| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.996011396011396, | |
| "eval_steps": 500, | |
| "global_step": 1314, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 1.1971258233647637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.7980484827875407, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.9071642149447434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6796, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.8612137999379124, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6794, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.8035666098155594, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6755, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.6770011867016273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6551, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.44801829754361133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.652, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.37755075969161783, | |
| "learning_rate": 5e-06, | |
| "loss": 0.655, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.31540683060359476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6397, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.3007494360593848, | |
| "learning_rate": 5e-06, | |
| "loss": 0.641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.33895214190090917, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6323, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.3070144915055194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6406, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.2895750901265279, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.3078158388563675, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6437, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.3110436970966206, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6362, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.31245569584499555, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6414, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.3596651585190044, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6332, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.2963606015052807, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6387, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.30315877922859497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6313, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.30426971666648045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6394, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.3090940011420846, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6357, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.3030681417284509, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6394, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.3237381931795037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.635, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.3005504395534347, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6309, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.33169918765087686, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6358, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.3009298815938261, | |
| "learning_rate": 5e-06, | |
| "loss": 0.634, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.30744307688401507, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6311, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.3279175755970601, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6419, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.3289090789927867, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6306, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.2854748875179496, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.2991563777299476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6286, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.33511506767288557, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6291, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.3037033252170676, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6258, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.33097093854534626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6316, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.3307444115460614, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6387, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.3151765558306375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6304, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.3379019384905337, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6242, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.3126887513754788, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6365, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.32925730498547584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.635, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.2978036556412762, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6382, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.289640703225658, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6345, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.3026561525544134, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6214, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.3397854219636717, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6344, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6250635981559753, | |
| "eval_runtime": 439.0667, | |
| "eval_samples_per_second": 26.928, | |
| "eval_steps_per_second": 0.421, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.3459608098032768, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6471, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.3262562439094346, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6014, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.31143402213282795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5952, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.2910747569488903, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.30400774756928156, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6035, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.33115180700526176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.29149552599551304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5984, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.3109915110332694, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.2961129445555981, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.32307405333599015, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5951, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.288036504729705, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6053, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.33288538265730133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6019, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.2879818949036318, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6034, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.3062524679342497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5975, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.2720920616055293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5959, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.2939303230115104, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5957, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.3473254630486921, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6013, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.3225692085792273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6013, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.2932018066888041, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6039, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.3139198151802545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6019, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.30804637385823225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5968, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.29934506174738645, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5947, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.2908995234453594, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5944, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.31573752727748167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.27582728820967456, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5906, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.32900911461957716, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5945, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.2864850746661905, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6101, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.3076750266232437, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5971, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.29013113513057376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6017, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.32853478390443247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.3212067064463354, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5959, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.2972760971170388, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5933, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.3094250761102705, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5972, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.2982342821177231, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5936, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.30920000199984904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6008, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.2949027515395575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5984, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.31043498815582843, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5851, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.30810688172811324, | |
| "learning_rate": 5e-06, | |
| "loss": 0.593, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.30623595909755325, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5908, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.327188525053139, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5946, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.310903558460967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.599, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.3021187702467701, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5972, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.3108930383190649, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5985, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.3507405640216123, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5959, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6187016367912292, | |
| "eval_runtime": 440.3195, | |
| "eval_samples_per_second": 26.851, | |
| "eval_steps_per_second": 0.42, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.33247529291148487, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6153, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.35035702544183833, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5544, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.3079737428410421, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5695, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.3546826206246178, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5676, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.33546462432559726, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5708, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.28495486013565147, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.2994932879877907, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5635, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.304625525109529, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5643, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.31522776479984477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.2935531068982711, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.28633664929312297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5585, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.323299232881518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5676, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.3023262779587687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5679, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.32932247022115296, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5654, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.3096111275725531, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5684, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.35230664675988677, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5697, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.2969558547430912, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5677, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.30518464062660466, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.2978848500767363, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5754, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.3003352203902967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5782, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.306630876746365, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5735, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.30337205010612617, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5711, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.3036174952543044, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5776, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.3097038070254852, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5711, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.3055259061973633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5692, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.2978967073586066, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.3134626755759451, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5683, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.30526868243301847, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5686, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.3094315211429326, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5698, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.2979337120230037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5726, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.29617078222655224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5677, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.2874153849084469, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.2882166610791341, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5719, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.29078138854804286, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5753, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.2866124714656832, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5652, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.2924235716239258, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.3070438197451834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5784, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.3055107717692077, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5751, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.3021077678301008, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5723, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.30622160394298603, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5732, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.28670420364394134, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5634, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.2968532310336153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5636, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.35184113878950307, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5648, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.3103099246416176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5746, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.6186709403991699, | |
| "eval_runtime": 440.9792, | |
| "eval_samples_per_second": 26.811, | |
| "eval_steps_per_second": 0.42, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.6038080361335789, | |
| "train_runtime": 70053.326, | |
| "train_samples_per_second": 9.619, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1314, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2755219238682624.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |