| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 10, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 16.75, | |
| "learning_rate": 1.142857142857143e-06, | |
| "loss": 2.1299, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.1395466327667236, | |
| "eval_runtime": 1.8752, | |
| "eval_samples_per_second": 83.192, | |
| "eval_steps_per_second": 4.266, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 17.125, | |
| "learning_rate": 2.285714285714286e-06, | |
| "loss": 2.0585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.9696139097213745, | |
| "eval_runtime": 1.8157, | |
| "eval_samples_per_second": 85.918, | |
| "eval_steps_per_second": 4.406, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 20.0, | |
| "learning_rate": 3.428571428571429e-06, | |
| "loss": 1.7178, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.4725638628005981, | |
| "eval_runtime": 1.828, | |
| "eval_samples_per_second": 85.337, | |
| "eval_steps_per_second": 4.376, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 12.5, | |
| "learning_rate": 4.571428571428572e-06, | |
| "loss": 1.1311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.9639529585838318, | |
| "eval_runtime": 1.8321, | |
| "eval_samples_per_second": 85.149, | |
| "eval_steps_per_second": 4.367, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 0.9087, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.8117697238922119, | |
| "eval_runtime": 1.8294, | |
| "eval_samples_per_second": 85.276, | |
| "eval_steps_per_second": 4.373, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 4.0, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 0.7361, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.7243122458457947, | |
| "eval_runtime": 1.8406, | |
| "eval_samples_per_second": 84.755, | |
| "eval_steps_per_second": 4.346, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 5.84375, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6542, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.6852245330810547, | |
| "eval_runtime": 1.8344, | |
| "eval_samples_per_second": 85.043, | |
| "eval_steps_per_second": 4.361, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 0.6405, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.6576731204986572, | |
| "eval_runtime": 1.8353, | |
| "eval_samples_per_second": 85.0, | |
| "eval_steps_per_second": 4.359, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.0285714285714285e-05, | |
| "loss": 0.6306, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.6408917307853699, | |
| "eval_runtime": 1.8368, | |
| "eval_samples_per_second": 84.931, | |
| "eval_steps_per_second": 4.355, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.5593, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.6218527555465698, | |
| "eval_runtime": 1.8407, | |
| "eval_samples_per_second": 84.75, | |
| "eval_steps_per_second": 4.346, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 1.2571428571428572e-05, | |
| "loss": 0.6108, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.6078172922134399, | |
| "eval_runtime": 1.8218, | |
| "eval_samples_per_second": 85.628, | |
| "eval_steps_per_second": 4.391, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 1.3714285714285716e-05, | |
| "loss": 0.6107, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.6042583584785461, | |
| "eval_runtime": 1.833, | |
| "eval_samples_per_second": 85.107, | |
| "eval_steps_per_second": 4.364, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 6.53125, | |
| "learning_rate": 1.4857142857142858e-05, | |
| "loss": 0.5921, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.6016473770141602, | |
| "eval_runtime": 1.8301, | |
| "eval_samples_per_second": 85.241, | |
| "eval_steps_per_second": 4.371, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.5577, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.5969346761703491, | |
| "eval_runtime": 1.8347, | |
| "eval_samples_per_second": 85.029, | |
| "eval_steps_per_second": 4.36, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.5214, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.5916711688041687, | |
| "eval_runtime": 1.8257, | |
| "eval_samples_per_second": 85.448, | |
| "eval_steps_per_second": 4.382, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 3.640625, | |
| "learning_rate": 1.8285714285714288e-05, | |
| "loss": 0.5675, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.5914089679718018, | |
| "eval_runtime": 1.824, | |
| "eval_samples_per_second": 85.525, | |
| "eval_steps_per_second": 4.386, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 3.046875, | |
| "learning_rate": 1.942857142857143e-05, | |
| "loss": 0.5718, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.5912750363349915, | |
| "eval_runtime": 1.8251, | |
| "eval_samples_per_second": 85.476, | |
| "eval_steps_per_second": 4.383, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 5.875, | |
| "learning_rate": 1.9999502669559432e-05, | |
| "loss": 0.5099, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.5953446626663208, | |
| "eval_runtime": 1.8315, | |
| "eval_samples_per_second": 85.174, | |
| "eval_steps_per_second": 4.368, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.9995524322835035e-05, | |
| "loss": 0.5531, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.5920645594596863, | |
| "eval_runtime": 1.8189, | |
| "eval_samples_per_second": 85.767, | |
| "eval_steps_per_second": 4.398, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.9987569212189224e-05, | |
| "loss": 0.5936, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.5868185758590698, | |
| "eval_runtime": 1.8197, | |
| "eval_samples_per_second": 85.727, | |
| "eval_steps_per_second": 4.396, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 0.5256, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.5831221342086792, | |
| "eval_runtime": 1.8324, | |
| "eval_samples_per_second": 85.133, | |
| "eval_steps_per_second": 4.366, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.9959742939952393e-05, | |
| "loss": 0.5436, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.5828912854194641, | |
| "eval_runtime": 1.8214, | |
| "eval_samples_per_second": 85.65, | |
| "eval_steps_per_second": 4.392, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.9939882849167853e-05, | |
| "loss": 0.5338, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.5832617282867432, | |
| "eval_runtime": 1.8287, | |
| "eval_samples_per_second": 85.307, | |
| "eval_steps_per_second": 4.375, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 3.375, | |
| "learning_rate": 1.9916068131670302e-05, | |
| "loss": 0.5825, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.5794676542282104, | |
| "eval_runtime": 1.8254, | |
| "eval_samples_per_second": 85.461, | |
| "eval_steps_per_second": 4.383, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 1.9888308262251286e-05, | |
| "loss": 0.5602, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5799536108970642, | |
| "eval_runtime": 1.8258, | |
| "eval_samples_per_second": 85.441, | |
| "eval_steps_per_second": 4.382, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 3.375, | |
| "learning_rate": 1.985661428529863e-05, | |
| "loss": 0.4275, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 0.6025771498680115, | |
| "eval_runtime": 1.8242, | |
| "eval_samples_per_second": 85.517, | |
| "eval_steps_per_second": 4.386, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.982099881040239e-05, | |
| "loss": 0.4108, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.5985576510429382, | |
| "eval_runtime": 1.8242, | |
| "eval_samples_per_second": 85.515, | |
| "eval_steps_per_second": 4.385, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.418, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.5975014567375183, | |
| "eval_runtime": 1.8198, | |
| "eval_samples_per_second": 85.722, | |
| "eval_steps_per_second": 4.396, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 1.9140625, | |
| "learning_rate": 1.9738061600429062e-05, | |
| "loss": 0.3805, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.6011523008346558, | |
| "eval_runtime": 1.8201, | |
| "eval_samples_per_second": 85.708, | |
| "eval_steps_per_second": 4.395, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.969077286229078e-05, | |
| "loss": 0.3967, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.6029513478279114, | |
| "eval_runtime": 1.8226, | |
| "eval_samples_per_second": 85.593, | |
| "eval_steps_per_second": 4.389, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.9639628606958535e-05, | |
| "loss": 0.4397, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.5951108932495117, | |
| "eval_runtime": 1.8172, | |
| "eval_samples_per_second": 85.844, | |
| "eval_steps_per_second": 4.402, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 2.515625, | |
| "learning_rate": 1.9584649182402358e-05, | |
| "loss": 0.4374, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.5968344211578369, | |
| "eval_runtime": 1.8254, | |
| "eval_samples_per_second": 85.46, | |
| "eval_steps_per_second": 4.383, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 1.9525856462431463e-05, | |
| "loss": 0.4249, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.5980938673019409, | |
| "eval_runtime": 1.8248, | |
| "eval_samples_per_second": 85.49, | |
| "eval_steps_per_second": 4.384, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 2.109375, | |
| "learning_rate": 1.9463273837991643e-05, | |
| "loss": 0.4135, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.5925901532173157, | |
| "eval_runtime": 1.8236, | |
| "eval_samples_per_second": 85.544, | |
| "eval_steps_per_second": 4.387, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.425, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.5934858322143555, | |
| "eval_runtime": 1.8225, | |
| "eval_samples_per_second": 85.597, | |
| "eval_steps_per_second": 4.39, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 2.4375, | |
| "learning_rate": 1.9326839968734278e-05, | |
| "loss": 0.4261, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.5896275639533997, | |
| "eval_runtime": 1.8188, | |
| "eval_samples_per_second": 85.773, | |
| "eval_steps_per_second": 4.399, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 3.0625, | |
| "learning_rate": 1.9253043004739967e-05, | |
| "loss": 0.4163, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.5982385277748108, | |
| "eval_runtime": 1.8212, | |
| "eval_samples_per_second": 85.656, | |
| "eval_steps_per_second": 4.393, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.917556467632734e-05, | |
| "loss": 0.4424, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.5906324982643127, | |
| "eval_runtime": 1.8214, | |
| "eval_samples_per_second": 85.646, | |
| "eval_steps_per_second": 4.392, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.9094435808594823e-05, | |
| "loss": 0.3827, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.6001599431037903, | |
| "eval_runtime": 1.8232, | |
| "eval_samples_per_second": 85.566, | |
| "eval_steps_per_second": 4.388, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 0.4036, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.5959637761116028, | |
| "eval_runtime": 1.8277, | |
| "eval_samples_per_second": 85.354, | |
| "eval_steps_per_second": 4.377, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.8921357004638837e-05, | |
| "loss": 0.3885, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.593512237071991, | |
| "eval_runtime": 1.8262, | |
| "eval_samples_per_second": 85.424, | |
| "eval_steps_per_second": 4.381, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 3.0, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 0.4268, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.5908737182617188, | |
| "eval_runtime": 1.8249, | |
| "eval_samples_per_second": 85.484, | |
| "eval_steps_per_second": 4.384, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.87340820061713e-05, | |
| "loss": 0.4051, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.5885254740715027, | |
| "eval_runtime": 1.8213, | |
| "eval_samples_per_second": 85.652, | |
| "eval_steps_per_second": 4.392, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 1.8635213190282312e-05, | |
| "loss": 0.4012, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.5890469551086426, | |
| "eval_runtime": 1.8253, | |
| "eval_samples_per_second": 85.467, | |
| "eval_steps_per_second": 4.383, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 1.8532908816321557e-05, | |
| "loss": 0.4283, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.587235152721405, | |
| "eval_runtime": 1.819, | |
| "eval_samples_per_second": 85.761, | |
| "eval_steps_per_second": 4.398, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 2.8125, | |
| "learning_rate": 1.8427209586540392e-05, | |
| "loss": 0.4044, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.5868382453918457, | |
| "eval_runtime": 1.8214, | |
| "eval_samples_per_second": 85.649, | |
| "eval_steps_per_second": 4.392, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 1.8318157553848694e-05, | |
| "loss": 0.4342, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.5887174606323242, | |
| "eval_runtime": 1.8229, | |
| "eval_samples_per_second": 85.58, | |
| "eval_steps_per_second": 4.389, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 1.8205796105083917e-05, | |
| "loss": 0.4291, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.5855108499526978, | |
| "eval_runtime": 1.8227, | |
| "eval_samples_per_second": 85.589, | |
| "eval_steps_per_second": 4.389, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.4303, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.5847751498222351, | |
| "eval_runtime": 1.8226, | |
| "eval_samples_per_second": 85.594, | |
| "eval_steps_per_second": 4.389, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 1.7971325072229227e-05, | |
| "loss": 0.4211, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5896024107933044, | |
| "eval_runtime": 1.8212, | |
| "eval_samples_per_second": 85.657, | |
| "eval_steps_per_second": 4.393, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.7849308773485226e-05, | |
| "loss": 0.214, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.669939398765564, | |
| "eval_runtime": 1.8254, | |
| "eval_samples_per_second": 85.461, | |
| "eval_steps_per_second": 4.383, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.7724169592245996e-05, | |
| "loss": 0.2126, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.6375145316123962, | |
| "eval_runtime": 1.8249, | |
| "eval_samples_per_second": 85.486, | |
| "eval_steps_per_second": 4.384, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 2.25, | |
| "learning_rate": 1.7595957315692782e-05, | |
| "loss": 0.2108, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.6472862958908081, | |
| "eval_runtime": 1.8227, | |
| "eval_samples_per_second": 85.589, | |
| "eval_steps_per_second": 4.389, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.7464722953651504e-05, | |
| "loss": 0.2154, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.6398993134498596, | |
| "eval_runtime": 1.8233, | |
| "eval_samples_per_second": 85.56, | |
| "eval_steps_per_second": 4.388, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 1.7265625, | |
| "learning_rate": 1.7330518718298263e-05, | |
| "loss": 0.2127, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.6527624130249023, | |
| "eval_runtime": 1.8317, | |
| "eval_samples_per_second": 85.168, | |
| "eval_steps_per_second": 4.368, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 2.40625, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.2106, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.6582281589508057, | |
| "eval_runtime": 1.8389, | |
| "eval_samples_per_second": 84.835, | |
| "eval_steps_per_second": 4.351, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 2.015625, | |
| "learning_rate": 1.705341536300409e-05, | |
| "loss": 0.1955, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.6634351015090942, | |
| "eval_runtime": 1.8422, | |
| "eval_samples_per_second": 84.68, | |
| "eval_steps_per_second": 4.343, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 2.65625, | |
| "learning_rate": 1.691062648986865e-05, | |
| "loss": 0.1913, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.6663269400596619, | |
| "eval_runtime": 1.8357, | |
| "eval_samples_per_second": 84.983, | |
| "eval_steps_per_second": 4.358, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.6765088193170055e-05, | |
| "loss": 0.226, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.6499953866004944, | |
| "eval_runtime": 1.839, | |
| "eval_samples_per_second": 84.83, | |
| "eval_steps_per_second": 4.35, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.6616858375968596e-05, | |
| "loss": 0.2094, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.6462793350219727, | |
| "eval_runtime": 1.8441, | |
| "eval_samples_per_second": 84.592, | |
| "eval_steps_per_second": 4.338, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.6465996012157996e-05, | |
| "loss": 0.205, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.6545242667198181, | |
| "eval_runtime": 1.8396, | |
| "eval_samples_per_second": 84.8, | |
| "eval_steps_per_second": 4.349, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.631256112300239e-05, | |
| "loss": 0.2099, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.6629713773727417, | |
| "eval_runtime": 1.8435, | |
| "eval_samples_per_second": 84.621, | |
| "eval_steps_per_second": 4.34, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.2197, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.657893717288971, | |
| "eval_runtime": 1.8357, | |
| "eval_samples_per_second": 84.98, | |
| "eval_steps_per_second": 4.358, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 1.599821894687914e-05, | |
| "loss": 0.2135, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 0.6627128720283508, | |
| "eval_runtime": 1.8361, | |
| "eval_samples_per_second": 84.964, | |
| "eval_steps_per_second": 4.357, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 1.5837436722347902e-05, | |
| "loss": 0.2234, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.6546624302864075, | |
| "eval_runtime": 1.8329, | |
| "eval_samples_per_second": 85.112, | |
| "eval_steps_per_second": 4.365, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.567433204758782e-05, | |
| "loss": 0.2104, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.6604743599891663, | |
| "eval_runtime": 1.8296, | |
| "eval_samples_per_second": 85.263, | |
| "eval_steps_per_second": 4.372, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 1.5508969814521026e-05, | |
| "loss": 0.2148, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.6577239632606506, | |
| "eval_runtime": 1.8328, | |
| "eval_samples_per_second": 85.115, | |
| "eval_steps_per_second": 4.365, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.534141581324929e-05, | |
| "loss": 0.2301, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.6536082029342651, | |
| "eval_runtime": 1.8432, | |
| "eval_samples_per_second": 84.638, | |
| "eval_steps_per_second": 4.34, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 2.375, | |
| "learning_rate": 1.5171736705879127e-05, | |
| "loss": 0.216, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.650008499622345, | |
| "eval_runtime": 1.8464, | |
| "eval_samples_per_second": 84.49, | |
| "eval_steps_per_second": 4.333, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.2006, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.6558033227920532, | |
| "eval_runtime": 1.8156, | |
| "eval_samples_per_second": 85.924, | |
| "eval_steps_per_second": 4.406, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.482627402182611e-05, | |
| "loss": 0.2158, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.6513029336929321, | |
| "eval_runtime": 1.8338, | |
| "eval_samples_per_second": 85.068, | |
| "eval_steps_per_second": 4.362, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 2.15625, | |
| "learning_rate": 1.4650627889012507e-05, | |
| "loss": 0.2103, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.6524425745010376, | |
| "eval_runtime": 1.842, | |
| "eval_samples_per_second": 84.692, | |
| "eval_steps_per_second": 4.343, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 2.546875, | |
| "learning_rate": 1.4473131483156326e-05, | |
| "loss": 0.2196, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 0.6501613259315491, | |
| "eval_runtime": 1.8283, | |
| "eval_samples_per_second": 85.325, | |
| "eval_steps_per_second": 4.376, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 2.609375, | |
| "learning_rate": 1.4293855421994094e-05, | |
| "loss": 0.2061, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.6513486504554749, | |
| "eval_runtime": 1.8281, | |
| "eval_samples_per_second": 85.335, | |
| "eval_steps_per_second": 4.376, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 1.4112871031306118e-05, | |
| "loss": 0.2223, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6523801684379578, | |
| "eval_runtime": 1.8268, | |
| "eval_samples_per_second": 85.394, | |
| "eval_steps_per_second": 4.379, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 2.25, | |
| "learning_rate": 1.3930250316539237e-05, | |
| "loss": 0.1221, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 0.7312780618667603, | |
| "eval_runtime": 1.8299, | |
| "eval_samples_per_second": 85.251, | |
| "eval_steps_per_second": 4.372, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 2.59375, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.1157, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.7543404698371887, | |
| "eval_runtime": 1.8272, | |
| "eval_samples_per_second": 85.375, | |
| "eval_steps_per_second": 4.378, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 1.356039116274357e-05, | |
| "loss": 0.1138, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.726587176322937, | |
| "eval_runtime": 1.8234, | |
| "eval_samples_per_second": 85.557, | |
| "eval_steps_per_second": 4.388, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 1.3373299873828303e-05, | |
| "loss": 0.123, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "eval_loss": 0.7310608625411987, | |
| "eval_runtime": 1.8252, | |
| "eval_samples_per_second": 85.47, | |
| "eval_steps_per_second": 4.383, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 1.390625, | |
| "learning_rate": 1.3184866502516846e-05, | |
| "loss": 0.111, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.7380203008651733, | |
| "eval_runtime": 1.8245, | |
| "eval_samples_per_second": 85.505, | |
| "eval_steps_per_second": 4.385, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 1.7578125, | |
| "learning_rate": 1.2995166017866194e-05, | |
| "loss": 0.1197, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "eval_loss": 0.735602080821991, | |
| "eval_runtime": 1.8271, | |
| "eval_samples_per_second": 85.381, | |
| "eval_steps_per_second": 4.379, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "grad_norm": 1.65625, | |
| "learning_rate": 1.2804273893060028e-05, | |
| "loss": 0.1253, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 0.7375702261924744, | |
| "eval_runtime": 1.8333, | |
| "eval_samples_per_second": 85.094, | |
| "eval_steps_per_second": 4.364, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.2612266075381385e-05, | |
| "loss": 0.1179, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 0.7395501732826233, | |
| "eval_runtime": 1.8275, | |
| "eval_samples_per_second": 85.364, | |
| "eval_steps_per_second": 4.378, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 1.8984375, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.1296, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_loss": 0.7340117692947388, | |
| "eval_runtime": 1.8276, | |
| "eval_samples_per_second": 85.358, | |
| "eval_steps_per_second": 4.377, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 0.1192, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_loss": 0.7283806800842285, | |
| "eval_runtime": 1.8268, | |
| "eval_samples_per_second": 85.394, | |
| "eval_steps_per_second": 4.379, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 1.2030314413671763e-05, | |
| "loss": 0.1151, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 0.7252658605575562, | |
| "eval_runtime": 1.8274, | |
| "eval_samples_per_second": 85.368, | |
| "eval_steps_per_second": 4.378, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 1.1834611718137825e-05, | |
| "loss": 0.1168, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 0.7386046648025513, | |
| "eval_runtime": 1.8276, | |
| "eval_samples_per_second": 85.358, | |
| "eval_steps_per_second": 4.377, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 3.859375, | |
| "learning_rate": 1.1638179114151378e-05, | |
| "loss": 0.12, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_loss": 0.75035160779953, | |
| "eval_runtime": 1.8285, | |
| "eval_samples_per_second": 85.315, | |
| "eval_steps_per_second": 4.375, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "grad_norm": 1.4140625, | |
| "learning_rate": 1.1441094753299802e-05, | |
| "loss": 0.1301, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_loss": 0.7399159073829651, | |
| "eval_runtime": 1.8281, | |
| "eval_samples_per_second": 85.335, | |
| "eval_steps_per_second": 4.376, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 1.7734375, | |
| "learning_rate": 1.1243437046474854e-05, | |
| "loss": 0.1159, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.734505295753479, | |
| "eval_runtime": 1.8287, | |
| "eval_samples_per_second": 85.307, | |
| "eval_steps_per_second": 4.375, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 2.125, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.1217, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 0.7360817193984985, | |
| "eval_runtime": 1.8327, | |
| "eval_samples_per_second": 85.118, | |
| "eval_steps_per_second": 4.365, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 1.78125, | |
| "learning_rate": 1.0846716347726233e-05, | |
| "loss": 0.1164, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_loss": 0.7412881255149841, | |
| "eval_runtime": 1.8259, | |
| "eval_samples_per_second": 85.439, | |
| "eval_steps_per_second": 4.382, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "grad_norm": 1.3984375, | |
| "learning_rate": 1.0647811192901518e-05, | |
| "loss": 0.1167, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 0.7428140044212341, | |
| "eval_runtime": 1.8329, | |
| "eval_samples_per_second": 85.111, | |
| "eval_steps_per_second": 4.365, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 1.044864830350515e-05, | |
| "loss": 0.122, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "eval_loss": 0.7407277226448059, | |
| "eval_runtime": 1.8317, | |
| "eval_samples_per_second": 85.165, | |
| "eval_steps_per_second": 4.367, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 1.3203125, | |
| "learning_rate": 1.0249306917380731e-05, | |
| "loss": 0.1174, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 0.739768385887146, | |
| "eval_runtime": 1.8255, | |
| "eval_samples_per_second": 85.457, | |
| "eval_steps_per_second": 4.382, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 1.625, | |
| "learning_rate": 1.0049866343387582e-05, | |
| "loss": 0.1152, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 0.7400333881378174, | |
| "eval_runtime": 1.827, | |
| "eval_samples_per_second": 85.384, | |
| "eval_steps_per_second": 4.379, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 9.850405929847367e-06, | |
| "loss": 0.1265, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "eval_loss": 0.7430944442749023, | |
| "eval_runtime": 1.8297, | |
| "eval_samples_per_second": 85.261, | |
| "eval_steps_per_second": 4.372, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "grad_norm": 1.4609375, | |
| "learning_rate": 9.651005032974994e-06, | |
| "loss": 0.1183, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 0.7510712742805481, | |
| "eval_runtime": 1.8296, | |
| "eval_samples_per_second": 85.264, | |
| "eval_steps_per_second": 4.373, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 9.4517429853064e-06, | |
| "loss": 0.1169, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 0.7500400543212891, | |
| "eval_runtime": 1.8299, | |
| "eval_samples_per_second": 85.252, | |
| "eval_steps_per_second": 4.372, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.8359375, | |
| "learning_rate": 9.252699064135759e-06, | |
| "loss": 0.1191, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.7431495785713196, | |
| "eval_runtime": 1.8402, | |
| "eval_samples_per_second": 84.774, | |
| "eval_steps_per_second": 4.347, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "total_flos": 9.48348331795415e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |