| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9946777054997042, | |
| "eval_steps": 500, | |
| "global_step": 1266, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02365464222353637, | |
| "grad_norm": 1.5665423397587683, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8891, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04730928444707274, | |
| "grad_norm": 1.0589767378232773, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0709639266706091, | |
| "grad_norm": 0.8838983419870171, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7599, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09461856889414548, | |
| "grad_norm": 0.9501620192903069, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7391, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11827321111768184, | |
| "grad_norm": 0.7634636002964827, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7272, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1419278533412182, | |
| "grad_norm": 0.6753406016779676, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7159, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16558249556475457, | |
| "grad_norm": 0.6614325908691252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7118, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18923713778829096, | |
| "grad_norm": 0.7719184686061289, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7019, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21289178001182732, | |
| "grad_norm": 0.7524231413666251, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6872, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23654642223536368, | |
| "grad_norm": 0.8110229180711027, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6853, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26020106445890007, | |
| "grad_norm": 0.4971482406443161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6909, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2838557066824364, | |
| "grad_norm": 0.9464051864732146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6782, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3075103489059728, | |
| "grad_norm": 0.5071907565316945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6744, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33116499112950915, | |
| "grad_norm": 0.9224817650868851, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6828, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35481963335304556, | |
| "grad_norm": 0.8885554899363501, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6661, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3784742755765819, | |
| "grad_norm": 0.4781037463107871, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6701, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4021289178001183, | |
| "grad_norm": 0.6023227514998295, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6677, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42578356002365464, | |
| "grad_norm": 0.5603961021476538, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6742, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 0.4984868681428728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6711, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47309284447072736, | |
| "grad_norm": 0.6312594557804502, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6689, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4967474866942638, | |
| "grad_norm": 0.9550758404721197, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6707, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5204021289178001, | |
| "grad_norm": 0.6169594889049308, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6699, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5440567711413364, | |
| "grad_norm": 0.46636130254439206, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6615, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5677114133648729, | |
| "grad_norm": 0.5215033819505257, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6657, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5913660555884093, | |
| "grad_norm": 0.5111456784576656, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6633, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6150206978119456, | |
| "grad_norm": 0.517604760100503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6531, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.638675340035482, | |
| "grad_norm": 0.6357411311158894, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6652, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6623299822590183, | |
| "grad_norm": 0.6476086780436829, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6676, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6859846244825547, | |
| "grad_norm": 0.46209126279187906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6601, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7096392667060911, | |
| "grad_norm": 0.521950153282793, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6554, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7332939089296274, | |
| "grad_norm": 0.47211201942387604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6617, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7569485511531638, | |
| "grad_norm": 0.5341122235375386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6563, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7806031933767001, | |
| "grad_norm": 0.5708931772664904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.654, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8042578356002366, | |
| "grad_norm": 0.6195560307499095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6543, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8279124778237729, | |
| "grad_norm": 0.5625110791293699, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6621, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8515671200473093, | |
| "grad_norm": 0.4510061091403496, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6546, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8752217622708457, | |
| "grad_norm": 0.46670984016010486, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6576, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 0.5044563574335732, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6489, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9225310467179184, | |
| "grad_norm": 0.6276485740632245, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6548, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9461856889414547, | |
| "grad_norm": 0.4849232290323015, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6473, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9698403311649911, | |
| "grad_norm": 0.47066212467927304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6504, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9934949733885275, | |
| "grad_norm": 0.5498376915549745, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6489, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9982259018332348, | |
| "eval_loss": 0.6508141756057739, | |
| "eval_runtime": 226.6795, | |
| "eval_samples_per_second": 50.243, | |
| "eval_steps_per_second": 0.393, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.0171496156120639, | |
| "grad_norm": 0.5216981625298186, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6225, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0408042578356003, | |
| "grad_norm": 0.5287278292361843, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6077, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0644589000591367, | |
| "grad_norm": 0.7304842680236713, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6058, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0881135422826729, | |
| "grad_norm": 0.5644902109246774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6138, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1117681845062093, | |
| "grad_norm": 0.4753652134651053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6129, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1354228267297457, | |
| "grad_norm": 0.7165345582019033, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6125, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1590774689532821, | |
| "grad_norm": 0.4641812019487026, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6106, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1827321111768185, | |
| "grad_norm": 0.4846409340358244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6065, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2063867534003547, | |
| "grad_norm": 0.5624538054911821, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6058, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2300413956238911, | |
| "grad_norm": 0.5069531857984526, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6114, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2536960378474276, | |
| "grad_norm": 0.5605749208808489, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6117, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.277350680070964, | |
| "grad_norm": 0.5081677690669225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6133, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3010053222945004, | |
| "grad_norm": 0.5493923133675747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6101, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3246599645180366, | |
| "grad_norm": 0.44898345952125707, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6096, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.348314606741573, | |
| "grad_norm": 0.6655768726116028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6094, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3719692489651094, | |
| "grad_norm": 0.4649052455972333, | |
| "learning_rate": 5e-06, | |
| "loss": 0.614, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3956238911886458, | |
| "grad_norm": 0.43539888089438844, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6138, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4192785334121822, | |
| "grad_norm": 0.5826398325628406, | |
| "learning_rate": 5e-06, | |
| "loss": 0.601, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4429331756357184, | |
| "grad_norm": 0.4128719638682357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4665878178592548, | |
| "grad_norm": 0.45529767094349805, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6052, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4902424600827913, | |
| "grad_norm": 0.4330632579708222, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6156, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5138971023063275, | |
| "grad_norm": 0.44938881612128456, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6152, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.537551744529864, | |
| "grad_norm": 0.46628155511438146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6041, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5612063867534003, | |
| "grad_norm": 0.5843372770531808, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6091, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5848610289769367, | |
| "grad_norm": 0.5865805864061058, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6085156712004731, | |
| "grad_norm": 0.6180152508932449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6098, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6321703134240093, | |
| "grad_norm": 0.5250880775614019, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6035, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.655824955647546, | |
| "grad_norm": 0.478978441549023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6107, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6794795978710821, | |
| "grad_norm": 0.5161048108398052, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6106, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.7031342400946186, | |
| "grad_norm": 0.5444636992966723, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6123, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.726788882318155, | |
| "grad_norm": 0.49014325863511293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6131, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7504435245416912, | |
| "grad_norm": 0.6313993012312799, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6059, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7740981667652278, | |
| "grad_norm": 0.5158091820023666, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6116, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 0.47029237511942096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.617, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8214074512123004, | |
| "grad_norm": 0.4280088668307211, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6167, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8450620934358368, | |
| "grad_norm": 0.42280798454326274, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6094, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.868716735659373, | |
| "grad_norm": 0.5015010241124669, | |
| "learning_rate": 5e-06, | |
| "loss": 0.606, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8923713778829097, | |
| "grad_norm": 0.4647527250682549, | |
| "learning_rate": 5e-06, | |
| "loss": 0.614, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9160260201064458, | |
| "grad_norm": 0.45335597096154956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6142, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.9396806623299823, | |
| "grad_norm": 0.4377674877634198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6009, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.9633353045535187, | |
| "grad_norm": 0.4922578419992401, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6108, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9869899467770549, | |
| "grad_norm": 0.4440378004846697, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5988, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9988172678888232, | |
| "eval_loss": 0.6402984857559204, | |
| "eval_runtime": 227.8867, | |
| "eval_samples_per_second": 49.977, | |
| "eval_steps_per_second": 0.391, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 2.0106445890005915, | |
| "grad_norm": 0.6249254373352294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5864, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0342992312241277, | |
| "grad_norm": 0.5229366411844095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5668, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.057953873447664, | |
| "grad_norm": 0.5273129182521392, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.0816085156712005, | |
| "grad_norm": 0.5807006714823286, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5605, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.5316074498783832, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5644, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.1289178001182734, | |
| "grad_norm": 0.571954438502547, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1525724423418096, | |
| "grad_norm": 0.4503797360191138, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5625, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1762270845653457, | |
| "grad_norm": 0.49334190713186854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5648, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1998817267888824, | |
| "grad_norm": 0.5335672716582398, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5647, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2235363690124186, | |
| "grad_norm": 0.5933317390318844, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5662, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 0.5891028799938252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5716, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.2708456534594914, | |
| "grad_norm": 0.5459106423210626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5651, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.2945002956830276, | |
| "grad_norm": 0.5290952299819603, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3181549379065642, | |
| "grad_norm": 0.612560828315047, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5695, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3418095801301004, | |
| "grad_norm": 0.4941237525745503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.365464222353637, | |
| "grad_norm": 0.5650925849128444, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3891188645771733, | |
| "grad_norm": 0.4960493342953518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4127735068007095, | |
| "grad_norm": 0.5675556976300212, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.436428149024246, | |
| "grad_norm": 0.4679420975237042, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5658, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4600827912477823, | |
| "grad_norm": 0.5934681961848346, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.483737433471319, | |
| "grad_norm": 0.4994164056392902, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5705, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.507392075694855, | |
| "grad_norm": 0.553203563454583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5692, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5310467179183913, | |
| "grad_norm": 0.4828644604519897, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5741, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.554701360141928, | |
| "grad_norm": 0.49982783159481065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5729, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.578356002365464, | |
| "grad_norm": 0.5028480314612812, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6020106445890008, | |
| "grad_norm": 0.47037814252850013, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5693, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.625665286812537, | |
| "grad_norm": 0.5106941109306207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.649319929036073, | |
| "grad_norm": 0.6215547951000225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5792, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.67297457125961, | |
| "grad_norm": 0.5708225359288293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5667, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "grad_norm": 0.4694908632163934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5666, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7202838557066826, | |
| "grad_norm": 0.5487886870493401, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.743938497930219, | |
| "grad_norm": 0.5178726800202738, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.767593140153755, | |
| "grad_norm": 0.572400968003655, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.7912477823772917, | |
| "grad_norm": 0.4505102109858482, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.814902424600828, | |
| "grad_norm": 0.4721423964551259, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5711, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.8385570668243645, | |
| "grad_norm": 0.45313707571101325, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.8622117090479007, | |
| "grad_norm": 0.4905572612804298, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5708, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.885866351271437, | |
| "grad_norm": 0.4488283221129483, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5644, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.9095209934949735, | |
| "grad_norm": 0.5086777707270197, | |
| "learning_rate": 5e-06, | |
| "loss": 0.57, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.9331756357185097, | |
| "grad_norm": 0.5014035211864805, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5719, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.9568302779420463, | |
| "grad_norm": 0.46427442721882733, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5812, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.9804849201655825, | |
| "grad_norm": 0.4933592342573123, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5728, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.9946777054997042, | |
| "eval_loss": 0.6413019895553589, | |
| "eval_runtime": 227.2584, | |
| "eval_samples_per_second": 50.115, | |
| "eval_steps_per_second": 0.392, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 2.9946777054997042, | |
| "step": 1266, | |
| "total_flos": 2120178393415680.0, | |
| "train_loss": 0.6201754979801027, | |
| "train_runtime": 38082.1567, | |
| "train_samples_per_second": 17.045, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1266, | |
| "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": 2120178393415680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |