-05, | |
| "loss": 2.1017, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 2.1558518409729004, | |
| "eval_runtime": 1697.0901, | |
| "eval_samples_per_second": 23.57, | |
| "eval_steps_per_second": 23.57, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.418364655456644e-05, | |
| "loss": 2.1148, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.4159000989119685e-05, | |
| "loss": 2.1143, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 2.160183906555176, | |
| "eval_runtime": 1697.0904, | |
| "eval_samples_per_second": 23.57, | |
| "eval_steps_per_second": 23.57, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.413435542367293e-05, | |
| "loss": 2.1132, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.4109709858226178e-05, | |
| "loss": 2.0962, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 2.155602216720581, | |
| "eval_runtime": 1696.9463, | |
| "eval_samples_per_second": 23.572, | |
| "eval_steps_per_second": 23.572, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.4085064292779428e-05, | |
| "loss": 2.1274, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.4060418727332674e-05, | |
| "loss": 2.1103, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 2.1536872386932373, | |
| "eval_runtime": 1696.9858, | |
| "eval_samples_per_second": 23.571, | |
| "eval_steps_per_second": 23.571, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.4035773161885923e-05, | |
| "loss": 2.1002, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.401112759643917e-05, | |
| "loss": 2.0708, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 2.1589629650115967, | |
| "eval_runtime": 1700.1693, | |
| "eval_samples_per_second": 23.527, | |
| "eval_steps_per_second": 23.527, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.3986482030992416e-05, | |
| "loss": 2.0797, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.3961836465545662e-05, | |
| "loss": 2.072, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 2.157003402709961, | |
| "eval_runtime": 1683.9269, | |
| "eval_samples_per_second": 23.754, | |
| "eval_steps_per_second": 23.754, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.3937190900098912e-05, | |
| "loss": 2.1007, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.3912545334652158e-05, | |
| "loss": 2.0734, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 2.152344226837158, | |
| "eval_runtime": 1685.7847, | |
| "eval_samples_per_second": 23.728, | |
| "eval_steps_per_second": 23.728, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3887899769205408e-05, | |
| "loss": 2.0679, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.3863254203758658e-05, | |
| "loss": 2.0927, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 2.1572160720825195, | |
| "eval_runtime": 1687.9536, | |
| "eval_samples_per_second": 23.697, | |
| "eval_steps_per_second": 23.697, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.3838608638311904e-05, | |
| "loss": 2.0667, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.381396307286515e-05, | |
| "loss": 2.0767, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 2.1578407287597656, | |
| "eval_runtime": 1683.6847, | |
| "eval_samples_per_second": 23.757, | |
| "eval_steps_per_second": 23.757, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.3789317507418396e-05, | |
| "loss": 2.0856, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.3764671941971646e-05, | |
| "loss": 2.087, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 2.1585898399353027, | |
| "eval_runtime": 1707.9519, | |
| "eval_samples_per_second": 23.42, | |
| "eval_steps_per_second": 23.42, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.3740026376524892e-05, | |
| "loss": 2.0583, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.3715380811078142e-05, | |
| "loss": 2.0817, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 2.1547696590423584, | |
| "eval_runtime": 1701.5775, | |
| "eval_samples_per_second": 23.508, | |
| "eval_steps_per_second": 23.508, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.369073524563139e-05, | |
| "loss": 2.091, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.3666089680184635e-05, | |
| "loss": 2.0842, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 2.159339427947998, | |
| "eval_runtime": 1702.707, | |
| "eval_samples_per_second": 23.492, | |
| "eval_steps_per_second": 23.492, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.364144411473788e-05, | |
| "loss": 2.0842, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.361679854929113e-05, | |
| "loss": 2.0801, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 2.1500117778778076, | |
| "eval_runtime": 1705.3521, | |
| "eval_samples_per_second": 23.456, | |
| "eval_steps_per_second": 23.456, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.3592152983844377e-05, | |
| "loss": 2.0596, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.356750741839763e-05, | |
| "loss": 2.0757, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 2.1629602909088135, | |
| "eval_runtime": 1695.1748, | |
| "eval_samples_per_second": 23.596, | |
| "eval_steps_per_second": 23.596, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.3542861852950876e-05, | |
| "loss": 2.0893, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.3518216287504123e-05, | |
| "loss": 2.0878, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 2.151366710662842, | |
| "eval_runtime": 1691.2631, | |
| "eval_samples_per_second": 23.651, | |
| "eval_steps_per_second": 23.651, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.349357072205737e-05, | |
| "loss": 2.0882, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.346892515661062e-05, | |
| "loss": 2.0758, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 2.1577887535095215, | |
| "eval_runtime": 1700.0595, | |
| "eval_samples_per_second": 23.529, | |
| "eval_steps_per_second": 23.529, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.3444279591163865e-05, | |
| "loss": 2.0691, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.341963402571711e-05, | |
| "loss": 2.0816, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 2.1542584896087646, | |
| "eval_runtime": 1689.3566, | |
| "eval_samples_per_second": 23.678, | |
| "eval_steps_per_second": 23.678, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.339498846027036e-05, | |
| "loss": 2.0819, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.3370342894823607e-05, | |
| "loss": 2.0853, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 2.152047634124756, | |
| "eval_runtime": 1696.0173, | |
| "eval_samples_per_second": 23.585, | |
| "eval_steps_per_second": 23.585, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2.3345697329376853e-05, | |
| "loss": 2.0638, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.33210517639301e-05, | |
| "loss": 2.0759, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 2.1569483280181885, | |
| "eval_runtime": 1694.0839, | |
| "eval_samples_per_second": 23.612, | |
| "eval_steps_per_second": 23.612, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.329640619848335e-05, | |
| "loss": 2.089, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.32717606330366e-05, | |
| "loss": 2.0847, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 2.150604724884033, | |
| "eval_runtime": 1694.889, | |
| "eval_samples_per_second": 23.6, | |
| "eval_steps_per_second": 23.6, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.324711506758985e-05, | |
| "loss": 2.072, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.3222469502143095e-05, | |
| "loss": 2.0684, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 2.152568817138672, | |
| "eval_runtime": 1698.9537, | |
| "eval_samples_per_second": 23.544, | |
| "eval_steps_per_second": 23.544, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.319782393669634e-05, | |
| "loss": 2.0769, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2.3173178371249587e-05, | |
| "loss": 2.0776, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 2.1548068523406982, | |
| "eval_runtime": 1697.8718, | |
| "eval_samples_per_second": 23.559, | |
| "eval_steps_per_second": 23.559, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.3148532805802837e-05, | |
| "loss": 2.0947, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.3123887240356083e-05, | |
| "loss": 2.0804, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 2.1525418758392334, | |
| "eval_runtime": 1696.6504, | |
| "eval_samples_per_second": 23.576, | |
| "eval_steps_per_second": 23.576, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.309924167490933e-05, | |
| "loss": 2.0667, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.307459610946258e-05, | |
| "loss": 2.0724, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 2.149521589279175, | |
| "eval_runtime": 1698.3371, | |
| "eval_samples_per_second": 23.552, | |
| "eval_steps_per_second": 23.552, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.3049950544015826e-05, | |
| "loss": 2.0728, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.3025304978569072e-05, | |
| "loss": 2.0699, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 2.1547553539276123, | |
| "eval_runtime": 1693.508, | |
| "eval_samples_per_second": 23.62, | |
| "eval_steps_per_second": 23.62, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.3000659413122318e-05, | |
| "loss": 2.0787, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.2976013847675568e-05, | |
| "loss": 2.0786, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 2.1501739025115967, | |
| "eval_runtime": 1698.296, | |
| "eval_samples_per_second": 23.553, | |
| "eval_steps_per_second": 23.553, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.2951368282228818e-05, | |
| "loss": 2.0667, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.2926722716782067e-05, | |
| "loss": 2.078, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 2.1527764797210693, | |
| "eval_runtime": 1691.4717, | |
| "eval_samples_per_second": 23.648, | |
| "eval_steps_per_second": 23.648, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.2902077151335314e-05, | |
| "loss": 2.0774, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.287743158588856e-05, | |
| "loss": 2.082, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 2.1524477005004883, | |
| "eval_runtime": 1702.729, | |
| "eval_samples_per_second": 23.492, | |
| "eval_steps_per_second": 23.492, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.2852786020441806e-05, | |
| "loss": 2.0654, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.2828140454995056e-05, | |
| "loss": 2.0641, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 2.1543331146240234, | |
| "eval_runtime": 1702.4222, | |
| "eval_samples_per_second": 23.496, | |
| "eval_steps_per_second": 23.496, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.2803494889548302e-05, | |
| "loss": 2.0681, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.2778849324101552e-05, | |
| "loss": 2.0676, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 2.148048162460327, | |
| "eval_runtime": 1691.5175, | |
| "eval_samples_per_second": 23.647, | |
| "eval_steps_per_second": 23.647, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.2754203758654798e-05, | |
| "loss": 2.0742, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.2729558193208044e-05, | |
| "loss": 2.0605, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 2.155611991882324, | |
| "eval_runtime": 1692.7049, | |
| "eval_samples_per_second": 23.631, | |
| "eval_steps_per_second": 23.631, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.270491262776129e-05, | |
| "loss": 2.0729, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.268026706231454e-05, | |
| "loss": 2.0763, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 2.1516194343566895, | |
| "eval_runtime": 1695.0008, | |
| "eval_samples_per_second": 23.599, | |
| "eval_steps_per_second": 23.599, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.2655621496867787e-05, | |
| "loss": 2.0678, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.2630975931421036e-05, | |
| "loss": 2.066, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 2.1532933712005615, | |
| "eval_runtime": 1693.3099, | |
| "eval_samples_per_second": 23.622, | |
| "eval_steps_per_second": 23.622, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.2606330365974286e-05, | |
| "loss": 2.0719, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.2581684800527532e-05, | |
| "loss": 2.0803, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 2.150263786315918, | |
| "eval_runtime": 1689.1882, | |
| "eval_samples_per_second": 23.68, | |
| "eval_steps_per_second": 23.68, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.255703923508078e-05, | |
| "loss": 2.0737, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.2532393669634025e-05, | |
| "loss": 2.0862, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 2.1463823318481445, | |
| "eval_runtime": 1693.5654, | |
| "eval_samples_per_second": 23.619, | |
| "eval_steps_per_second": 23.619, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2.2507748104187274e-05, | |
| "loss": 2.0769, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.248310253874052e-05, | |
| "loss": 2.075, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 2.1545963287353516, | |
| "eval_runtime": 1697.0015, | |
| "eval_samples_per_second": 23.571, | |
| "eval_steps_per_second": 23.571, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.245845697329377e-05, | |
| "loss": 2.0745, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.2433811407847017e-05, | |
| "loss": 2.0801, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 2.146970748901367, | |
| "eval_runtime": 1700.75, | |
| "eval_samples_per_second": 23.519, | |
| "eval_steps_per_second": 23.519, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.2409165842400263e-05, | |
| "loss": 2.0755, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.238452027695351e-05, | |
| "loss": 2.0714, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 2.1499733924865723, | |
| "eval_runtime": 1700.6102, | |
| "eval_samples_per_second": 23.521, | |
| "eval_steps_per_second": 23.521, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.2359874711506756e-05, | |
| "loss": 2.0688, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.233522914606001e-05, | |
| "loss": 2.0764, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 2.141591787338257, | |
| "eval_runtime": 1694.1493, | |
| "eval_samples_per_second": 23.611, | |
| "eval_steps_per_second": 23.611, | |
| "step": 156000 | |
| } | |
| ], | |
| "max_steps": 607100, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.115410746630144e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |