| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.72549019607843, | |
| "eval_steps": 31, | |
| "global_step": 310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03137254901960784, | |
| "grad_norm": 17.784626007080078, | |
| "learning_rate": 2e-05, | |
| "loss": 7.7199, | |
| "num_input_tokens_seen": 789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06274509803921569, | |
| "grad_norm": 12.485037803649902, | |
| "learning_rate": 4e-05, | |
| "loss": 5.2762, | |
| "num_input_tokens_seen": 1656, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 7.9316840171813965, | |
| "learning_rate": 6e-05, | |
| "loss": 4.3107, | |
| "num_input_tokens_seen": 2529, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12549019607843137, | |
| "grad_norm": 9.721095085144043, | |
| "learning_rate": 8e-05, | |
| "loss": 4.8054, | |
| "num_input_tokens_seen": 3389, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 8.977057456970215, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4644, | |
| "num_input_tokens_seen": 4244, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 10.086724281311035, | |
| "learning_rate": 0.00012, | |
| "loss": 5.6263, | |
| "num_input_tokens_seen": 5059, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2196078431372549, | |
| "grad_norm": 13.49176025390625, | |
| "learning_rate": 0.00014, | |
| "loss": 5.4706, | |
| "num_input_tokens_seen": 5918, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25098039215686274, | |
| "grad_norm": 11.12248706817627, | |
| "learning_rate": 0.00016, | |
| "loss": 4.4177, | |
| "num_input_tokens_seen": 6758, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 6.923247814178467, | |
| "learning_rate": 0.00018, | |
| "loss": 3.9388, | |
| "num_input_tokens_seen": 7653, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 11.242279052734375, | |
| "learning_rate": 0.0002, | |
| "loss": 4.3202, | |
| "num_input_tokens_seen": 8464, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34509803921568627, | |
| "grad_norm": 8.588418960571289, | |
| "learning_rate": 0.00019995065603657316, | |
| "loss": 3.116, | |
| "num_input_tokens_seen": 9348, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 9.73305892944336, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 2.723, | |
| "num_input_tokens_seen": 10204, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.40784313725490196, | |
| "grad_norm": 15.396673202514648, | |
| "learning_rate": 0.00019955619646030802, | |
| "loss": 2.4929, | |
| "num_input_tokens_seen": 11030, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4392156862745098, | |
| "grad_norm": 24.212421417236328, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.7489, | |
| "num_input_tokens_seen": 11845, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 14.499921798706055, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 1.8677, | |
| "num_input_tokens_seen": 12686, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5019607843137255, | |
| "grad_norm": 16.502588272094727, | |
| "learning_rate": 0.0001982287250728689, | |
| "loss": 1.3637, | |
| "num_input_tokens_seen": 13505, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 14.297043800354004, | |
| "learning_rate": 0.00019759167619387476, | |
| "loss": 1.5026, | |
| "num_input_tokens_seen": 14344, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 9.703812599182129, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 1.4165, | |
| "num_input_tokens_seen": 15218, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.596078431372549, | |
| "grad_norm": 12.656659126281738, | |
| "learning_rate": 0.0001960293685676943, | |
| "loss": 1.0906, | |
| "num_input_tokens_seen": 16040, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 58.49094772338867, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9817, | |
| "num_input_tokens_seen": 16874, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 9.382222175598145, | |
| "learning_rate": 0.00019408807689542257, | |
| "loss": 1.1198, | |
| "num_input_tokens_seen": 17682, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6901960784313725, | |
| "grad_norm": 10.244654655456543, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 1.2596, | |
| "num_input_tokens_seen": 18539, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7215686274509804, | |
| "grad_norm": 8.23478889465332, | |
| "learning_rate": 0.00019177546256839812, | |
| "loss": 1.2768, | |
| "num_input_tokens_seen": 19432, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 19.18866729736328, | |
| "learning_rate": 0.00019048270524660196, | |
| "loss": 1.3043, | |
| "num_input_tokens_seen": 20264, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 6.661506175994873, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 0.8769, | |
| "num_input_tokens_seen": 21113, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8156862745098039, | |
| "grad_norm": 6.4282546043396, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.0473, | |
| "num_input_tokens_seen": 21966, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 11.599508285522461, | |
| "learning_rate": 0.0001860742027003944, | |
| "loss": 1.0205, | |
| "num_input_tokens_seen": 22821, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8784313725490196, | |
| "grad_norm": 9.272802352905273, | |
| "learning_rate": 0.00018443279255020152, | |
| "loss": 1.2292, | |
| "num_input_tokens_seen": 23733, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9098039215686274, | |
| "grad_norm": 7.99858283996582, | |
| "learning_rate": 0.00018270805742745617, | |
| "loss": 1.1247, | |
| "num_input_tokens_seen": 24593, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 10.046642303466797, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.2097, | |
| "num_input_tokens_seen": 25425, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9725490196078431, | |
| "grad_norm": 9.499373435974121, | |
| "learning_rate": 0.00017901550123756904, | |
| "loss": 1.1345, | |
| "num_input_tokens_seen": 26228, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.003921568627451, | |
| "grad_norm": 5.625377178192139, | |
| "learning_rate": 0.00017705132427757895, | |
| "loss": 1.1178, | |
| "num_input_tokens_seen": 27085, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.035294117647059, | |
| "grad_norm": 4.716068744659424, | |
| "learning_rate": 0.00017501110696304596, | |
| "loss": 0.8997, | |
| "num_input_tokens_seen": 27917, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 4.880837440490723, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 0.654, | |
| "num_input_tokens_seen": 28796, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0980392156862746, | |
| "grad_norm": 3.4638915061950684, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7083, | |
| "num_input_tokens_seen": 29650, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1294117647058823, | |
| "grad_norm": 6.4757561683654785, | |
| "learning_rate": 0.00016845471059286887, | |
| "loss": 0.981, | |
| "num_input_tokens_seen": 30477, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1607843137254903, | |
| "grad_norm": 6.666485786437988, | |
| "learning_rate": 0.00016613118653236518, | |
| "loss": 1.1384, | |
| "num_input_tokens_seen": 31314, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.192156862745098, | |
| "grad_norm": 6.810871601104736, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.0914, | |
| "num_input_tokens_seen": 32129, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.223529411764706, | |
| "grad_norm": 4.342460632324219, | |
| "learning_rate": 0.00016129070536529766, | |
| "loss": 0.784, | |
| "num_input_tokens_seen": 32980, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2549019607843137, | |
| "grad_norm": 6.6151204109191895, | |
| "learning_rate": 0.0001587785252292473, | |
| "loss": 1.151, | |
| "num_input_tokens_seen": 33811, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2862745098039214, | |
| "grad_norm": 6.701898097991943, | |
| "learning_rate": 0.00015620833778521307, | |
| "loss": 1.1066, | |
| "num_input_tokens_seen": 34640, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3176470588235294, | |
| "grad_norm": 3.7148549556732178, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 1.1097, | |
| "num_input_tokens_seen": 35540, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3490196078431373, | |
| "grad_norm": 4.791841506958008, | |
| "learning_rate": 0.00015090414157503714, | |
| "loss": 0.9391, | |
| "num_input_tokens_seen": 36388, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.380392156862745, | |
| "grad_norm": 6.712942123413086, | |
| "learning_rate": 0.00014817536741017152, | |
| "loss": 0.8025, | |
| "num_input_tokens_seen": 37254, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 3.204245090484619, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.6842, | |
| "num_input_tokens_seen": 38098, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4431372549019608, | |
| "grad_norm": 4.535635471343994, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 0.7039, | |
| "num_input_tokens_seen": 39024, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4745098039215687, | |
| "grad_norm": 5.812551021575928, | |
| "learning_rate": 0.00013971478906347806, | |
| "loss": 1.0178, | |
| "num_input_tokens_seen": 39876, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5058823529411764, | |
| "grad_norm": 5.7899169921875, | |
| "learning_rate": 0.00013681245526846783, | |
| "loss": 0.8895, | |
| "num_input_tokens_seen": 40691, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5372549019607842, | |
| "grad_norm": 4.779058933258057, | |
| "learning_rate": 0.00013387379202452917, | |
| "loss": 0.7015, | |
| "num_input_tokens_seen": 41529, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5686274509803921, | |
| "grad_norm": 4.17733907699585, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8385, | |
| "num_input_tokens_seen": 42347, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 3.26069974899292, | |
| "learning_rate": 0.00012789911060392294, | |
| "loss": 0.6932, | |
| "num_input_tokens_seen": 43170, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.6313725490196078, | |
| "grad_norm": 3.7764294147491455, | |
| "learning_rate": 0.00012486898871648546, | |
| "loss": 0.6722, | |
| "num_input_tokens_seen": 44017, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.6627450980392156, | |
| "grad_norm": 5.631955146789551, | |
| "learning_rate": 0.00012181432413965425, | |
| "loss": 0.8225, | |
| "num_input_tokens_seen": 44895, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.6941176470588235, | |
| "grad_norm": 3.0410749912261963, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 0.5853, | |
| "num_input_tokens_seen": 45780, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.7254901960784315, | |
| "grad_norm": 6.754289627075195, | |
| "learning_rate": 0.00011564344650402312, | |
| "loss": 0.8272, | |
| "num_input_tokens_seen": 46623, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.7568627450980392, | |
| "grad_norm": 4.92588472366333, | |
| "learning_rate": 0.00011253332335643046, | |
| "loss": 0.588, | |
| "num_input_tokens_seen": 47446, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.788235294117647, | |
| "grad_norm": 5.982916831970215, | |
| "learning_rate": 0.00010941083133185143, | |
| "loss": 0.9413, | |
| "num_input_tokens_seen": 48260, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.8196078431372549, | |
| "grad_norm": 3.09069561958313, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 0.7281, | |
| "num_input_tokens_seen": 49095, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.8509803921568628, | |
| "grad_norm": 7.942086219787598, | |
| "learning_rate": 0.00010314107590781284, | |
| "loss": 0.8998, | |
| "num_input_tokens_seen": 49948, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 6.040829181671143, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7494, | |
| "num_input_tokens_seen": 50794, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.9137254901960783, | |
| "grad_norm": 5.524172782897949, | |
| "learning_rate": 9.685892409218717e-05, | |
| "loss": 1.1642, | |
| "num_input_tokens_seen": 51649, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.9450980392156862, | |
| "grad_norm": 4.093544960021973, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 0.9137, | |
| "num_input_tokens_seen": 52499, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.9764705882352942, | |
| "grad_norm": 3.3669676780700684, | |
| "learning_rate": 9.058916866814858e-05, | |
| "loss": 0.7343, | |
| "num_input_tokens_seen": 53345, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.007843137254902, | |
| "grad_norm": 6.184525966644287, | |
| "learning_rate": 8.746667664356956e-05, | |
| "loss": 0.8992, | |
| "num_input_tokens_seen": 54201, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.0392156862745097, | |
| "grad_norm": 4.793566703796387, | |
| "learning_rate": 8.435655349597695e-05, | |
| "loss": 0.6028, | |
| "num_input_tokens_seen": 55036, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.070588235294118, | |
| "grad_norm": 4.015380859375, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 0.6597, | |
| "num_input_tokens_seen": 55868, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.1019607843137256, | |
| "grad_norm": 2.2828500270843506, | |
| "learning_rate": 7.818567586034575e-05, | |
| "loss": 0.5288, | |
| "num_input_tokens_seen": 56724, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 3.3936123847961426, | |
| "learning_rate": 7.513101128351454e-05, | |
| "loss": 0.6818, | |
| "num_input_tokens_seen": 57579, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.164705882352941, | |
| "grad_norm": 3.684924602508545, | |
| "learning_rate": 7.210088939607708e-05, | |
| "loss": 0.7798, | |
| "num_input_tokens_seen": 58425, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.196078431372549, | |
| "grad_norm": 3.1493935585021973, | |
| "learning_rate": 6.909830056250524e-05, | |
| "loss": 0.7207, | |
| "num_input_tokens_seen": 59270, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.227450980392157, | |
| "grad_norm": 5.103849411010742, | |
| "learning_rate": 6.612620797547087e-05, | |
| "loss": 0.6483, | |
| "num_input_tokens_seen": 60127, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.2588235294117647, | |
| "grad_norm": 1.9273674488067627, | |
| "learning_rate": 6.318754473153221e-05, | |
| "loss": 0.5992, | |
| "num_input_tokens_seen": 61059, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.2901960784313724, | |
| "grad_norm": 2.9266533851623535, | |
| "learning_rate": 6.0285210936521955e-05, | |
| "loss": 0.6952, | |
| "num_input_tokens_seen": 61905, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.3215686274509806, | |
| "grad_norm": 2.3648922443389893, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 0.5068, | |
| "num_input_tokens_seen": 62745, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 3.8562815189361572, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.7024, | |
| "num_input_tokens_seen": 63594, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.384313725490196, | |
| "grad_norm": 2.478416919708252, | |
| "learning_rate": 5.182463258982846e-05, | |
| "loss": 0.5721, | |
| "num_input_tokens_seen": 64453, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.4156862745098038, | |
| "grad_norm": 2.117917776107788, | |
| "learning_rate": 4.909585842496292e-05, | |
| "loss": 0.4472, | |
| "num_input_tokens_seen": 65284, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.447058823529412, | |
| "grad_norm": 2.4827864170074463, | |
| "learning_rate": 4.641732050210036e-05, | |
| "loss": 0.414, | |
| "num_input_tokens_seen": 66110, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.4784313725490197, | |
| "grad_norm": 3.7768778800964355, | |
| "learning_rate": 4.3791662214786934e-05, | |
| "loss": 0.5808, | |
| "num_input_tokens_seen": 66934, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.5098039215686274, | |
| "grad_norm": 3.4247841835021973, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.5447, | |
| "num_input_tokens_seen": 67775, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.541176470588235, | |
| "grad_norm": 4.182628631591797, | |
| "learning_rate": 3.8709294634702376e-05, | |
| "loss": 0.4573, | |
| "num_input_tokens_seen": 68630, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.572549019607843, | |
| "grad_norm": 4.045778274536133, | |
| "learning_rate": 3.6257601025131026e-05, | |
| "loss": 0.7857, | |
| "num_input_tokens_seen": 69484, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.603921568627451, | |
| "grad_norm": 2.6151039600372314, | |
| "learning_rate": 3.386881346763483e-05, | |
| "loss": 0.7443, | |
| "num_input_tokens_seen": 70355, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.635294117647059, | |
| "grad_norm": 3.3898870944976807, | |
| "learning_rate": 3.154528940713113e-05, | |
| "loss": 0.5147, | |
| "num_input_tokens_seen": 71198, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.8886942863464355, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.3022, | |
| "num_input_tokens_seen": 72040, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.6980392156862747, | |
| "grad_norm": 5.151848316192627, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 0.3934, | |
| "num_input_tokens_seen": 72907, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.7294117647058824, | |
| "grad_norm": 3.1100125312805176, | |
| "learning_rate": 2.4988893036954043e-05, | |
| "loss": 0.6222, | |
| "num_input_tokens_seen": 73742, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.76078431372549, | |
| "grad_norm": 2.5638794898986816, | |
| "learning_rate": 2.2948675722421086e-05, | |
| "loss": 0.5721, | |
| "num_input_tokens_seen": 74587, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.792156862745098, | |
| "grad_norm": 3.2768828868865967, | |
| "learning_rate": 2.098449876243098e-05, | |
| "loss": 0.5144, | |
| "num_input_tokens_seen": 75433, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 4.178157806396484, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.463, | |
| "num_input_tokens_seen": 76218, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.854901960784314, | |
| "grad_norm": 4.432765960693359, | |
| "learning_rate": 1.7291942572543807e-05, | |
| "loss": 0.6351, | |
| "num_input_tokens_seen": 77053, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.8862745098039215, | |
| "grad_norm": 2.8439605236053467, | |
| "learning_rate": 1.5567207449798515e-05, | |
| "loss": 0.5897, | |
| "num_input_tokens_seen": 77899, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.9176470588235293, | |
| "grad_norm": 3.0817153453826904, | |
| "learning_rate": 1.3925797299605625e-05, | |
| "loss": 0.6083, | |
| "num_input_tokens_seen": 78767, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.9490196078431374, | |
| "grad_norm": 3.2820534706115723, | |
| "learning_rate": 1.2369331995613643e-05, | |
| "loss": 0.5075, | |
| "num_input_tokens_seen": 79591, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.980392156862745, | |
| "grad_norm": 4.051931858062744, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.4958, | |
| "num_input_tokens_seen": 80422, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.011764705882353, | |
| "grad_norm": 3.6439077854156494, | |
| "learning_rate": 9.517294753398042e-06, | |
| "loss": 0.8383, | |
| "num_input_tokens_seen": 81282, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.0431372549019606, | |
| "grad_norm": 3.559818983078003, | |
| "learning_rate": 8.224537431601908e-06, | |
| "loss": 0.5131, | |
| "num_input_tokens_seen": 82101, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.074509803921569, | |
| "grad_norm": 2.2776846885681152, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 0.5896, | |
| "num_input_tokens_seen": 82989, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.1058823529411765, | |
| "grad_norm": 2.8956410884857178, | |
| "learning_rate": 5.911923104577455e-06, | |
| "loss": 0.5902, | |
| "num_input_tokens_seen": 83838, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.1372549019607843, | |
| "grad_norm": 2.3653640747070312, | |
| "learning_rate": 4.8943483704846585e-06, | |
| "loss": 0.278, | |
| "num_input_tokens_seen": 84654, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.168627450980392, | |
| "grad_norm": 2.7463765144348145, | |
| "learning_rate": 3.970631432305694e-06, | |
| "loss": 0.4051, | |
| "num_input_tokens_seen": 85493, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 1.9491956233978271, | |
| "learning_rate": 3.141683887136904e-06, | |
| "loss": 0.3255, | |
| "num_input_tokens_seen": 86381, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.231372549019608, | |
| "grad_norm": 3.7543513774871826, | |
| "learning_rate": 2.4083238061252678e-06, | |
| "loss": 0.5123, | |
| "num_input_tokens_seen": 87182, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.2627450980392156, | |
| "grad_norm": 2.68157958984375, | |
| "learning_rate": 1.771274927131128e-06, | |
| "loss": 0.5409, | |
| "num_input_tokens_seen": 88059, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 2.971251964569092, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.3435, | |
| "num_input_tokens_seen": 88889, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.3254901960784315, | |
| "grad_norm": 2.606720209121704, | |
| "learning_rate": 7.885298685522235e-07, | |
| "loss": 0.5119, | |
| "num_input_tokens_seen": 89747, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.3568627450980393, | |
| "grad_norm": 2.622124433517456, | |
| "learning_rate": 4.438035396920004e-07, | |
| "loss": 0.5565, | |
| "num_input_tokens_seen": 90612, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 3.388235294117647, | |
| "grad_norm": 2.256873846054077, | |
| "learning_rate": 1.973271571728441e-07, | |
| "loss": 0.4164, | |
| "num_input_tokens_seen": 91453, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 3.4196078431372547, | |
| "grad_norm": 3.2237167358398438, | |
| "learning_rate": 4.934396342684e-08, | |
| "loss": 0.5135, | |
| "num_input_tokens_seen": 92304, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 3.450980392156863, | |
| "grad_norm": 2.807044267654419, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4391, | |
| "num_input_tokens_seen": 93130, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.4823529411764707, | |
| "grad_norm": 2.9154107570648193, | |
| "learning_rate": 0.00019995065603657316, | |
| "loss": 0.5719, | |
| "num_input_tokens_seen": 93953, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 3.5137254901960784, | |
| "grad_norm": 3.265385150909424, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 0.7463, | |
| "num_input_tokens_seen": 94803, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.545098039215686, | |
| "grad_norm": 5.992981910705566, | |
| "learning_rate": 0.00019955619646030802, | |
| "loss": 0.7756, | |
| "num_input_tokens_seen": 95673, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 3.576470588235294, | |
| "grad_norm": 6.979043483734131, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.5761, | |
| "num_input_tokens_seen": 96559, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.607843137254902, | |
| "grad_norm": 9.418047904968262, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.7796, | |
| "num_input_tokens_seen": 97366, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.6392156862745098, | |
| "grad_norm": 3.6083357334136963, | |
| "learning_rate": 0.00019822872507286888, | |
| "loss": 0.3696, | |
| "num_input_tokens_seen": 98197, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 3.6705882352941175, | |
| "grad_norm": 4.184770584106445, | |
| "learning_rate": 0.00019759167619387476, | |
| "loss": 0.4349, | |
| "num_input_tokens_seen": 99019, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 3.7019607843137257, | |
| "grad_norm": 5.8201799392700195, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 0.434, | |
| "num_input_tokens_seen": 99866, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 3.7333333333333334, | |
| "grad_norm": 5.535106182098389, | |
| "learning_rate": 0.0001960293685676943, | |
| "loss": 0.6474, | |
| "num_input_tokens_seen": 100723, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 3.3299312591552734, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.4361, | |
| "num_input_tokens_seen": 101581, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.796078431372549, | |
| "grad_norm": 7.6674323081970215, | |
| "learning_rate": 0.00019408807689542257, | |
| "loss": 0.575, | |
| "num_input_tokens_seen": 102418, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 3.8274509803921566, | |
| "grad_norm": 7.189317226409912, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 0.8572, | |
| "num_input_tokens_seen": 103281, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.8588235294117648, | |
| "grad_norm": 4.600097179412842, | |
| "learning_rate": 0.00019177546256839812, | |
| "loss": 0.6253, | |
| "num_input_tokens_seen": 104128, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 3.8901960784313725, | |
| "grad_norm": 6.0382585525512695, | |
| "learning_rate": 0.00019048270524660193, | |
| "loss": 0.4465, | |
| "num_input_tokens_seen": 104972, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 3.9215686274509802, | |
| "grad_norm": 5.221591949462891, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 0.6236, | |
| "num_input_tokens_seen": 105833, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 3.9529411764705884, | |
| "grad_norm": 4.43485164642334, | |
| "learning_rate": 0.0001876306680043864, | |
| "loss": 0.6026, | |
| "num_input_tokens_seen": 106656, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.984313725490196, | |
| "grad_norm": 4.633317947387695, | |
| "learning_rate": 0.0001860742027003944, | |
| "loss": 0.4891, | |
| "num_input_tokens_seen": 107479, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.015686274509804, | |
| "grad_norm": 2.710853338241577, | |
| "learning_rate": 0.00018443279255020155, | |
| "loss": 0.4361, | |
| "num_input_tokens_seen": 108376, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.047058823529412, | |
| "grad_norm": 3.0707015991210938, | |
| "learning_rate": 0.0001827080574274562, | |
| "loss": 0.4198, | |
| "num_input_tokens_seen": 109228, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.078431372549019, | |
| "grad_norm": 2.8015506267547607, | |
| "learning_rate": 0.0001809016994374947, | |
| "loss": 0.4515, | |
| "num_input_tokens_seen": 110061, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.109803921568627, | |
| "grad_norm": 3.3442440032958984, | |
| "learning_rate": 0.00017901550123756906, | |
| "loss": 0.3318, | |
| "num_input_tokens_seen": 110927, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 4.141176470588236, | |
| "grad_norm": 2.747676372528076, | |
| "learning_rate": 0.00017705132427757895, | |
| "loss": 0.4279, | |
| "num_input_tokens_seen": 111786, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.172549019607843, | |
| "grad_norm": 3.85593581199646, | |
| "learning_rate": 0.00017501110696304596, | |
| "loss": 0.3526, | |
| "num_input_tokens_seen": 112632, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.203921568627451, | |
| "grad_norm": 3.7865078449249268, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 0.4617, | |
| "num_input_tokens_seen": 113486, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 2.6525180339813232, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.2388, | |
| "num_input_tokens_seen": 114336, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 10.199384689331055, | |
| "learning_rate": 0.00016845471059286887, | |
| "loss": 0.4286, | |
| "num_input_tokens_seen": 115202, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.298039215686274, | |
| "grad_norm": 3.65986967086792, | |
| "learning_rate": 0.00016613118653236518, | |
| "loss": 0.478, | |
| "num_input_tokens_seen": 116036, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 4.329411764705882, | |
| "grad_norm": 2.575523614883423, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 0.229, | |
| "num_input_tokens_seen": 116868, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 4.36078431372549, | |
| "grad_norm": 5.756189346313477, | |
| "learning_rate": 0.00016129070536529766, | |
| "loss": 0.5141, | |
| "num_input_tokens_seen": 117745, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 4.392156862745098, | |
| "grad_norm": 3.640237331390381, | |
| "learning_rate": 0.0001587785252292473, | |
| "loss": 0.2679, | |
| "num_input_tokens_seen": 118582, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.423529411764706, | |
| "grad_norm": 4.511353015899658, | |
| "learning_rate": 0.00015620833778521304, | |
| "loss": 0.381, | |
| "num_input_tokens_seen": 119445, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 4.454901960784314, | |
| "grad_norm": 12.773442268371582, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 0.5296, | |
| "num_input_tokens_seen": 120241, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 4.486274509803922, | |
| "grad_norm": 3.347665548324585, | |
| "learning_rate": 0.00015090414157503714, | |
| "loss": 0.3427, | |
| "num_input_tokens_seen": 121096, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 4.517647058823529, | |
| "grad_norm": 3.0967466831207275, | |
| "learning_rate": 0.00014817536741017158, | |
| "loss": 0.3916, | |
| "num_input_tokens_seen": 121910, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.549019607843137, | |
| "grad_norm": 2.6861841678619385, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.3054, | |
| "num_input_tokens_seen": 122762, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 4.580392156862745, | |
| "grad_norm": 4.615218162536621, | |
| "learning_rate": 0.0001425779291565073, | |
| "loss": 0.3923, | |
| "num_input_tokens_seen": 123593, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 4.6117647058823525, | |
| "grad_norm": 6.789853572845459, | |
| "learning_rate": 0.00013971478906347803, | |
| "loss": 0.438, | |
| "num_input_tokens_seen": 124446, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 4.643137254901961, | |
| "grad_norm": 4.128298282623291, | |
| "learning_rate": 0.00013681245526846777, | |
| "loss": 0.4208, | |
| "num_input_tokens_seen": 125313, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 4.674509803921569, | |
| "grad_norm": 3.4282140731811523, | |
| "learning_rate": 0.00013387379202452917, | |
| "loss": 0.3717, | |
| "num_input_tokens_seen": 126184, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 6.779294967651367, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.4152, | |
| "num_input_tokens_seen": 127026, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.737254901960784, | |
| "grad_norm": 3.086122989654541, | |
| "learning_rate": 0.00012789911060392294, | |
| "loss": 0.3011, | |
| "num_input_tokens_seen": 127883, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 4.768627450980392, | |
| "grad_norm": 5.97057580947876, | |
| "learning_rate": 0.0001248689887164855, | |
| "loss": 0.3705, | |
| "num_input_tokens_seen": 128689, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 4.796477317810059, | |
| "learning_rate": 0.00012181432413965421, | |
| "loss": 0.4362, | |
| "num_input_tokens_seen": 129520, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 4.8313725490196076, | |
| "grad_norm": 3.3298208713531494, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 0.4988, | |
| "num_input_tokens_seen": 130406, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 4.862745098039216, | |
| "grad_norm": 3.887026071548462, | |
| "learning_rate": 0.00011564344650402312, | |
| "loss": 0.5444, | |
| "num_input_tokens_seen": 131276, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 4.894117647058824, | |
| "grad_norm": 6.220418453216553, | |
| "learning_rate": 0.00011253332335643046, | |
| "loss": 0.4078, | |
| "num_input_tokens_seen": 132090, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 4.925490196078432, | |
| "grad_norm": 2.757842779159546, | |
| "learning_rate": 0.00010941083133185146, | |
| "loss": 0.3539, | |
| "num_input_tokens_seen": 132909, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 4.956862745098039, | |
| "grad_norm": 2.275514602661133, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 0.3512, | |
| "num_input_tokens_seen": 133799, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 4.988235294117647, | |
| "grad_norm": 3.4296388626098633, | |
| "learning_rate": 0.00010314107590781284, | |
| "loss": 0.3426, | |
| "num_input_tokens_seen": 134640, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 5.019607843137255, | |
| "grad_norm": 1.8311214447021484, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1619, | |
| "num_input_tokens_seen": 135491, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.050980392156863, | |
| "grad_norm": 2.676769495010376, | |
| "learning_rate": 9.685892409218724e-05, | |
| "loss": 0.221, | |
| "num_input_tokens_seen": 136317, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 5.08235294117647, | |
| "grad_norm": 1.8601126670837402, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 0.2427, | |
| "num_input_tokens_seen": 137191, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 5.113725490196078, | |
| "grad_norm": 1.8501461744308472, | |
| "learning_rate": 9.058916866814858e-05, | |
| "loss": 0.2443, | |
| "num_input_tokens_seen": 138029, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 5.145098039215687, | |
| "grad_norm": 1.612574815750122, | |
| "learning_rate": 8.746667664356956e-05, | |
| "loss": 0.1391, | |
| "num_input_tokens_seen": 138848, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 5.176470588235294, | |
| "grad_norm": 1.7896589040756226, | |
| "learning_rate": 8.435655349597684e-05, | |
| "loss": 0.0778, | |
| "num_input_tokens_seen": 139648, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 5.207843137254902, | |
| "grad_norm": 3.172090530395508, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 0.2737, | |
| "num_input_tokens_seen": 140500, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 5.23921568627451, | |
| "grad_norm": 2.280182361602783, | |
| "learning_rate": 7.818567586034581e-05, | |
| "loss": 0.18, | |
| "num_input_tokens_seen": 141331, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 5.270588235294118, | |
| "grad_norm": 3.10487699508667, | |
| "learning_rate": 7.513101128351459e-05, | |
| "loss": 0.2636, | |
| "num_input_tokens_seen": 142188, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 5.301960784313725, | |
| "grad_norm": 2.16359543800354, | |
| "learning_rate": 7.210088939607707e-05, | |
| "loss": 0.1788, | |
| "num_input_tokens_seen": 143005, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 3.690769910812378, | |
| "learning_rate": 6.909830056250524e-05, | |
| "loss": 0.1271, | |
| "num_input_tokens_seen": 143796, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.364705882352941, | |
| "grad_norm": 4.808859348297119, | |
| "learning_rate": 6.612620797547091e-05, | |
| "loss": 0.1235, | |
| "num_input_tokens_seen": 144594, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 5.396078431372549, | |
| "grad_norm": 2.4017834663391113, | |
| "learning_rate": 6.318754473153218e-05, | |
| "loss": 0.1417, | |
| "num_input_tokens_seen": 145432, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 5.427450980392157, | |
| "grad_norm": 10.861905097961426, | |
| "learning_rate": 6.0285210936521976e-05, | |
| "loss": 0.3499, | |
| "num_input_tokens_seen": 146307, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 5.458823529411765, | |
| "grad_norm": 6.508179664611816, | |
| "learning_rate": 5.742207084349277e-05, | |
| "loss": 0.2636, | |
| "num_input_tokens_seen": 147159, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 5.490196078431373, | |
| "grad_norm": 3.551328659057617, | |
| "learning_rate": 5.4600950026045285e-05, | |
| "loss": 0.1685, | |
| "num_input_tokens_seen": 147990, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 5.52156862745098, | |
| "grad_norm": 5.636049747467041, | |
| "learning_rate": 5.182463258982846e-05, | |
| "loss": 0.2804, | |
| "num_input_tokens_seen": 148782, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 5.552941176470588, | |
| "grad_norm": 4.598341941833496, | |
| "learning_rate": 4.909585842496292e-05, | |
| "loss": 0.3087, | |
| "num_input_tokens_seen": 149687, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 5.584313725490196, | |
| "grad_norm": 5.29741907119751, | |
| "learning_rate": 4.6417320502100316e-05, | |
| "loss": 0.3299, | |
| "num_input_tokens_seen": 150565, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 5.6156862745098035, | |
| "grad_norm": 3.7548561096191406, | |
| "learning_rate": 4.379166221478697e-05, | |
| "loss": 0.3047, | |
| "num_input_tokens_seen": 151419, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 5.647058823529412, | |
| "grad_norm": 2.995479106903076, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.2234, | |
| "num_input_tokens_seen": 152249, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.67843137254902, | |
| "grad_norm": 2.391935110092163, | |
| "learning_rate": 3.8709294634702376e-05, | |
| "loss": 0.1819, | |
| "num_input_tokens_seen": 153097, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 5.709803921568628, | |
| "grad_norm": 2.5566658973693848, | |
| "learning_rate": 3.625760102513099e-05, | |
| "loss": 0.2642, | |
| "num_input_tokens_seen": 153970, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 5.741176470588235, | |
| "grad_norm": 2.3486950397491455, | |
| "learning_rate": 3.386881346763483e-05, | |
| "loss": 0.1399, | |
| "num_input_tokens_seen": 154821, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 5.772549019607843, | |
| "grad_norm": 3.2803895473480225, | |
| "learning_rate": 3.15452894071312e-05, | |
| "loss": 0.2416, | |
| "num_input_tokens_seen": 155654, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 5.803921568627451, | |
| "grad_norm": 3.5313189029693604, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.1808, | |
| "num_input_tokens_seen": 156464, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 5.8352941176470585, | |
| "grad_norm": 2.8547775745391846, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 0.2565, | |
| "num_input_tokens_seen": 157360, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 5.866666666666667, | |
| "grad_norm": 2.3218977451324463, | |
| "learning_rate": 2.4988893036954043e-05, | |
| "loss": 0.1691, | |
| "num_input_tokens_seen": 158193, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 5.898039215686275, | |
| "grad_norm": 2.2196223735809326, | |
| "learning_rate": 2.2948675722421032e-05, | |
| "loss": 0.4082, | |
| "num_input_tokens_seen": 159122, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 5.929411764705883, | |
| "grad_norm": 2.5707294940948486, | |
| "learning_rate": 2.098449876243096e-05, | |
| "loss": 0.2091, | |
| "num_input_tokens_seen": 159987, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 5.96078431372549, | |
| "grad_norm": 3.849001407623291, | |
| "learning_rate": 1.909830056250529e-05, | |
| "loss": 0.258, | |
| "num_input_tokens_seen": 160876, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.992156862745098, | |
| "grad_norm": 7.267693042755127, | |
| "learning_rate": 1.7291942572543807e-05, | |
| "loss": 0.3389, | |
| "num_input_tokens_seen": 161713, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 6.023529411764706, | |
| "grad_norm": 2.107445240020752, | |
| "learning_rate": 1.5567207449798495e-05, | |
| "loss": 0.1413, | |
| "num_input_tokens_seen": 162530, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 6.0549019607843135, | |
| "grad_norm": 1.9133341312408447, | |
| "learning_rate": 1.3925797299605625e-05, | |
| "loss": 0.098, | |
| "num_input_tokens_seen": 163339, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 6.086274509803921, | |
| "grad_norm": 2.2540628910064697, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 0.1409, | |
| "num_input_tokens_seen": 164183, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 6.117647058823529, | |
| "grad_norm": 1.5692024230957031, | |
| "learning_rate": 1.08993475811632e-05, | |
| "loss": 0.1951, | |
| "num_input_tokens_seen": 165009, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 6.149019607843138, | |
| "grad_norm": 1.885223150253296, | |
| "learning_rate": 9.517294753398064e-06, | |
| "loss": 0.1493, | |
| "num_input_tokens_seen": 165856, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 6.180392156862745, | |
| "grad_norm": 1.3335139751434326, | |
| "learning_rate": 8.224537431601908e-06, | |
| "loss": 0.054, | |
| "num_input_tokens_seen": 166686, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 6.211764705882353, | |
| "grad_norm": 2.255988359451294, | |
| "learning_rate": 7.022351411174855e-06, | |
| "loss": 0.1965, | |
| "num_input_tokens_seen": 167544, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 6.243137254901961, | |
| "grad_norm": 4.721761703491211, | |
| "learning_rate": 5.911923104577455e-06, | |
| "loss": 0.1935, | |
| "num_input_tokens_seen": 168348, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 6.2745098039215685, | |
| "grad_norm": 2.2551510334014893, | |
| "learning_rate": 4.8943483704846585e-06, | |
| "loss": 0.1393, | |
| "num_input_tokens_seen": 169231, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.305882352941176, | |
| "grad_norm": 1.8611195087432861, | |
| "learning_rate": 3.970631432305694e-06, | |
| "loss": 0.1288, | |
| "num_input_tokens_seen": 170060, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 6.337254901960784, | |
| "grad_norm": 2.192089796066284, | |
| "learning_rate": 3.141683887136904e-06, | |
| "loss": 0.2037, | |
| "num_input_tokens_seen": 170917, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 6.368627450980393, | |
| "grad_norm": 1.2144159078598022, | |
| "learning_rate": 2.4083238061252678e-06, | |
| "loss": 0.0774, | |
| "num_input_tokens_seen": 171774, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 1.9125508069992065, | |
| "learning_rate": 1.771274927131139e-06, | |
| "loss": 0.1388, | |
| "num_input_tokens_seen": 172589, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 6.431372549019608, | |
| "grad_norm": 1.6493868827819824, | |
| "learning_rate": 1.231165940486223e-06, | |
| "loss": 0.1192, | |
| "num_input_tokens_seen": 173418, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 6.462745098039216, | |
| "grad_norm": 1.91011643409729, | |
| "learning_rate": 7.885298685522235e-07, | |
| "loss": 0.0885, | |
| "num_input_tokens_seen": 174236, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 6.4941176470588236, | |
| "grad_norm": 1.8174355030059814, | |
| "learning_rate": 4.438035396920115e-07, | |
| "loss": 0.2875, | |
| "num_input_tokens_seen": 175172, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 6.525490196078431, | |
| "grad_norm": 1.7092390060424805, | |
| "learning_rate": 1.973271571728441e-07, | |
| "loss": 0.1039, | |
| "num_input_tokens_seen": 176023, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 6.556862745098039, | |
| "grad_norm": 1.8284764289855957, | |
| "learning_rate": 4.934396342684e-08, | |
| "loss": 0.1365, | |
| "num_input_tokens_seen": 176906, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 6.588235294117647, | |
| "grad_norm": 1.697880506515503, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1889, | |
| "num_input_tokens_seen": 177795, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.6196078431372545, | |
| "grad_norm": 1.8329994678497314, | |
| "learning_rate": 0.00019995065603657314, | |
| "loss": 0.2207, | |
| "num_input_tokens_seen": 178672, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 6.650980392156863, | |
| "grad_norm": 2.528137683868408, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 0.1294, | |
| "num_input_tokens_seen": 179466, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 6.682352941176471, | |
| "grad_norm": 5.707077503204346, | |
| "learning_rate": 0.00019955619646030802, | |
| "loss": 0.1878, | |
| "num_input_tokens_seen": 180332, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 6.713725490196079, | |
| "grad_norm": 5.38962459564209, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.1539, | |
| "num_input_tokens_seen": 181169, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 6.745098039215686, | |
| "grad_norm": 8.556888580322266, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.3257, | |
| "num_input_tokens_seen": 182059, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 6.776470588235294, | |
| "grad_norm": 5.112634658813477, | |
| "learning_rate": 0.00019822872507286888, | |
| "loss": 0.1682, | |
| "num_input_tokens_seen": 182890, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 6.807843137254902, | |
| "grad_norm": 5.386922359466553, | |
| "learning_rate": 0.00019759167619387476, | |
| "loss": 0.1355, | |
| "num_input_tokens_seen": 183734, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 6.8392156862745095, | |
| "grad_norm": 9.67380142211914, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 0.1565, | |
| "num_input_tokens_seen": 184542, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 6.870588235294118, | |
| "grad_norm": 4.442196369171143, | |
| "learning_rate": 0.00019602936856769434, | |
| "loss": 0.1822, | |
| "num_input_tokens_seen": 185420, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 6.901960784313726, | |
| "grad_norm": 6.283408164978027, | |
| "learning_rate": 0.0001951056516295154, | |
| "loss": 0.2803, | |
| "num_input_tokens_seen": 186278, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.933333333333334, | |
| "grad_norm": 2.322974920272827, | |
| "learning_rate": 0.0001940880768954225, | |
| "loss": 0.175, | |
| "num_input_tokens_seen": 187146, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 6.964705882352941, | |
| "grad_norm": 4.757282733917236, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 0.2458, | |
| "num_input_tokens_seen": 187998, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 6.996078431372549, | |
| "grad_norm": 10.94787883758545, | |
| "learning_rate": 0.00019177546256839812, | |
| "loss": 0.4605, | |
| "num_input_tokens_seen": 188820, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 7.027450980392157, | |
| "grad_norm": 3.9081947803497314, | |
| "learning_rate": 0.00019048270524660193, | |
| "loss": 0.1243, | |
| "num_input_tokens_seen": 189615, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 4.866150856018066, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 0.2121, | |
| "num_input_tokens_seen": 190498, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 7.090196078431372, | |
| "grad_norm": 2.8364100456237793, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 0.2427, | |
| "num_input_tokens_seen": 191385, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 7.12156862745098, | |
| "grad_norm": 1.5343717336654663, | |
| "learning_rate": 0.0001860742027003944, | |
| "loss": 0.0782, | |
| "num_input_tokens_seen": 192218, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 7.152941176470589, | |
| "grad_norm": 2.824655771255493, | |
| "learning_rate": 0.0001844327925502015, | |
| "loss": 0.0852, | |
| "num_input_tokens_seen": 193056, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.184313725490196, | |
| "grad_norm": 6.053825378417969, | |
| "learning_rate": 0.0001827080574274562, | |
| "loss": 0.2932, | |
| "num_input_tokens_seen": 193874, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 7.215686274509804, | |
| "grad_norm": 7.972029685974121, | |
| "learning_rate": 0.0001809016994374948, | |
| "loss": 0.1712, | |
| "num_input_tokens_seen": 194758, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.247058823529412, | |
| "grad_norm": 3.326019287109375, | |
| "learning_rate": 0.00017901550123756906, | |
| "loss": 0.1383, | |
| "num_input_tokens_seen": 195658, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 7.2784313725490195, | |
| "grad_norm": 2.4085988998413086, | |
| "learning_rate": 0.000177051324277579, | |
| "loss": 0.0777, | |
| "num_input_tokens_seen": 196482, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 7.309803921568627, | |
| "grad_norm": 4.651546001434326, | |
| "learning_rate": 0.00017501110696304596, | |
| "loss": 0.1553, | |
| "num_input_tokens_seen": 197329, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 7.341176470588235, | |
| "grad_norm": 2.4471681118011475, | |
| "learning_rate": 0.00017289686274214112, | |
| "loss": 0.1341, | |
| "num_input_tokens_seen": 198158, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 7.372549019607844, | |
| "grad_norm": 4.855953216552734, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.081, | |
| "num_input_tokens_seen": 198961, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 7.403921568627451, | |
| "grad_norm": 6.432670593261719, | |
| "learning_rate": 0.00016845471059286893, | |
| "loss": 0.0946, | |
| "num_input_tokens_seen": 199788, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 7.435294117647059, | |
| "grad_norm": 4.775556564331055, | |
| "learning_rate": 0.00016613118653236518, | |
| "loss": 0.1548, | |
| "num_input_tokens_seen": 200637, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 7.466666666666667, | |
| "grad_norm": 4.532850742340088, | |
| "learning_rate": 0.0001637423989748689, | |
| "loss": 0.0952, | |
| "num_input_tokens_seen": 201482, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 7.4980392156862745, | |
| "grad_norm": 7.549116134643555, | |
| "learning_rate": 0.00016129070536529766, | |
| "loss": 0.2452, | |
| "num_input_tokens_seen": 202333, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 7.529411764705882, | |
| "grad_norm": 3.5515332221984863, | |
| "learning_rate": 0.00015877852522924726, | |
| "loss": 0.1033, | |
| "num_input_tokens_seen": 203151, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.56078431372549, | |
| "grad_norm": 4.602539539337158, | |
| "learning_rate": 0.00015620833778521304, | |
| "loss": 0.1349, | |
| "num_input_tokens_seen": 204022, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 7.592156862745098, | |
| "grad_norm": 2.6608591079711914, | |
| "learning_rate": 0.00015358267949789971, | |
| "loss": 0.1057, | |
| "num_input_tokens_seen": 204856, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 7.623529411764705, | |
| "grad_norm": 5.953851699829102, | |
| "learning_rate": 0.00015090414157503714, | |
| "loss": 0.168, | |
| "num_input_tokens_seen": 205751, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 7.654901960784314, | |
| "grad_norm": 2.4022793769836426, | |
| "learning_rate": 0.00014817536741017158, | |
| "loss": 0.1534, | |
| "num_input_tokens_seen": 206614, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 7.686274509803922, | |
| "grad_norm": 5.277859210968018, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.1876, | |
| "num_input_tokens_seen": 207442, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 7.7176470588235295, | |
| "grad_norm": 3.6555447578430176, | |
| "learning_rate": 0.0001425779291565073, | |
| "loss": 0.1528, | |
| "num_input_tokens_seen": 208268, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 7.749019607843137, | |
| "grad_norm": 13.82836627960205, | |
| "learning_rate": 0.00013971478906347803, | |
| "loss": 0.2893, | |
| "num_input_tokens_seen": 209161, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 7.780392156862745, | |
| "grad_norm": 4.631089687347412, | |
| "learning_rate": 0.00013681245526846785, | |
| "loss": 0.1996, | |
| "num_input_tokens_seen": 209987, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 7.811764705882353, | |
| "grad_norm": 5.084930419921875, | |
| "learning_rate": 0.00013387379202452922, | |
| "loss": 0.2305, | |
| "num_input_tokens_seen": 210827, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 7.8431372549019605, | |
| "grad_norm": 4.121197700500488, | |
| "learning_rate": 0.00013090169943749463, | |
| "loss": 0.3338, | |
| "num_input_tokens_seen": 211698, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.874509803921569, | |
| "grad_norm": 3.6635348796844482, | |
| "learning_rate": 0.0001278991106039229, | |
| "loss": 0.2121, | |
| "num_input_tokens_seen": 212549, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 7.905882352941177, | |
| "grad_norm": 2.271726369857788, | |
| "learning_rate": 0.0001248689887164855, | |
| "loss": 0.0888, | |
| "num_input_tokens_seen": 213388, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 7.9372549019607845, | |
| "grad_norm": 2.883363962173462, | |
| "learning_rate": 0.00012181432413965421, | |
| "loss": 0.2263, | |
| "num_input_tokens_seen": 214226, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 7.968627450980392, | |
| "grad_norm": 5.223812580108643, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 0.1085, | |
| "num_input_tokens_seen": 215089, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 3.1294803619384766, | |
| "learning_rate": 0.00011564344650402304, | |
| "loss": 0.2069, | |
| "num_input_tokens_seen": 215904, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 8.031372549019608, | |
| "grad_norm": 3.5736420154571533, | |
| "learning_rate": 0.00011253332335643046, | |
| "loss": 0.0774, | |
| "num_input_tokens_seen": 216721, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 8.062745098039215, | |
| "grad_norm": 1.6127935647964478, | |
| "learning_rate": 0.00010941083133185139, | |
| "loss": 0.0487, | |
| "num_input_tokens_seen": 217568, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 8.094117647058823, | |
| "grad_norm": 1.9943934679031372, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 0.049, | |
| "num_input_tokens_seen": 218393, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 8.125490196078431, | |
| "grad_norm": 5.851587772369385, | |
| "learning_rate": 0.00010314107590781291, | |
| "loss": 0.121, | |
| "num_input_tokens_seen": 219230, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 8.156862745098039, | |
| "grad_norm": 2.693629026412964, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0664, | |
| "num_input_tokens_seen": 220048, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.188235294117646, | |
| "grad_norm": 6.576751708984375, | |
| "learning_rate": 9.685892409218724e-05, | |
| "loss": 0.0818, | |
| "num_input_tokens_seen": 220906, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 8.219607843137254, | |
| "grad_norm": 1.8238303661346436, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 0.0977, | |
| "num_input_tokens_seen": 221795, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 8.250980392156862, | |
| "grad_norm": 2.1661157608032227, | |
| "learning_rate": 9.058916866814851e-05, | |
| "loss": 0.0617, | |
| "num_input_tokens_seen": 222644, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 8.282352941176471, | |
| "grad_norm": 3.1537587642669678, | |
| "learning_rate": 8.746667664356956e-05, | |
| "loss": 0.1102, | |
| "num_input_tokens_seen": 223465, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 8.313725490196079, | |
| "grad_norm": 12.85554027557373, | |
| "learning_rate": 8.435655349597699e-05, | |
| "loss": 0.1478, | |
| "num_input_tokens_seen": 224302, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 8.345098039215687, | |
| "grad_norm": 4.586164474487305, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 0.2202, | |
| "num_input_tokens_seen": 225154, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 8.376470588235295, | |
| "grad_norm": 3.9367291927337646, | |
| "learning_rate": 7.818567586034566e-05, | |
| "loss": 0.0682, | |
| "num_input_tokens_seen": 226040, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 8.407843137254902, | |
| "grad_norm": 2.0368969440460205, | |
| "learning_rate": 7.513101128351452e-05, | |
| "loss": 0.0402, | |
| "num_input_tokens_seen": 226847, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 8.43921568627451, | |
| "grad_norm": 1.0436691045761108, | |
| "learning_rate": 7.210088939607714e-05, | |
| "loss": 0.0185, | |
| "num_input_tokens_seen": 227680, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 8.470588235294118, | |
| "grad_norm": 1.8092098236083984, | |
| "learning_rate": 6.909830056250524e-05, | |
| "loss": 0.0442, | |
| "num_input_tokens_seen": 228543, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.501960784313725, | |
| "grad_norm": 1.526930332183838, | |
| "learning_rate": 6.612620797547091e-05, | |
| "loss": 0.0362, | |
| "num_input_tokens_seen": 229373, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 8.533333333333333, | |
| "grad_norm": 1.8258460760116577, | |
| "learning_rate": 6.318754473153218e-05, | |
| "loss": 0.0457, | |
| "num_input_tokens_seen": 230190, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 8.564705882352941, | |
| "grad_norm": 1.3038586378097534, | |
| "learning_rate": 6.0285210936521976e-05, | |
| "loss": 0.0831, | |
| "num_input_tokens_seen": 231024, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 8.596078431372549, | |
| "grad_norm": 5.259337902069092, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 0.1228, | |
| "num_input_tokens_seen": 231915, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 8.627450980392156, | |
| "grad_norm": 0.8257218599319458, | |
| "learning_rate": 5.460095002604537e-05, | |
| "loss": 0.0171, | |
| "num_input_tokens_seen": 232711, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 8.658823529411764, | |
| "grad_norm": 1.649411916732788, | |
| "learning_rate": 5.182463258982846e-05, | |
| "loss": 0.0366, | |
| "num_input_tokens_seen": 233534, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 8.690196078431372, | |
| "grad_norm": 4.529787540435791, | |
| "learning_rate": 4.909585842496292e-05, | |
| "loss": 0.1006, | |
| "num_input_tokens_seen": 234406, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 8.72156862745098, | |
| "grad_norm": 3.721914052963257, | |
| "learning_rate": 4.6417320502100425e-05, | |
| "loss": 0.1088, | |
| "num_input_tokens_seen": 235270, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 8.75294117647059, | |
| "grad_norm": 8.44381046295166, | |
| "learning_rate": 4.379166221478697e-05, | |
| "loss": 0.1685, | |
| "num_input_tokens_seen": 236150, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 8.784313725490197, | |
| "grad_norm": 3.0152742862701416, | |
| "learning_rate": 4.122147477075266e-05, | |
| "loss": 0.0961, | |
| "num_input_tokens_seen": 237030, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.815686274509805, | |
| "grad_norm": 2.386852502822876, | |
| "learning_rate": 3.8709294634702376e-05, | |
| "loss": 0.112, | |
| "num_input_tokens_seen": 237889, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 8.847058823529412, | |
| "grad_norm": 3.819979667663574, | |
| "learning_rate": 3.6257601025131094e-05, | |
| "loss": 0.0342, | |
| "num_input_tokens_seen": 238703, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 8.87843137254902, | |
| "grad_norm": 2.879319190979004, | |
| "learning_rate": 3.386881346763483e-05, | |
| "loss": 0.1328, | |
| "num_input_tokens_seen": 239619, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 8.909803921568628, | |
| "grad_norm": 4.421603679656982, | |
| "learning_rate": 3.1545289407131097e-05, | |
| "loss": 0.141, | |
| "num_input_tokens_seen": 240466, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 8.941176470588236, | |
| "grad_norm": 1.440587043762207, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0686, | |
| "num_input_tokens_seen": 241295, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 8.972549019607843, | |
| "grad_norm": 1.706859827041626, | |
| "learning_rate": 2.71031372578588e-05, | |
| "loss": 0.0272, | |
| "num_input_tokens_seen": 242157, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 9.003921568627451, | |
| "grad_norm": 1.8288636207580566, | |
| "learning_rate": 2.4988893036954043e-05, | |
| "loss": 0.0571, | |
| "num_input_tokens_seen": 243008, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 9.035294117647059, | |
| "grad_norm": 0.7292274236679077, | |
| "learning_rate": 2.294867572242112e-05, | |
| "loss": 0.0109, | |
| "num_input_tokens_seen": 243807, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 9.066666666666666, | |
| "grad_norm": 1.1452817916870117, | |
| "learning_rate": 2.098449876243096e-05, | |
| "loss": 0.0239, | |
| "num_input_tokens_seen": 244652, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 9.098039215686274, | |
| "grad_norm": 1.0900837182998657, | |
| "learning_rate": 1.909830056250529e-05, | |
| "loss": 0.0197, | |
| "num_input_tokens_seen": 245514, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.129411764705882, | |
| "grad_norm": 1.1233842372894287, | |
| "learning_rate": 1.7291942572543807e-05, | |
| "loss": 0.059, | |
| "num_input_tokens_seen": 246368, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 9.16078431372549, | |
| "grad_norm": 1.2153921127319336, | |
| "learning_rate": 1.5567207449798515e-05, | |
| "loss": 0.0487, | |
| "num_input_tokens_seen": 247234, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 9.192156862745097, | |
| "grad_norm": 1.7913979291915894, | |
| "learning_rate": 1.3925797299605625e-05, | |
| "loss": 0.0462, | |
| "num_input_tokens_seen": 248080, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 9.223529411764705, | |
| "grad_norm": 0.9466875195503235, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 0.0196, | |
| "num_input_tokens_seen": 248920, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 9.254901960784313, | |
| "grad_norm": 2.3814680576324463, | |
| "learning_rate": 1.0899347581163277e-05, | |
| "loss": 0.021, | |
| "num_input_tokens_seen": 249739, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 9.286274509803922, | |
| "grad_norm": 1.2178651094436646, | |
| "learning_rate": 9.517294753397998e-06, | |
| "loss": 0.0089, | |
| "num_input_tokens_seen": 250537, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 9.31764705882353, | |
| "grad_norm": 3.2499518394470215, | |
| "learning_rate": 8.224537431601864e-06, | |
| "loss": 0.0794, | |
| "num_input_tokens_seen": 251375, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 9.349019607843138, | |
| "grad_norm": 2.116999626159668, | |
| "learning_rate": 7.022351411174888e-06, | |
| "loss": 0.0815, | |
| "num_input_tokens_seen": 252200, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 9.380392156862746, | |
| "grad_norm": 1.607701301574707, | |
| "learning_rate": 5.911923104577455e-06, | |
| "loss": 0.0686, | |
| "num_input_tokens_seen": 253122, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": 1.501824975013733, | |
| "learning_rate": 4.8943483704846585e-06, | |
| "loss": 0.0453, | |
| "num_input_tokens_seen": 253966, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.443137254901961, | |
| "grad_norm": 0.8923909664154053, | |
| "learning_rate": 3.970631432305694e-06, | |
| "loss": 0.0136, | |
| "num_input_tokens_seen": 254841, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 9.474509803921569, | |
| "grad_norm": 1.3790185451507568, | |
| "learning_rate": 3.141683887136904e-06, | |
| "loss": 0.0812, | |
| "num_input_tokens_seen": 255706, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 9.505882352941176, | |
| "grad_norm": 0.6012554168701172, | |
| "learning_rate": 2.4083238061252567e-06, | |
| "loss": 0.012, | |
| "num_input_tokens_seen": 256525, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 9.537254901960784, | |
| "grad_norm": 0.9253413677215576, | |
| "learning_rate": 1.771274927131139e-06, | |
| "loss": 0.0088, | |
| "num_input_tokens_seen": 257340, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 9.568627450980392, | |
| "grad_norm": 0.8364208936691284, | |
| "learning_rate": 1.2311659404862453e-06, | |
| "loss": 0.0128, | |
| "num_input_tokens_seen": 258165, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 1.1087877750396729, | |
| "learning_rate": 7.885298685522235e-07, | |
| "loss": 0.0406, | |
| "num_input_tokens_seen": 259015, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 9.631372549019607, | |
| "grad_norm": 1.227319359779358, | |
| "learning_rate": 4.438035396920115e-07, | |
| "loss": 0.0136, | |
| "num_input_tokens_seen": 259833, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 9.662745098039215, | |
| "grad_norm": 1.0235058069229126, | |
| "learning_rate": 1.973271571728441e-07, | |
| "loss": 0.037, | |
| "num_input_tokens_seen": 260686, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 9.694117647058823, | |
| "grad_norm": 1.069370150566101, | |
| "learning_rate": 4.934396342684e-08, | |
| "loss": 0.0366, | |
| "num_input_tokens_seen": 261513, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 9.72549019607843, | |
| "grad_norm": 1.2721508741378784, | |
| "learning_rate": 0.0, | |
| "loss": 0.0282, | |
| "num_input_tokens_seen": 262364, | |
| "step": 310 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 310, | |
| "num_input_tokens_seen": 262364, | |
| "num_train_epochs": 10, | |
| "save_steps": 31, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5870993062052984e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |