| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.524137931034483, | |
| "eval_steps": 1, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013793103448275862, | |
| "grad_norm": 6.989287853240967, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 1.8926, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013793103448275862, | |
| "eval_loss": 2.144650459289551, | |
| "eval_runtime": 17.2592, | |
| "eval_samples_per_second": 1.159, | |
| "eval_steps_per_second": 0.579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027586206896551724, | |
| "grad_norm": 6.281332492828369, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.986, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027586206896551724, | |
| "eval_loss": 2.0905685424804688, | |
| "eval_runtime": 17.6184, | |
| "eval_samples_per_second": 1.135, | |
| "eval_steps_per_second": 0.568, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041379310344827586, | |
| "grad_norm": 4.347537040710449, | |
| "learning_rate": 6.818181818181818e-06, | |
| "loss": 1.9355, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.041379310344827586, | |
| "eval_loss": 1.9983774423599243, | |
| "eval_runtime": 17.5928, | |
| "eval_samples_per_second": 1.137, | |
| "eval_steps_per_second": 0.568, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05517241379310345, | |
| "grad_norm": 4.809764385223389, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.7509, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05517241379310345, | |
| "eval_loss": 1.8737837076187134, | |
| "eval_runtime": 17.6375, | |
| "eval_samples_per_second": 1.134, | |
| "eval_steps_per_second": 0.567, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 3.4548702239990234, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 1.8838, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "eval_loss": 1.7746165990829468, | |
| "eval_runtime": 18.0257, | |
| "eval_samples_per_second": 1.11, | |
| "eval_steps_per_second": 0.555, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "grad_norm": 3.1943702697753906, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 1.7707, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "eval_loss": 1.6792665719985962, | |
| "eval_runtime": 17.7498, | |
| "eval_samples_per_second": 1.127, | |
| "eval_steps_per_second": 0.563, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09655172413793103, | |
| "grad_norm": 3.318288564682007, | |
| "learning_rate": 1.590909090909091e-05, | |
| "loss": 1.7171, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09655172413793103, | |
| "eval_loss": 1.5874873399734497, | |
| "eval_runtime": 17.6295, | |
| "eval_samples_per_second": 1.134, | |
| "eval_steps_per_second": 0.567, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 3.210330009460449, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.5734, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "eval_loss": 1.535287618637085, | |
| "eval_runtime": 17.6232, | |
| "eval_samples_per_second": 1.135, | |
| "eval_steps_per_second": 0.567, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12413793103448276, | |
| "grad_norm": 3.2319107055664062, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 1.7986, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12413793103448276, | |
| "eval_loss": 1.467301607131958, | |
| "eval_runtime": 17.5824, | |
| "eval_samples_per_second": 1.138, | |
| "eval_steps_per_second": 0.569, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 2.79286789894104, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.5025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "eval_loss": 1.3961191177368164, | |
| "eval_runtime": 18.3446, | |
| "eval_samples_per_second": 1.09, | |
| "eval_steps_per_second": 0.545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15172413793103448, | |
| "grad_norm": 2.885422706604004, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5477, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15172413793103448, | |
| "eval_loss": 1.3420469760894775, | |
| "eval_runtime": 17.7683, | |
| "eval_samples_per_second": 1.126, | |
| "eval_steps_per_second": 0.563, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16551724137931034, | |
| "grad_norm": 2.7671327590942383, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 1.6921, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16551724137931034, | |
| "eval_loss": 1.3071445226669312, | |
| "eval_runtime": 17.652, | |
| "eval_samples_per_second": 1.133, | |
| "eval_steps_per_second": 0.567, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1793103448275862, | |
| "grad_norm": 2.9047963619232178, | |
| "learning_rate": 2.954545454545455e-05, | |
| "loss": 1.5365, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1793103448275862, | |
| "eval_loss": 1.2601890563964844, | |
| "eval_runtime": 17.5232, | |
| "eval_samples_per_second": 1.141, | |
| "eval_steps_per_second": 0.571, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19310344827586207, | |
| "grad_norm": 2.6054675579071045, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 1.6621, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19310344827586207, | |
| "eval_loss": 1.2506535053253174, | |
| "eval_runtime": 17.6295, | |
| "eval_samples_per_second": 1.134, | |
| "eval_steps_per_second": 0.567, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 2.538036823272705, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 1.6763, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "eval_loss": 1.2366451025009155, | |
| "eval_runtime": 18.6172, | |
| "eval_samples_per_second": 1.074, | |
| "eval_steps_per_second": 0.537, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 2.5125789642333984, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 1.668, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "eval_loss": 1.2205184698104858, | |
| "eval_runtime": 17.7529, | |
| "eval_samples_per_second": 1.127, | |
| "eval_steps_per_second": 0.563, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23448275862068965, | |
| "grad_norm": 5.055665969848633, | |
| "learning_rate": 3.8636363636363636e-05, | |
| "loss": 1.5703, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23448275862068965, | |
| "eval_loss": 1.167407751083374, | |
| "eval_runtime": 17.5902, | |
| "eval_samples_per_second": 1.137, | |
| "eval_steps_per_second": 0.568, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2482758620689655, | |
| "grad_norm": 2.567411422729492, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 1.4859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2482758620689655, | |
| "eval_loss": 1.1367636919021606, | |
| "eval_runtime": 17.4832, | |
| "eval_samples_per_second": 1.144, | |
| "eval_steps_per_second": 0.572, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2620689655172414, | |
| "grad_norm": 2.3214948177337646, | |
| "learning_rate": 4.318181818181819e-05, | |
| "loss": 1.4511, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2620689655172414, | |
| "eval_loss": 1.1296402215957642, | |
| "eval_runtime": 17.6655, | |
| "eval_samples_per_second": 1.132, | |
| "eval_steps_per_second": 0.566, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 2.390448570251465, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 1.7181, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "eval_loss": 1.126497507095337, | |
| "eval_runtime": 17.9736, | |
| "eval_samples_per_second": 1.113, | |
| "eval_steps_per_second": 0.556, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2896551724137931, | |
| "grad_norm": 2.3728342056274414, | |
| "learning_rate": 4.772727272727273e-05, | |
| "loss": 1.4155, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2896551724137931, | |
| "eval_loss": 1.09345281124115, | |
| "eval_runtime": 17.8283, | |
| "eval_samples_per_second": 1.122, | |
| "eval_steps_per_second": 0.561, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30344827586206896, | |
| "grad_norm": 2.4872097969055176, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3752, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.30344827586206896, | |
| "eval_loss": 1.0705276727676392, | |
| "eval_runtime": 17.6481, | |
| "eval_samples_per_second": 1.133, | |
| "eval_steps_per_second": 0.567, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31724137931034485, | |
| "grad_norm": 2.953234910964966, | |
| "learning_rate": 4.999672209164081e-05, | |
| "loss": 1.4449, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.31724137931034485, | |
| "eval_loss": 1.0468412637710571, | |
| "eval_runtime": 17.6053, | |
| "eval_samples_per_second": 1.136, | |
| "eval_steps_per_second": 0.568, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3310344827586207, | |
| "grad_norm": 2.47603702545166, | |
| "learning_rate": 4.998688922613788e-05, | |
| "loss": 1.4286, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3310344827586207, | |
| "eval_loss": 1.0292497873306274, | |
| "eval_runtime": 17.5777, | |
| "eval_samples_per_second": 1.138, | |
| "eval_steps_per_second": 0.569, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 2.2879106998443604, | |
| "learning_rate": 4.997050398198977e-05, | |
| "loss": 1.5164, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "eval_loss": 1.0196115970611572, | |
| "eval_runtime": 17.9439, | |
| "eval_samples_per_second": 1.115, | |
| "eval_steps_per_second": 0.557, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3586206896551724, | |
| "grad_norm": 2.319134473800659, | |
| "learning_rate": 4.9947570655942796e-05, | |
| "loss": 1.5282, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3586206896551724, | |
| "eval_loss": 1.013381004333496, | |
| "eval_runtime": 17.7628, | |
| "eval_samples_per_second": 1.126, | |
| "eval_steps_per_second": 0.563, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3724137931034483, | |
| "grad_norm": 2.259608745574951, | |
| "learning_rate": 4.991809526186424e-05, | |
| "loss": 1.4901, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3724137931034483, | |
| "eval_loss": 1.0091207027435303, | |
| "eval_runtime": 17.619, | |
| "eval_samples_per_second": 1.135, | |
| "eval_steps_per_second": 0.568, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38620689655172413, | |
| "grad_norm": 2.2252631187438965, | |
| "learning_rate": 4.988208552916535e-05, | |
| "loss": 1.5518, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.38620689655172413, | |
| "eval_loss": 1.0063353776931763, | |
| "eval_runtime": 17.4778, | |
| "eval_samples_per_second": 1.144, | |
| "eval_steps_per_second": 0.572, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.2154901027679443, | |
| "learning_rate": 4.983955090077444e-05, | |
| "loss": 1.4682, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.99261075258255, | |
| "eval_runtime": 17.4894, | |
| "eval_samples_per_second": 1.144, | |
| "eval_steps_per_second": 0.572, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 2.320786237716675, | |
| "learning_rate": 4.9790502530660635e-05, | |
| "loss": 1.4691, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "eval_loss": 0.9836109280586243, | |
| "eval_runtime": 16.9043, | |
| "eval_samples_per_second": 1.183, | |
| "eval_steps_per_second": 0.592, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.42758620689655175, | |
| "grad_norm": 2.1385531425476074, | |
| "learning_rate": 4.9734953280908904e-05, | |
| "loss": 1.4696, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.42758620689655175, | |
| "eval_loss": 0.976610541343689, | |
| "eval_runtime": 17.3486, | |
| "eval_samples_per_second": 1.153, | |
| "eval_steps_per_second": 0.576, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4413793103448276, | |
| "grad_norm": 2.2254769802093506, | |
| "learning_rate": 4.967291771834727e-05, | |
| "loss": 1.531, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4413793103448276, | |
| "eval_loss": 0.9718761444091797, | |
| "eval_runtime": 17.5285, | |
| "eval_samples_per_second": 1.141, | |
| "eval_steps_per_second": 0.57, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.45517241379310347, | |
| "grad_norm": 2.34843373298645, | |
| "learning_rate": 4.960441211072686e-05, | |
| "loss": 1.5484, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45517241379310347, | |
| "eval_loss": 0.9682589769363403, | |
| "eval_runtime": 17.5952, | |
| "eval_samples_per_second": 1.137, | |
| "eval_steps_per_second": 0.568, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4689655172413793, | |
| "grad_norm": 1.9610539674758911, | |
| "learning_rate": 4.9529454422455976e-05, | |
| "loss": 1.3204, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4689655172413793, | |
| "eval_loss": 0.9610344767570496, | |
| "eval_runtime": 17.6076, | |
| "eval_samples_per_second": 1.136, | |
| "eval_steps_per_second": 0.568, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 2.2027809619903564, | |
| "learning_rate": 4.944806430988927e-05, | |
| "loss": 1.3801, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "eval_loss": 0.9546059370040894, | |
| "eval_runtime": 17.5811, | |
| "eval_samples_per_second": 1.138, | |
| "eval_steps_per_second": 0.569, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.496551724137931, | |
| "grad_norm": 2.3457250595092773, | |
| "learning_rate": 4.936026311617316e-05, | |
| "loss": 1.4401, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.496551724137931, | |
| "eval_loss": 0.9482511281967163, | |
| "eval_runtime": 17.8351, | |
| "eval_samples_per_second": 1.121, | |
| "eval_steps_per_second": 0.561, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5103448275862069, | |
| "grad_norm": 2.161039352416992, | |
| "learning_rate": 4.926607386564898e-05, | |
| "loss": 1.4067, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5103448275862069, | |
| "eval_loss": 0.9448164701461792, | |
| "eval_runtime": 17.6014, | |
| "eval_samples_per_second": 1.136, | |
| "eval_steps_per_second": 0.568, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5241379310344828, | |
| "grad_norm": 2.1683900356292725, | |
| "learning_rate": 4.916552125781528e-05, | |
| "loss": 1.3806, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5241379310344828, | |
| "eval_loss": 0.9402996897697449, | |
| "eval_runtime": 17.6524, | |
| "eval_samples_per_second": 1.133, | |
| "eval_steps_per_second": 0.566, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5379310344827586, | |
| "grad_norm": 2.2735962867736816, | |
| "learning_rate": 4.9058631660850765e-05, | |
| "loss": 1.4937, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5379310344827586, | |
| "eval_loss": 0.9291872978210449, | |
| "eval_runtime": 17.5838, | |
| "eval_samples_per_second": 1.137, | |
| "eval_steps_per_second": 0.569, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5655172413793104, | |
| "grad_norm": 2.2170450687408447, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 1.316, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5655172413793104, | |
| "eval_loss": 0.9163956642150879, | |
| "eval_runtime": 15.7145, | |
| "eval_samples_per_second": 1.273, | |
| "eval_steps_per_second": 0.636, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5793103448275863, | |
| "grad_norm": 2.2266974449157715, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.3854, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5793103448275863, | |
| "eval_loss": 0.9137259721755981, | |
| "eval_runtime": 15.7133, | |
| "eval_samples_per_second": 1.273, | |
| "eval_steps_per_second": 0.636, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.593103448275862, | |
| "grad_norm": 2.3451268672943115, | |
| "learning_rate": 6.818181818181818e-06, | |
| "loss": 1.4208, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.593103448275862, | |
| "eval_loss": 0.9096618890762329, | |
| "eval_runtime": 15.7895, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.633, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6068965517241379, | |
| "grad_norm": 2.0125885009765625, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.4302, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6068965517241379, | |
| "eval_loss": 0.9058458209037781, | |
| "eval_runtime": 15.6899, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.637, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 2.1096601486206055, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 1.3981, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "eval_loss": 0.8982122540473938, | |
| "eval_runtime": 15.707, | |
| "eval_samples_per_second": 1.273, | |
| "eval_steps_per_second": 0.637, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6344827586206897, | |
| "grad_norm": 1.971846342086792, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 1.263, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6344827586206897, | |
| "eval_loss": 0.891434371471405, | |
| "eval_runtime": 15.7993, | |
| "eval_samples_per_second": 1.266, | |
| "eval_steps_per_second": 0.633, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6482758620689655, | |
| "grad_norm": 1.9724080562591553, | |
| "learning_rate": 1.590909090909091e-05, | |
| "loss": 1.355, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6482758620689655, | |
| "eval_loss": 0.8870094418525696, | |
| "eval_runtime": 15.6828, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.638, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6620689655172414, | |
| "grad_norm": 2.0631349086761475, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.3375, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6620689655172414, | |
| "eval_loss": 0.8790606260299683, | |
| "eval_runtime": 15.6783, | |
| "eval_samples_per_second": 1.276, | |
| "eval_steps_per_second": 0.638, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6758620689655173, | |
| "grad_norm": 2.1942760944366455, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 1.3937, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6758620689655173, | |
| "eval_loss": 0.8732376098632812, | |
| "eval_runtime": 15.6854, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.638, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 2.119081497192383, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.5447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "eval_loss": 0.8692445755004883, | |
| "eval_runtime": 15.6827, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.638, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7034482758620689, | |
| "grad_norm": 1.9801068305969238, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.2777, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7034482758620689, | |
| "eval_loss": 0.8668963313102722, | |
| "eval_runtime": 15.7049, | |
| "eval_samples_per_second": 1.273, | |
| "eval_steps_per_second": 0.637, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7172413793103448, | |
| "grad_norm": 2.0645248889923096, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 1.3444, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7172413793103448, | |
| "eval_loss": 0.8615155220031738, | |
| "eval_runtime": 15.6899, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.637, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7310344827586207, | |
| "grad_norm": 2.1377453804016113, | |
| "learning_rate": 2.954545454545455e-05, | |
| "loss": 1.4174, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7310344827586207, | |
| "eval_loss": 0.8575263023376465, | |
| "eval_runtime": 15.6427, | |
| "eval_samples_per_second": 1.279, | |
| "eval_steps_per_second": 0.639, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7448275862068966, | |
| "grad_norm": 2.1462454795837402, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 1.429, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7448275862068966, | |
| "eval_loss": 0.8533774614334106, | |
| "eval_runtime": 15.7668, | |
| "eval_samples_per_second": 1.268, | |
| "eval_steps_per_second": 0.634, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7724137931034483, | |
| "grad_norm": 2.1803667545318604, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 1.4271, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7724137931034483, | |
| "eval_loss": 0.8433731198310852, | |
| "eval_runtime": 17.9885, | |
| "eval_samples_per_second": 1.112, | |
| "eval_steps_per_second": 0.556, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7862068965517242, | |
| "grad_norm": 2.3162448406219482, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.4689, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7862068965517242, | |
| "eval_loss": 0.8418852090835571, | |
| "eval_runtime": 18.2763, | |
| "eval_samples_per_second": 1.094, | |
| "eval_steps_per_second": 0.547, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.9732853174209595, | |
| "learning_rate": 6.818181818181818e-06, | |
| "loss": 1.2825, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.8386393785476685, | |
| "eval_runtime": 18.1184, | |
| "eval_samples_per_second": 1.104, | |
| "eval_steps_per_second": 0.552, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8137931034482758, | |
| "grad_norm": 2.0547423362731934, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.2972, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8137931034482758, | |
| "eval_loss": 0.8355510830879211, | |
| "eval_runtime": 18.2216, | |
| "eval_samples_per_second": 1.098, | |
| "eval_steps_per_second": 0.549, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 2.0684103965759277, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 1.3615, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "eval_loss": 0.8328086137771606, | |
| "eval_runtime": 18.8073, | |
| "eval_samples_per_second": 1.063, | |
| "eval_steps_per_second": 0.532, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8413793103448276, | |
| "grad_norm": 2.0212347507476807, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 1.3648, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8413793103448276, | |
| "eval_loss": 0.8308294415473938, | |
| "eval_runtime": 18.376, | |
| "eval_samples_per_second": 1.088, | |
| "eval_steps_per_second": 0.544, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8551724137931035, | |
| "grad_norm": 1.9967029094696045, | |
| "learning_rate": 1.590909090909091e-05, | |
| "loss": 1.4334, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8551724137931035, | |
| "eval_loss": 0.8297985792160034, | |
| "eval_runtime": 18.24, | |
| "eval_samples_per_second": 1.096, | |
| "eval_steps_per_second": 0.548, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8689655172413793, | |
| "grad_norm": 1.956730842590332, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.246, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8689655172413793, | |
| "eval_loss": 0.8276138305664062, | |
| "eval_runtime": 18.1099, | |
| "eval_samples_per_second": 1.104, | |
| "eval_steps_per_second": 0.552, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8827586206896552, | |
| "grad_norm": 1.8840367794036865, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 1.2346, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8827586206896552, | |
| "eval_loss": 0.8268927335739136, | |
| "eval_runtime": 18.2242, | |
| "eval_samples_per_second": 1.097, | |
| "eval_steps_per_second": 0.549, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 1.9588886499404907, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.3699, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "eval_loss": 0.8241379857063293, | |
| "eval_runtime": 18.6162, | |
| "eval_samples_per_second": 1.074, | |
| "eval_steps_per_second": 0.537, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9103448275862069, | |
| "grad_norm": 2.001984119415283, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4399, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9103448275862069, | |
| "eval_loss": 0.8220138549804688, | |
| "eval_runtime": 18.4936, | |
| "eval_samples_per_second": 1.081, | |
| "eval_steps_per_second": 0.541, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9241379310344827, | |
| "grad_norm": 1.9502840042114258, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 1.1969, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9241379310344827, | |
| "eval_loss": 0.8098680377006531, | |
| "eval_runtime": 18.2406, | |
| "eval_samples_per_second": 1.096, | |
| "eval_steps_per_second": 0.548, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9379310344827586, | |
| "grad_norm": 1.8572745323181152, | |
| "learning_rate": 2.954545454545455e-05, | |
| "loss": 1.1968, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.9379310344827586, | |
| "eval_loss": 0.7934565544128418, | |
| "eval_runtime": 18.2457, | |
| "eval_samples_per_second": 1.096, | |
| "eval_steps_per_second": 0.548, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.9517241379310345, | |
| "grad_norm": 2.0354831218719482, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 1.2528, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9517241379310345, | |
| "eval_loss": 0.7829666137695312, | |
| "eval_runtime": 18.2217, | |
| "eval_samples_per_second": 1.098, | |
| "eval_steps_per_second": 0.549, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 2.1164538860321045, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 1.3873, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "eval_loss": 0.7753366231918335, | |
| "eval_runtime": 18.5302, | |
| "eval_samples_per_second": 1.079, | |
| "eval_steps_per_second": 0.54, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9793103448275862, | |
| "grad_norm": 2.032721996307373, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 1.232, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9793103448275862, | |
| "eval_loss": 0.7628229856491089, | |
| "eval_runtime": 18.4062, | |
| "eval_samples_per_second": 1.087, | |
| "eval_steps_per_second": 0.543, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.993103448275862, | |
| "grad_norm": 2.1039462089538574, | |
| "learning_rate": 3.8636363636363636e-05, | |
| "loss": 1.2715, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.993103448275862, | |
| "eval_loss": 0.751362681388855, | |
| "eval_runtime": 18.2628, | |
| "eval_samples_per_second": 1.095, | |
| "eval_steps_per_second": 0.548, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.006896551724138, | |
| "grad_norm": 2.1415343284606934, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 1.3012, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.006896551724138, | |
| "eval_loss": 0.7407116293907166, | |
| "eval_runtime": 18.1993, | |
| "eval_samples_per_second": 1.099, | |
| "eval_steps_per_second": 0.549, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.0206896551724138, | |
| "grad_norm": 1.9539107084274292, | |
| "learning_rate": 4.318181818181819e-05, | |
| "loss": 1.1411, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.0206896551724138, | |
| "eval_loss": 0.7367935180664062, | |
| "eval_runtime": 18.2237, | |
| "eval_samples_per_second": 1.097, | |
| "eval_steps_per_second": 0.549, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 2.0641109943389893, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 1.0793, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "eval_loss": 0.7307212948799133, | |
| "eval_runtime": 18.5348, | |
| "eval_samples_per_second": 1.079, | |
| "eval_steps_per_second": 0.54, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0482758620689656, | |
| "grad_norm": 1.918042778968811, | |
| "learning_rate": 4.772727272727273e-05, | |
| "loss": 1.0897, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.0482758620689656, | |
| "eval_loss": 0.7253277897834778, | |
| "eval_runtime": 18.4554, | |
| "eval_samples_per_second": 1.084, | |
| "eval_steps_per_second": 0.542, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.0620689655172413, | |
| "grad_norm": 2.216691493988037, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2309, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0620689655172413, | |
| "eval_loss": 0.7224608659744263, | |
| "eval_runtime": 18.0728, | |
| "eval_samples_per_second": 1.107, | |
| "eval_steps_per_second": 0.553, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0758620689655172, | |
| "grad_norm": 2.304621934890747, | |
| "learning_rate": 4.999672209164081e-05, | |
| "loss": 1.1722, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0758620689655172, | |
| "eval_loss": 0.7266848683357239, | |
| "eval_runtime": 18.2053, | |
| "eval_samples_per_second": 1.099, | |
| "eval_steps_per_second": 0.549, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.089655172413793, | |
| "grad_norm": 2.0087103843688965, | |
| "learning_rate": 4.998688922613788e-05, | |
| "loss": 1.105, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.089655172413793, | |
| "eval_loss": 0.7276325225830078, | |
| "eval_runtime": 18.0661, | |
| "eval_samples_per_second": 1.107, | |
| "eval_steps_per_second": 0.554, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 2.047912836074829, | |
| "learning_rate": 4.997050398198977e-05, | |
| "loss": 1.0507, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "eval_loss": 0.7239590883255005, | |
| "eval_runtime": 18.4343, | |
| "eval_samples_per_second": 1.085, | |
| "eval_steps_per_second": 0.542, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1172413793103448, | |
| "grad_norm": 2.004422664642334, | |
| "learning_rate": 4.9947570655942796e-05, | |
| "loss": 0.9516, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.1172413793103448, | |
| "eval_loss": 0.7144821882247925, | |
| "eval_runtime": 18.3983, | |
| "eval_samples_per_second": 1.087, | |
| "eval_steps_per_second": 0.544, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.1310344827586207, | |
| "grad_norm": 2.013328790664673, | |
| "learning_rate": 4.991809526186424e-05, | |
| "loss": 1.0593, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.1310344827586207, | |
| "eval_loss": 0.7059406638145447, | |
| "eval_runtime": 18.2362, | |
| "eval_samples_per_second": 1.097, | |
| "eval_steps_per_second": 0.548, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.1448275862068966, | |
| "grad_norm": 2.068134069442749, | |
| "learning_rate": 4.988208552916535e-05, | |
| "loss": 1.1188, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.1448275862068966, | |
| "eval_loss": 0.7021835446357727, | |
| "eval_runtime": 18.1868, | |
| "eval_samples_per_second": 1.1, | |
| "eval_steps_per_second": 0.55, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.1586206896551725, | |
| "grad_norm": 2.2628672122955322, | |
| "learning_rate": 4.983955090077444e-05, | |
| "loss": 1.1473, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.1586206896551725, | |
| "eval_loss": 0.6942790150642395, | |
| "eval_runtime": 18.1494, | |
| "eval_samples_per_second": 1.102, | |
| "eval_steps_per_second": 0.551, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "grad_norm": 2.1747775077819824, | |
| "learning_rate": 4.9790502530660635e-05, | |
| "loss": 1.1778, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "eval_loss": 0.6942981481552124, | |
| "eval_runtime": 18.8763, | |
| "eval_samples_per_second": 1.06, | |
| "eval_steps_per_second": 0.53, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.186206896551724, | |
| "grad_norm": 2.152348041534424, | |
| "learning_rate": 4.9734953280908904e-05, | |
| "loss": 1.331, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.186206896551724, | |
| "eval_loss": 0.6978840827941895, | |
| "eval_runtime": 18.349, | |
| "eval_samples_per_second": 1.09, | |
| "eval_steps_per_second": 0.545, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.069314956665039, | |
| "learning_rate": 4.967291771834727e-05, | |
| "loss": 1.1638, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.6983293294906616, | |
| "eval_runtime": 18.1961, | |
| "eval_samples_per_second": 1.099, | |
| "eval_steps_per_second": 0.55, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.2137931034482758, | |
| "grad_norm": 2.037853717803955, | |
| "learning_rate": 4.960441211072686e-05, | |
| "loss": 1.1118, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.2137931034482758, | |
| "eval_loss": 0.6962876915931702, | |
| "eval_runtime": 18.1105, | |
| "eval_samples_per_second": 1.104, | |
| "eval_steps_per_second": 0.552, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.2275862068965517, | |
| "grad_norm": 1.9961076974868774, | |
| "learning_rate": 4.9529454422455976e-05, | |
| "loss": 1.0972, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.2275862068965517, | |
| "eval_loss": 0.6896785497665405, | |
| "eval_runtime": 18.0553, | |
| "eval_samples_per_second": 1.108, | |
| "eval_steps_per_second": 0.554, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "grad_norm": 2.28176212310791, | |
| "learning_rate": 4.944806430988927e-05, | |
| "loss": 1.3304, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "eval_loss": 0.6826642751693726, | |
| "eval_runtime": 18.5055, | |
| "eval_samples_per_second": 1.081, | |
| "eval_steps_per_second": 0.54, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2551724137931035, | |
| "grad_norm": 1.894646406173706, | |
| "learning_rate": 4.936026311617316e-05, | |
| "loss": 1.0935, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.2551724137931035, | |
| "eval_loss": 0.678307831287384, | |
| "eval_runtime": 18.3532, | |
| "eval_samples_per_second": 1.09, | |
| "eval_steps_per_second": 0.545, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.2689655172413792, | |
| "grad_norm": 2.0475075244903564, | |
| "learning_rate": 4.926607386564898e-05, | |
| "loss": 1.2393, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.2689655172413792, | |
| "eval_loss": 0.6765857934951782, | |
| "eval_runtime": 18.2689, | |
| "eval_samples_per_second": 1.095, | |
| "eval_steps_per_second": 0.547, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.282758620689655, | |
| "grad_norm": 2.140949249267578, | |
| "learning_rate": 4.916552125781528e-05, | |
| "loss": 1.0277, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.282758620689655, | |
| "eval_loss": 0.6735562682151794, | |
| "eval_runtime": 18.1407, | |
| "eval_samples_per_second": 1.102, | |
| "eval_steps_per_second": 0.551, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.296551724137931, | |
| "grad_norm": 2.235147476196289, | |
| "learning_rate": 4.9058631660850765e-05, | |
| "loss": 1.2081, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.296551724137931, | |
| "eval_loss": 0.6619122624397278, | |
| "eval_runtime": 18.2145, | |
| "eval_samples_per_second": 1.098, | |
| "eval_steps_per_second": 0.549, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "grad_norm": 2.077143669128418, | |
| "learning_rate": 4.894543310469968e-05, | |
| "loss": 1.2378, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "eval_loss": 0.6547893285751343, | |
| "eval_runtime": 18.7488, | |
| "eval_samples_per_second": 1.067, | |
| "eval_steps_per_second": 0.533, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.3241379310344827, | |
| "grad_norm": 1.9517972469329834, | |
| "learning_rate": 4.882595527372152e-05, | |
| "loss": 1.0997, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.3241379310344827, | |
| "eval_loss": 0.6498640775680542, | |
| "eval_runtime": 18.4304, | |
| "eval_samples_per_second": 1.085, | |
| "eval_steps_per_second": 0.543, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.3379310344827586, | |
| "grad_norm": 2.0447959899902344, | |
| "learning_rate": 4.870022949890676e-05, | |
| "loss": 0.9613, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.3379310344827586, | |
| "eval_loss": 0.6370054483413696, | |
| "eval_runtime": 18.252, | |
| "eval_samples_per_second": 1.096, | |
| "eval_steps_per_second": 0.548, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.3517241379310345, | |
| "grad_norm": 2.078657865524292, | |
| "learning_rate": 4.856828874966086e-05, | |
| "loss": 1.1216, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.3517241379310345, | |
| "eval_loss": 0.6291982531547546, | |
| "eval_runtime": 18.2386, | |
| "eval_samples_per_second": 1.097, | |
| "eval_steps_per_second": 0.548, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.3655172413793104, | |
| "grad_norm": 2.0556623935699463, | |
| "learning_rate": 4.8430167625158595e-05, | |
| "loss": 1.0718, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.3655172413793104, | |
| "eval_loss": 0.6218433380126953, | |
| "eval_runtime": 18.1671, | |
| "eval_samples_per_second": 1.101, | |
| "eval_steps_per_second": 0.55, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 2.0707523822784424, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 1.2557, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.6193124055862427, | |
| "eval_runtime": 15.3335, | |
| "eval_samples_per_second": 1.304, | |
| "eval_steps_per_second": 0.652, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.4137931034482758, | |
| "grad_norm": 2.099379539489746, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.1953, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.4137931034482758, | |
| "eval_loss": 0.6185603141784668, | |
| "eval_runtime": 15.3458, | |
| "eval_samples_per_second": 1.303, | |
| "eval_steps_per_second": 0.652, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.4275862068965517, | |
| "grad_norm": 1.9917728900909424, | |
| "learning_rate": 6.818181818181818e-06, | |
| "loss": 1.2443, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.4275862068965517, | |
| "eval_loss": 0.6176949739456177, | |
| "eval_runtime": 15.2437, | |
| "eval_samples_per_second": 1.312, | |
| "eval_steps_per_second": 0.656, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.4413793103448276, | |
| "grad_norm": 1.8723604679107666, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.0864, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.4413793103448276, | |
| "eval_loss": 0.6164005994796753, | |
| "eval_runtime": 15.2753, | |
| "eval_samples_per_second": 1.309, | |
| "eval_steps_per_second": 0.655, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.4551724137931035, | |
| "grad_norm": 1.98838472366333, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 1.2297, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.4551724137931035, | |
| "eval_loss": 0.6155186891555786, | |
| "eval_runtime": 15.2373, | |
| "eval_samples_per_second": 1.313, | |
| "eval_steps_per_second": 0.656, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.4689655172413794, | |
| "grad_norm": 1.8609561920166016, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 0.9922, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.4689655172413794, | |
| "eval_loss": 0.6143234372138977, | |
| "eval_runtime": 15.4977, | |
| "eval_samples_per_second": 1.291, | |
| "eval_steps_per_second": 0.645, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.4827586206896552, | |
| "grad_norm": 2.010931968688965, | |
| "learning_rate": 1.590909090909091e-05, | |
| "loss": 1.1338, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.4827586206896552, | |
| "eval_loss": 0.610894501209259, | |
| "eval_runtime": 15.4008, | |
| "eval_samples_per_second": 1.299, | |
| "eval_steps_per_second": 0.649, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.4965517241379311, | |
| "grad_norm": 1.9721729755401611, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.0459, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.4965517241379311, | |
| "eval_loss": 0.606325089931488, | |
| "eval_runtime": 15.2962, | |
| "eval_samples_per_second": 1.308, | |
| "eval_steps_per_second": 0.654, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.510344827586207, | |
| "grad_norm": 2.1253089904785156, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 1.285, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.510344827586207, | |
| "eval_loss": 0.6013532876968384, | |
| "eval_runtime": 15.3278, | |
| "eval_samples_per_second": 1.305, | |
| "eval_steps_per_second": 0.652, | |
| "step": 109 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 216, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3916678204158771e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |