| { | |
| "best_metric": 2.269778251647949, | |
| "best_model_checkpoint": "../../saves/Qwen1.5-7B-Chat/lora/sft/checkpoint-1200", | |
| "epoch": 7.111111111111111, | |
| "eval_steps": 400, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 2.701119899749756, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.3102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 3.890558958053589, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8998, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.3287036418914795, | |
| "learning_rate": 4.999552306674344e-05, | |
| "loss": 3.241, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.6666322946548462, | |
| "learning_rate": 4.998209387040829e-05, | |
| "loss": 2.677, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.6145800352096558, | |
| "learning_rate": 4.9959717220723784e-05, | |
| "loss": 2.6172, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.5234311819076538, | |
| "learning_rate": 4.9928401131991305e-05, | |
| "loss": 2.5621, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.6433086395263672, | |
| "learning_rate": 4.9888156820213974e-05, | |
| "loss": 2.587, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.5955637693405151, | |
| "learning_rate": 4.9838998699079625e-05, | |
| "loss": 2.6315, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.5844753980636597, | |
| "learning_rate": 4.9780944374798435e-05, | |
| "loss": 2.5056, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.6106901168823242, | |
| "learning_rate": 4.971401463979721e-05, | |
| "loss": 2.5099, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.7099446654319763, | |
| "learning_rate": 4.963823346527248e-05, | |
| "loss": 2.4891, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.6092314720153809, | |
| "learning_rate": 4.9553627992605066e-05, | |
| "loss": 2.546, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.5691718459129333, | |
| "learning_rate": 4.946022852363932e-05, | |
| "loss": 2.4562, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.7633320689201355, | |
| "learning_rate": 4.9358068509830334e-05, | |
| "loss": 2.5554, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.7102218866348267, | |
| "learning_rate": 4.924718454026318e-05, | |
| "loss": 2.5479, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.7560188174247742, | |
| "learning_rate": 4.912761632854833e-05, | |
| "loss": 2.4747, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.6717157959938049, | |
| "learning_rate": 4.8999406698598074e-05, | |
| "loss": 2.5173, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.6935433745384216, | |
| "learning_rate": 4.886260156928888e-05, | |
| "loss": 2.4288, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 1.0115560293197632, | |
| "learning_rate": 4.8717249938015415e-05, | |
| "loss": 2.5331, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.7541220784187317, | |
| "learning_rate": 4.856340386314182e-05, | |
| "loss": 2.4577, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.8513575196266174, | |
| "learning_rate": 4.840111844535682e-05, | |
| "loss": 2.496, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.7479698061943054, | |
| "learning_rate": 4.8230451807939135e-05, | |
| "loss": 2.4142, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.7310675978660583, | |
| "learning_rate": 4.8051465075940336e-05, | |
| "loss": 2.4913, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.8907930850982666, | |
| "learning_rate": 4.786422235429269e-05, | |
| "loss": 2.3697, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.9348196387290955, | |
| "learning_rate": 4.766879070484956e-05, | |
| "loss": 2.4631, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.9181344509124756, | |
| "learning_rate": 4.746524012236706e-05, | |
| "loss": 2.4411, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.7747082710266113, | |
| "learning_rate": 4.725364350943492e-05, | |
| "loss": 2.3592, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.9620688557624817, | |
| "learning_rate": 4.703407665036622e-05, | |
| "loss": 2.3433, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 1.016157865524292, | |
| "learning_rate": 4.680661818405485e-05, | |
| "loss": 2.3396, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.8236090540885925, | |
| "learning_rate": 4.657134957581057e-05, | |
| "loss": 2.3637, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.9651027321815491, | |
| "learning_rate": 4.6328355088181915e-05, | |
| "loss": 2.3831, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.7949943542480469, | |
| "learning_rate": 4.607772175077711e-05, | |
| "loss": 2.4422, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.9031904935836792, | |
| "learning_rate": 4.581953932909403e-05, | |
| "loss": 2.4595, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 0.859309732913971, | |
| "learning_rate": 4.555390029237026e-05, | |
| "loss": 2.3967, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 1.1613001823425293, | |
| "learning_rate": 4.528089978046481e-05, | |
| "loss": 2.3132, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 0.9616575837135315, | |
| "learning_rate": 4.500063556978337e-05, | |
| "loss": 2.4425, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 0.7751485109329224, | |
| "learning_rate": 4.471320803825915e-05, | |
| "loss": 2.3591, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 1.3079149723052979, | |
| "learning_rate": 4.441872012940214e-05, | |
| "loss": 2.3323, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 0.8369519710540771, | |
| "learning_rate": 4.4117277315429366e-05, | |
| "loss": 2.5005, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 1.0954837799072266, | |
| "learning_rate": 4.380898755948953e-05, | |
| "loss": 2.3058, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 2.299175500869751, | |
| "eval_runtime": 74.4017, | |
| "eval_samples_per_second": 8.064, | |
| "eval_steps_per_second": 4.032, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 1.0771162509918213, | |
| "learning_rate": 4.349396127699552e-05, | |
| "loss": 2.4145, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 0.7209674119949341, | |
| "learning_rate": 4.3172311296078595e-05, | |
| "loss": 2.3519, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 1.0076887607574463, | |
| "learning_rate": 4.284415281717847e-05, | |
| "loss": 2.3699, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 0.9578609466552734, | |
| "learning_rate": 4.250960337178377e-05, | |
| "loss": 2.3923, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 0.9023878574371338, | |
| "learning_rate": 4.216878278033753e-05, | |
| "loss": 2.3618, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 1.1171501874923706, | |
| "learning_rate": 4.1821813109322974e-05, | |
| "loss": 2.4161, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 1.2200597524642944, | |
| "learning_rate": 4.1468818627544845e-05, | |
| "loss": 2.3592, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 0.9814207553863525, | |
| "learning_rate": 4.1109925761621925e-05, | |
| "loss": 2.4143, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 1.2403128147125244, | |
| "learning_rate": 4.0745263050706784e-05, | |
| "loss": 2.3558, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.9680503606796265, | |
| "learning_rate": 4.037496110044884e-05, | |
| "loss": 2.3103, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 0.9476011991500854, | |
| "learning_rate": 3.999915253621739e-05, | |
| "loss": 2.369, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 0.9985129237174988, | |
| "learning_rate": 3.961797195560118e-05, | |
| "loss": 2.2797, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "grad_norm": 1.1295677423477173, | |
| "learning_rate": 3.9231555880201655e-05, | |
| "loss": 2.3331, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.854465126991272, | |
| "learning_rate": 3.8840042706737114e-05, | |
| "loss": 2.2353, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "grad_norm": 0.9416671991348267, | |
| "learning_rate": 3.8443572657475304e-05, | |
| "loss": 2.285, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 1.1753567457199097, | |
| "learning_rate": 3.804228773001212e-05, | |
| "loss": 2.3359, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "grad_norm": 1.0389409065246582, | |
| "learning_rate": 3.7636331646414524e-05, | |
| "loss": 2.3567, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 1.197994589805603, | |
| "learning_rate": 3.7225849801745835e-05, | |
| "loss": 2.3137, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 1.1205960512161255, | |
| "learning_rate": 3.6810989211991774e-05, | |
| "loss": 2.3268, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "grad_norm": 1.1302969455718994, | |
| "learning_rate": 3.639189846140604e-05, | |
| "loss": 2.4254, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "grad_norm": 1.1475387811660767, | |
| "learning_rate": 3.596872764929413e-05, | |
| "loss": 2.3282, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "grad_norm": 1.2079755067825317, | |
| "learning_rate": 3.55416283362546e-05, | |
| "loss": 2.2859, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "grad_norm": 1.274043321609497, | |
| "learning_rate": 3.511075348989692e-05, | |
| "loss": 2.3619, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "grad_norm": 1.3108967542648315, | |
| "learning_rate": 3.4676257430055434e-05, | |
| "loss": 2.202, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "grad_norm": 1.1571152210235596, | |
| "learning_rate": 3.4238295773518924e-05, | |
| "loss": 2.3114, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "grad_norm": 1.2922154664993286, | |
| "learning_rate": 3.379702537829583e-05, | |
| "loss": 2.3175, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "grad_norm": 0.8678541779518127, | |
| "learning_rate": 3.335260428743475e-05, | |
| "loss": 2.4348, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "grad_norm": 1.2109763622283936, | |
| "learning_rate": 3.29051916724206e-05, | |
| "loss": 2.3685, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "grad_norm": 1.21372389793396, | |
| "learning_rate": 3.2454947776166636e-05, | |
| "loss": 2.1795, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "grad_norm": 1.2954655885696411, | |
| "learning_rate": 3.200203385562268e-05, | |
| "loss": 2.2299, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "grad_norm": 1.4054641723632812, | |
| "learning_rate": 3.154661212402017e-05, | |
| "loss": 2.3114, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "grad_norm": 1.2466893196105957, | |
| "learning_rate": 3.10888456927748e-05, | |
| "loss": 2.2702, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "grad_norm": 1.0978355407714844, | |
| "learning_rate": 3.0628898513067353e-05, | |
| "loss": 2.2537, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "grad_norm": 1.3766223192214966, | |
| "learning_rate": 3.0166935317123823e-05, | |
| "loss": 2.3131, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "grad_norm": 1.152358889579773, | |
| "learning_rate": 2.9703121559215845e-05, | |
| "loss": 2.38, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 1.3584524393081665, | |
| "learning_rate": 2.923762335640242e-05, | |
| "loss": 2.3432, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "grad_norm": 1.3569154739379883, | |
| "learning_rate": 2.8770607429034352e-05, | |
| "loss": 2.2632, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "grad_norm": 1.4426939487457275, | |
| "learning_rate": 2.8302241041042565e-05, | |
| "loss": 2.2501, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "grad_norm": 1.2213878631591797, | |
| "learning_rate": 2.783269194003175e-05, | |
| "loss": 2.3787, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "grad_norm": 1.5808135271072388, | |
| "learning_rate": 2.7362128297200785e-05, | |
| "loss": 2.3647, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_loss": 2.2738687992095947, | |
| "eval_runtime": 80.6321, | |
| "eval_samples_per_second": 7.441, | |
| "eval_steps_per_second": 3.721, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 1.2698041200637817, | |
| "learning_rate": 2.6890718647111422e-05, | |
| "loss": 2.2942, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "grad_norm": 1.2770848274230957, | |
| "learning_rate": 2.6418631827326857e-05, | |
| "loss": 2.347, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "grad_norm": 1.2166974544525146, | |
| "learning_rate": 2.5946036917941762e-05, | |
| "loss": 2.2969, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "grad_norm": 1.4275230169296265, | |
| "learning_rate": 2.5473103181025476e-05, | |
| "loss": 2.2556, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "grad_norm": 1.2852686643600464, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.2781, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "grad_norm": 1.6887468099594116, | |
| "learning_rate": 2.4526896818974533e-05, | |
| "loss": 2.2843, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "grad_norm": 1.328687310218811, | |
| "learning_rate": 2.4053963082058244e-05, | |
| "loss": 2.229, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "grad_norm": 1.3591057062149048, | |
| "learning_rate": 2.3581368172673152e-05, | |
| "loss": 2.2851, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "grad_norm": 1.3400282859802246, | |
| "learning_rate": 2.310928135288859e-05, | |
| "loss": 2.18, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "grad_norm": 1.3457157611846924, | |
| "learning_rate": 2.263787170279922e-05, | |
| "loss": 2.2501, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "grad_norm": 1.5690137147903442, | |
| "learning_rate": 2.2167308059968254e-05, | |
| "loss": 2.2682, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "grad_norm": 1.429304599761963, | |
| "learning_rate": 2.1697758958957448e-05, | |
| "loss": 2.3144, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "grad_norm": 1.4117275476455688, | |
| "learning_rate": 2.1229392570965657e-05, | |
| "loss": 2.2955, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "grad_norm": 1.7679541110992432, | |
| "learning_rate": 2.0762376643597582e-05, | |
| "loss": 2.2117, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "grad_norm": 1.4710173606872559, | |
| "learning_rate": 2.029687844078416e-05, | |
| "loss": 2.3107, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "grad_norm": 1.2774254083633423, | |
| "learning_rate": 1.9833064682876176e-05, | |
| "loss": 2.2242, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "grad_norm": 1.5879724025726318, | |
| "learning_rate": 1.937110148693265e-05, | |
| "loss": 2.2299, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "grad_norm": 1.3109989166259766, | |
| "learning_rate": 1.8911154307225203e-05, | |
| "loss": 2.3555, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "grad_norm": 1.6713744401931763, | |
| "learning_rate": 1.8453387875979834e-05, | |
| "loss": 2.2603, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "grad_norm": 1.6011615991592407, | |
| "learning_rate": 1.7997966144377325e-05, | |
| "loss": 2.2731, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "grad_norm": 1.4683603048324585, | |
| "learning_rate": 1.754505222383337e-05, | |
| "loss": 2.2876, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "grad_norm": 1.3678452968597412, | |
| "learning_rate": 1.70948083275794e-05, | |
| "loss": 2.3123, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "grad_norm": 1.4179573059082031, | |
| "learning_rate": 1.6647395712565256e-05, | |
| "loss": 2.1601, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "grad_norm": 1.4710493087768555, | |
| "learning_rate": 1.6202974621704175e-05, | |
| "loss": 2.1918, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "grad_norm": 1.5775597095489502, | |
| "learning_rate": 1.576170422648108e-05, | |
| "loss": 2.3438, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "grad_norm": 1.7641725540161133, | |
| "learning_rate": 1.5323742569944572e-05, | |
| "loss": 2.1773, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "grad_norm": 1.5010628700256348, | |
| "learning_rate": 1.4889246510103077e-05, | |
| "loss": 2.2014, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 1.5155980587005615, | |
| "learning_rate": 1.4458371663745401e-05, | |
| "loss": 2.2616, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "grad_norm": 1.337975025177002, | |
| "learning_rate": 1.4031272350705871e-05, | |
| "loss": 2.2648, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "grad_norm": 1.788812518119812, | |
| "learning_rate": 1.3608101538593965e-05, | |
| "loss": 2.2841, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "grad_norm": 1.6673487424850464, | |
| "learning_rate": 1.3189010788008233e-05, | |
| "loss": 2.3188, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "grad_norm": 1.4954336881637573, | |
| "learning_rate": 1.277415019825417e-05, | |
| "loss": 2.2268, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "grad_norm": 1.5983794927597046, | |
| "learning_rate": 1.2363668353585487e-05, | |
| "loss": 2.2214, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "grad_norm": 1.6327165365219116, | |
| "learning_rate": 1.195771226998789e-05, | |
| "loss": 2.2109, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "grad_norm": 1.7117351293563843, | |
| "learning_rate": 1.1556427342524698e-05, | |
| "loss": 2.3153, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "grad_norm": 1.8630892038345337, | |
| "learning_rate": 1.1159957293262888e-05, | |
| "loss": 2.216, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "grad_norm": 1.6396968364715576, | |
| "learning_rate": 1.0768444119798357e-05, | |
| "loss": 2.2552, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "grad_norm": 1.5091443061828613, | |
| "learning_rate": 1.0382028044398822e-05, | |
| "loss": 2.2435, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "grad_norm": 1.4590834379196167, | |
| "learning_rate": 1.0000847463782615e-05, | |
| "loss": 2.2492, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "grad_norm": 1.8363531827926636, | |
| "learning_rate": 9.625038899551161e-06, | |
| "loss": 2.1918, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 2.269778251647949, | |
| "eval_runtime": 74.1482, | |
| "eval_samples_per_second": 8.092, | |
| "eval_steps_per_second": 4.046, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1680, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 400, | |
| "total_flos": 1.1235201502895145e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |