diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..77b1962bf2e216644bf583385e95c9d61ddcf138 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,34 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-1143/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-2286/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text +checkpoint-3426/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint-1143/optimizer_0/.metadata b/checkpoint-1143/optimizer_0/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..712d94f9189e637582fde9ca1b2f5a1936fc64a8 --- /dev/null +++ b/checkpoint-1143/optimizer_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd9e6d4beebe1690c8d99358768b1076a1ef1cc8b20ffcd62703a3eedb0a8c1 +size 342948 diff --git a/checkpoint-1143/optimizer_0/__0_0.distcp b/checkpoint-1143/optimizer_0/__0_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..7d7bce7821187dca75f400b0786be4d1a3aa62c5 --- /dev/null +++ b/checkpoint-1143/optimizer_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac5d3d1efa4b6d99d1205acb964c22ea995f4bd6308ffbd12a6a9a61a033edd +size 2472090861 diff --git a/checkpoint-1143/optimizer_0/__1_0.distcp b/checkpoint-1143/optimizer_0/__1_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..9a1c4b6a2b05228e51181ee8a344d38b4df04d00 --- /dev/null +++ b/checkpoint-1143/optimizer_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad08430914c0679e24ea6913676ee83efb7824038c5bbea284c334cfed3228da +size 2472174123 diff --git a/checkpoint-1143/optimizer_0/__2_0.distcp b/checkpoint-1143/optimizer_0/__2_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..1dc706dddd88fabc2ad7b4fb5c9be98c21e26643 --- /dev/null +++ b/checkpoint-1143/optimizer_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bde2bc55ebaca643a45b848a1f65bd0167fadda186065db992b6c9ced3b1d9 +size 2472182518 diff --git a/checkpoint-1143/optimizer_0/__3_0.distcp b/checkpoint-1143/optimizer_0/__3_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..8a9d6edcf40fdc5468ef6b04ebda9d1c8adc9421 --- /dev/null +++ b/checkpoint-1143/optimizer_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125861a679a795fe13b3c02eea22db849c3a207a98f7be2da110e34a20261fe2 +size 2472179190 diff --git a/checkpoint-1143/pytorch_model_fsdp_0/.metadata b/checkpoint-1143/pytorch_model_fsdp_0/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..1e43c535298f750fcdd5070f4a2fe1a3751a6450 --- /dev/null +++ b/checkpoint-1143/pytorch_model_fsdp_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242ac3ba3946c42f208f825806645989b468fa09b96c8ce90963492896751f1f +size 129152 diff --git a/checkpoint-1143/pytorch_model_fsdp_0/__0_0.distcp b/checkpoint-1143/pytorch_model_fsdp_0/__0_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..5253520b9b6edf3fa1e1afa3d39049595de8c61d --- /dev/null +++ b/checkpoint-1143/pytorch_model_fsdp_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba534ac3db914d6a6f3843e9623a0d7cf4cdd4717a3ef9f7cdf435477c8f7fa +size 1498714507 diff --git a/checkpoint-1143/pytorch_model_fsdp_0/__1_0.distcp b/checkpoint-1143/pytorch_model_fsdp_0/__1_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..861a3ca7b84b5cd31dbfaf806ad69731413080ba --- /dev/null +++ b/checkpoint-1143/pytorch_model_fsdp_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10517f1ee98d272b691d5be2ab0caf5f706dfd979bba9550f5d5eb3010cc53f +size 1498714507 diff --git a/checkpoint-1143/pytorch_model_fsdp_0/__2_0.distcp b/checkpoint-1143/pytorch_model_fsdp_0/__2_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..069def49c1230ef7c19ba6b375bc66f55ae76374 --- /dev/null +++ b/checkpoint-1143/pytorch_model_fsdp_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5757f685250c771031aa71f39e5e57af65de3a3584f16d428d6703c19a45f2f +size 1498714507 diff --git a/checkpoint-1143/pytorch_model_fsdp_0/__3_0.distcp b/checkpoint-1143/pytorch_model_fsdp_0/__3_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..43dc82e053f0fff2a9a0efc1afc8dc3442617118 --- /dev/null +++ b/checkpoint-1143/pytorch_model_fsdp_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa13d888ab3434a3a556da28c7400c57cdec90df0696570dc11c2f67fb68fe9 +size 1498714507 diff --git a/checkpoint-1143/rng_state_0.pth b/checkpoint-1143/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..08fe74f5a6509346bc7bac0a5ffae3f0c1235010 --- /dev/null +++ b/checkpoint-1143/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4188048c882e5b595f5e2cce07e8c73ea45afa11bc95f5627f2d6191ccaa5e40 +size 15429 diff --git a/checkpoint-1143/rng_state_1.pth b/checkpoint-1143/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..c34a6346a54e818fbc0db7ed1066952b078027e4 --- /dev/null +++ b/checkpoint-1143/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb1f7b1acfd920c8cdef076eee48ccfec7d3ed4d8c5d83c2592fbbb4a4f9b38 +size 15429 diff --git a/checkpoint-1143/rng_state_2.pth b/checkpoint-1143/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..98679a008686d92dc4d6a79a00e839fa51627c00 --- /dev/null +++ b/checkpoint-1143/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5664fd5079c69dc8edcc429ded884f07d45c771f27a5a65fe1ad751348f9e1de +size 15429 diff --git a/checkpoint-1143/rng_state_3.pth b/checkpoint-1143/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..d0852d3d83273be11573602862d25a8ec574a5ae --- /dev/null +++ b/checkpoint-1143/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3f17c4e252e5b7e99f3573c3bca992070f9ef436dd578ee9e88c333a94cef0 +size 15429 diff --git a/checkpoint-1143/scheduler.pt b/checkpoint-1143/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d3bcc81d1b63dc5bfdac6500a4f5bfca786928d9 --- /dev/null +++ b/checkpoint-1143/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa4344f06305e3a8793199a02dc90908e6c605511a625eb80252b479a7a39796 +size 1465 diff --git a/checkpoint-1143/trainer_state.json b/checkpoint-1143/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1cd54a1a6be95179435b90cfbca6f66f7da2bf12 --- /dev/null +++ b/checkpoint-1143/trainer_state.json @@ -0,0 +1,846 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 1143, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0, + "eval_loss": 2.1641297340393066, + "eval_runtime": 4.2967, + "eval_samples_per_second": 4.655, + "eval_steps_per_second": 0.465, + "step": 0 + }, + { + "epoch": 0.0008750820389411508, + "grad_norm": 6.37307071685791, + "learning_rate": 2.915451895043732e-07, + "loss": 1.6434, + "step": 1 + }, + { + "epoch": 0.008750820389411508, + "grad_norm": 4.0545759201049805, + "learning_rate": 2.915451895043732e-06, + "loss": 1.6965, + "step": 10 + }, + { + "epoch": 0.017501640778823015, + "grad_norm": 2.363191604614258, + "learning_rate": 5.830903790087464e-06, + "loss": 1.5272, + "step": 20 + }, + { + "epoch": 0.02625246116823452, + "grad_norm": 1.6348848342895508, + "learning_rate": 8.746355685131195e-06, + "loss": 1.389, + "step": 30 + }, + { + "epoch": 0.03500328155764603, + "grad_norm": 1.6716902256011963, + "learning_rate": 1.1661807580174927e-05, + "loss": 1.348, + "step": 40 + }, + { + "epoch": 0.04375410194705753, + "grad_norm": 1.510228157043457, + "learning_rate": 1.457725947521866e-05, + "loss": 1.2997, + "step": 50 + }, + { + "epoch": 0.05250492233646904, + "grad_norm": 1.6153247356414795, + "learning_rate": 1.749271137026239e-05, + "loss": 1.2665, + "step": 60 + }, + { + "epoch": 0.06125574272588055, + "grad_norm": 1.446387767791748, + "learning_rate": 2.0408163265306123e-05, + "loss": 1.237, + "step": 70 + }, + { + "epoch": 0.07000656311529206, + "grad_norm": 1.3039863109588623, + "learning_rate": 2.3323615160349855e-05, + "loss": 1.2341, + "step": 80 + }, + { + "epoch": 0.07875738350470357, + "grad_norm": 1.4866383075714111, + "learning_rate": 2.6239067055393584e-05, + "loss": 1.2338, + "step": 90 + }, + { + "epoch": 0.08750820389411507, + "grad_norm": 1.358859658241272, + "learning_rate": 2.915451895043732e-05, + "loss": 1.2331, + "step": 100 + }, + { + "epoch": 0.09625902428352658, + "grad_norm": 1.847506046295166, + "learning_rate": 3.206997084548105e-05, + "loss": 1.1628, + "step": 110 + }, + { + "epoch": 0.10500984467293809, + "grad_norm": 1.7742356061935425, + "learning_rate": 3.498542274052478e-05, + "loss": 1.1846, + "step": 120 + }, + { + "epoch": 0.1137606650623496, + "grad_norm": 1.3415714502334595, + "learning_rate": 3.790087463556852e-05, + "loss": 1.1699, + "step": 130 + }, + { + "epoch": 0.1225114854517611, + "grad_norm": 1.5319396257400513, + "learning_rate": 4.0816326530612245e-05, + "loss": 1.181, + "step": 140 + }, + { + "epoch": 0.1312623058411726, + "grad_norm": 1.3915642499923706, + "learning_rate": 4.373177842565598e-05, + "loss": 1.189, + "step": 150 + }, + { + "epoch": 0.14001312623058412, + "grad_norm": 1.175917625427246, + "learning_rate": 4.664723032069971e-05, + "loss": 1.1605, + "step": 160 + }, + { + "epoch": 0.14876394661999562, + "grad_norm": 1.3125519752502441, + "learning_rate": 4.956268221574344e-05, + "loss": 1.1734, + "step": 170 + }, + { + "epoch": 0.15751476700940714, + "grad_norm": 1.2966923713684082, + "learning_rate": 5.247813411078717e-05, + "loss": 1.2075, + "step": 180 + }, + { + "epoch": 0.16626558739881864, + "grad_norm": 1.2630099058151245, + "learning_rate": 5.539358600583091e-05, + "loss": 1.1791, + "step": 190 + }, + { + "epoch": 0.17501640778823013, + "grad_norm": 1.306665301322937, + "learning_rate": 5.830903790087464e-05, + "loss": 1.1469, + "step": 200 + }, + { + "epoch": 0.18376722817764166, + "grad_norm": 1.19467031955719, + "learning_rate": 6.122448979591838e-05, + "loss": 1.185, + "step": 210 + }, + { + "epoch": 0.19251804856705315, + "grad_norm": 1.416387677192688, + "learning_rate": 6.41399416909621e-05, + "loss": 1.2061, + "step": 220 + }, + { + "epoch": 0.20126886895646467, + "grad_norm": 1.3546264171600342, + "learning_rate": 6.705539358600583e-05, + "loss": 1.2016, + "step": 230 + }, + { + "epoch": 0.21001968934587617, + "grad_norm": 1.2417850494384766, + "learning_rate": 6.997084548104956e-05, + "loss": 1.1797, + "step": 240 + }, + { + "epoch": 0.2187705097352877, + "grad_norm": 1.2703570127487183, + "learning_rate": 7.28862973760933e-05, + "loss": 1.2059, + "step": 250 + }, + { + "epoch": 0.2275213301246992, + "grad_norm": 1.2479429244995117, + "learning_rate": 7.580174927113704e-05, + "loss": 1.1958, + "step": 260 + }, + { + "epoch": 0.23627215051411068, + "grad_norm": 1.507601261138916, + "learning_rate": 7.871720116618077e-05, + "loss": 1.2151, + "step": 270 + }, + { + "epoch": 0.2450229709035222, + "grad_norm": 1.2083854675292969, + "learning_rate": 8.163265306122449e-05, + "loss": 1.2202, + "step": 280 + }, + { + "epoch": 0.2537737912929337, + "grad_norm": 1.2939566373825073, + "learning_rate": 8.454810495626822e-05, + "loss": 1.1916, + "step": 290 + }, + { + "epoch": 0.2625246116823452, + "grad_norm": 1.2871382236480713, + "learning_rate": 8.746355685131195e-05, + "loss": 1.222, + "step": 300 + }, + { + "epoch": 0.27127543207175675, + "grad_norm": 1.1558256149291992, + "learning_rate": 9.037900874635569e-05, + "loss": 1.2094, + "step": 310 + }, + { + "epoch": 0.28002625246116825, + "grad_norm": 1.0638883113861084, + "learning_rate": 9.329446064139942e-05, + "loss": 1.2, + "step": 320 + }, + { + "epoch": 0.28877707285057974, + "grad_norm": 1.1072458028793335, + "learning_rate": 9.620991253644317e-05, + "loss": 1.224, + "step": 330 + }, + { + "epoch": 0.29752789323999124, + "grad_norm": 1.1332110166549683, + "learning_rate": 9.912536443148688e-05, + "loss": 1.2266, + "step": 340 + }, + { + "epoch": 0.30627871362940273, + "grad_norm": 1.0537033081054688, + "learning_rate": 9.999872800049233e-05, + "loss": 1.2173, + "step": 350 + }, + { + "epoch": 0.3150295340188143, + "grad_norm": 1.090928316116333, + "learning_rate": 9.999249795462235e-05, + "loss": 1.2416, + "step": 360 + }, + { + "epoch": 0.3237803544082258, + "grad_norm": 1.0084835290908813, + "learning_rate": 9.998107687592326e-05, + "loss": 1.2094, + "step": 370 + }, + { + "epoch": 0.3325311747976373, + "grad_norm": 1.82576584815979, + "learning_rate": 9.996446595031691e-05, + "loss": 1.2246, + "step": 380 + }, + { + "epoch": 0.34128199518704877, + "grad_norm": 1.2305560111999512, + "learning_rate": 9.994266690261928e-05, + "loss": 1.2647, + "step": 390 + }, + { + "epoch": 0.35003281557646027, + "grad_norm": 1.170067548751831, + "learning_rate": 9.991568199636148e-05, + "loss": 1.1829, + "step": 400 + }, + { + "epoch": 0.3587836359658718, + "grad_norm": 1.0299819707870483, + "learning_rate": 9.988351403355454e-05, + "loss": 1.2471, + "step": 410 + }, + { + "epoch": 0.3675344563552833, + "grad_norm": 0.9742593765258789, + "learning_rate": 9.98461663543987e-05, + "loss": 1.2049, + "step": 420 + }, + { + "epoch": 0.3762852767446948, + "grad_norm": 0.9377045631408691, + "learning_rate": 9.980364283693638e-05, + "loss": 1.1963, + "step": 430 + }, + { + "epoch": 0.3850360971341063, + "grad_norm": 1.0425899028778076, + "learning_rate": 9.97559478966496e-05, + "loss": 1.2167, + "step": 440 + }, + { + "epoch": 0.39378691752351785, + "grad_norm": 0.9749513864517212, + "learning_rate": 9.97030864860014e-05, + "loss": 1.2166, + "step": 450 + }, + { + "epoch": 0.40253773791292935, + "grad_norm": 1.0552780628204346, + "learning_rate": 9.964506409392176e-05, + "loss": 1.2228, + "step": 460 + }, + { + "epoch": 0.41128855830234085, + "grad_norm": 1.0261808633804321, + "learning_rate": 9.958188674523748e-05, + "loss": 1.2252, + "step": 470 + }, + { + "epoch": 0.42003937869175234, + "grad_norm": 0.9530945420265198, + "learning_rate": 9.951356100004665e-05, + "loss": 1.1845, + "step": 480 + }, + { + "epoch": 0.42879019908116384, + "grad_norm": 0.8990481495857239, + "learning_rate": 9.94400939530375e-05, + "loss": 1.2283, + "step": 490 + }, + { + "epoch": 0.4375410194705754, + "grad_norm": 0.9713592529296875, + "learning_rate": 9.936149323275169e-05, + "loss": 1.1945, + "step": 500 + }, + { + "epoch": 0.4462918398599869, + "grad_norm": 1.003854513168335, + "learning_rate": 9.927776700079216e-05, + "loss": 1.2322, + "step": 510 + }, + { + "epoch": 0.4550426602493984, + "grad_norm": 0.935400664806366, + "learning_rate": 9.918892395097572e-05, + "loss": 1.2272, + "step": 520 + }, + { + "epoch": 0.4637934806388099, + "grad_norm": 1.075519323348999, + "learning_rate": 9.90949733084303e-05, + "loss": 1.2069, + "step": 530 + }, + { + "epoch": 0.47254430102822137, + "grad_norm": 0.9949712157249451, + "learning_rate": 9.8995924828637e-05, + "loss": 1.2083, + "step": 540 + }, + { + "epoch": 0.4812951214176329, + "grad_norm": 0.8942195773124695, + "learning_rate": 9.889178879641717e-05, + "loss": 1.2137, + "step": 550 + }, + { + "epoch": 0.4900459418070444, + "grad_norm": 0.9525908827781677, + "learning_rate": 9.878257602486445e-05, + "loss": 1.2348, + "step": 560 + }, + { + "epoch": 0.4987967621964559, + "grad_norm": 0.895167350769043, + "learning_rate": 9.8668297854222e-05, + "loss": 1.2034, + "step": 570 + }, + { + "epoch": 0.5075475825858674, + "grad_norm": 1.0244312286376953, + "learning_rate": 9.854896615070495e-05, + "loss": 1.1942, + "step": 580 + }, + { + "epoch": 0.516298402975279, + "grad_norm": 0.9835163950920105, + "learning_rate": 9.842459330526826e-05, + "loss": 1.2182, + "step": 590 + }, + { + "epoch": 0.5250492233646904, + "grad_norm": 0.9238565564155579, + "learning_rate": 9.829519223232006e-05, + "loss": 1.1992, + "step": 600 + }, + { + "epoch": 0.533800043754102, + "grad_norm": 0.9063233733177185, + "learning_rate": 9.81607763683808e-05, + "loss": 1.2135, + "step": 610 + }, + { + "epoch": 0.5425508641435135, + "grad_norm": 0.9810764193534851, + "learning_rate": 9.802135967068782e-05, + "loss": 1.1909, + "step": 620 + }, + { + "epoch": 0.5513016845329249, + "grad_norm": 0.9388274550437927, + "learning_rate": 9.787695661574632e-05, + "loss": 1.1693, + "step": 630 + }, + { + "epoch": 0.5600525049223365, + "grad_norm": 0.933283805847168, + "learning_rate": 9.772758219782601e-05, + "loss": 1.1857, + "step": 640 + }, + { + "epoch": 0.5688033253117479, + "grad_norm": 0.947989284992218, + "learning_rate": 9.757325192740425e-05, + "loss": 1.1901, + "step": 650 + }, + { + "epoch": 0.5775541457011595, + "grad_norm": 0.8272686004638672, + "learning_rate": 9.741398182955548e-05, + "loss": 1.2087, + "step": 660 + }, + { + "epoch": 0.586304966090571, + "grad_norm": 0.8907813429832458, + "learning_rate": 9.724978844228717e-05, + "loss": 1.201, + "step": 670 + }, + { + "epoch": 0.5950557864799825, + "grad_norm": 0.8374966382980347, + "learning_rate": 9.708068881482271e-05, + "loss": 1.2028, + "step": 680 + }, + { + "epoch": 0.603806606869394, + "grad_norm": 0.9283761382102966, + "learning_rate": 9.690670050583095e-05, + "loss": 1.1995, + "step": 690 + }, + { + "epoch": 0.6125574272588055, + "grad_norm": 0.8573452234268188, + "learning_rate": 9.672784158160307e-05, + "loss": 1.1372, + "step": 700 + }, + { + "epoch": 0.621308247648217, + "grad_norm": 0.8831506371498108, + "learning_rate": 9.654413061417655e-05, + "loss": 1.1626, + "step": 710 + }, + { + "epoch": 0.6300590680376286, + "grad_norm": 0.9180812239646912, + "learning_rate": 9.635558667940683e-05, + "loss": 1.1466, + "step": 720 + }, + { + "epoch": 0.63880988842704, + "grad_norm": 0.8657775521278381, + "learning_rate": 9.616222935498646e-05, + "loss": 1.2052, + "step": 730 + }, + { + "epoch": 0.6475607088164516, + "grad_norm": 0.9488115310668945, + "learning_rate": 9.596407871841229e-05, + "loss": 1.1651, + "step": 740 + }, + { + "epoch": 0.656311529205863, + "grad_norm": 0.8592752814292908, + "learning_rate": 9.57611553449006e-05, + "loss": 1.1953, + "step": 750 + }, + { + "epoch": 0.6650623495952745, + "grad_norm": 0.889445960521698, + "learning_rate": 9.555348030525076e-05, + "loss": 1.1647, + "step": 760 + }, + { + "epoch": 0.6738131699846861, + "grad_norm": 0.8997176885604858, + "learning_rate": 9.534107516365725e-05, + "loss": 1.167, + "step": 770 + }, + { + "epoch": 0.6825639903740975, + "grad_norm": 0.8208065032958984, + "learning_rate": 9.512396197547053e-05, + "loss": 1.1631, + "step": 780 + }, + { + "epoch": 0.6913148107635091, + "grad_norm": 0.8419785499572754, + "learning_rate": 9.490216328490692e-05, + "loss": 1.1857, + "step": 790 + }, + { + "epoch": 0.7000656311529205, + "grad_norm": 0.8125676512718201, + "learning_rate": 9.467570212270767e-05, + "loss": 1.2426, + "step": 800 + }, + { + "epoch": 0.7088164515423321, + "grad_norm": 0.9222508072853088, + "learning_rate": 9.444460200374748e-05, + "loss": 1.1452, + "step": 810 + }, + { + "epoch": 0.7175672719317436, + "grad_norm": 0.8932722210884094, + "learning_rate": 9.420888692459291e-05, + "loss": 1.1647, + "step": 820 + }, + { + "epoch": 0.7263180923211551, + "grad_norm": 0.817932665348053, + "learning_rate": 9.396858136101066e-05, + "loss": 1.1618, + "step": 830 + }, + { + "epoch": 0.7350689127105666, + "grad_norm": 0.8717408180236816, + "learning_rate": 9.372371026542595e-05, + "loss": 1.1517, + "step": 840 + }, + { + "epoch": 0.7438197330999782, + "grad_norm": 0.8578230142593384, + "learning_rate": 9.347429906433174e-05, + "loss": 1.2009, + "step": 850 + }, + { + "epoch": 0.7525705534893896, + "grad_norm": 0.8276301622390747, + "learning_rate": 9.322037365564845e-05, + "loss": 1.1627, + "step": 860 + }, + { + "epoch": 0.7613213738788012, + "grad_norm": 0.7934173941612244, + "learning_rate": 9.296196040603475e-05, + "loss": 1.1735, + "step": 870 + }, + { + "epoch": 0.7700721942682126, + "grad_norm": 0.8270857930183411, + "learning_rate": 9.269908614814995e-05, + "loss": 1.149, + "step": 880 + }, + { + "epoch": 0.7788230146576242, + "grad_norm": 1.0632795095443726, + "learning_rate": 9.243177817786757e-05, + "loss": 1.1937, + "step": 890 + }, + { + "epoch": 0.7875738350470357, + "grad_norm": 0.8449203968048096, + "learning_rate": 9.216006425144118e-05, + "loss": 1.1787, + "step": 900 + }, + { + "epoch": 0.7963246554364471, + "grad_norm": 0.7634311318397522, + "learning_rate": 9.188397258262221e-05, + "loss": 1.1445, + "step": 910 + }, + { + "epoch": 0.8050754758258587, + "grad_norm": 0.7856956720352173, + "learning_rate": 9.160353183973046e-05, + "loss": 1.1519, + "step": 920 + }, + { + "epoch": 0.8138262962152701, + "grad_norm": 0.8162206411361694, + "learning_rate": 9.131877114267711e-05, + "loss": 1.1282, + "step": 930 + }, + { + "epoch": 0.8225771166046817, + "grad_norm": 0.8263719081878662, + "learning_rate": 9.102972005994122e-05, + "loss": 1.1127, + "step": 940 + }, + { + "epoch": 0.8313279369940932, + "grad_norm": 0.831969141960144, + "learning_rate": 9.073640860549931e-05, + "loss": 1.1446, + "step": 950 + }, + { + "epoch": 0.8400787573835047, + "grad_norm": 0.8127765655517578, + "learning_rate": 9.043886723570884e-05, + "loss": 1.1649, + "step": 960 + }, + { + "epoch": 0.8488295777729162, + "grad_norm": 0.7642777562141418, + "learning_rate": 9.013712684614582e-05, + "loss": 1.1656, + "step": 970 + }, + { + "epoch": 0.8575803981623277, + "grad_norm": 0.8071634769439697, + "learning_rate": 8.983121876839657e-05, + "loss": 1.1414, + "step": 980 + }, + { + "epoch": 0.8663312185517392, + "grad_norm": 0.7789682149887085, + "learning_rate": 8.95211747668046e-05, + "loss": 1.1127, + "step": 990 + }, + { + "epoch": 0.8750820389411508, + "grad_norm": 0.7899104356765747, + "learning_rate": 8.920702703517204e-05, + "loss": 1.1218, + "step": 1000 + }, + { + "epoch": 0.8838328593305622, + "grad_norm": 0.726874053478241, + "learning_rate": 8.888880819341702e-05, + "loss": 1.1345, + "step": 1010 + }, + { + "epoch": 0.8925836797199738, + "grad_norm": 0.8020316958427429, + "learning_rate": 8.856655128418637e-05, + "loss": 1.1229, + "step": 1020 + }, + { + "epoch": 0.9013345001093852, + "grad_norm": 0.8466740250587463, + "learning_rate": 8.824028976942465e-05, + "loss": 1.1451, + "step": 1030 + }, + { + "epoch": 0.9100853204987968, + "grad_norm": 0.7729008793830872, + "learning_rate": 8.791005752689958e-05, + "loss": 1.1204, + "step": 1040 + }, + { + "epoch": 0.9188361408882083, + "grad_norm": 0.8055347204208374, + "learning_rate": 8.757588884668434e-05, + "loss": 1.1372, + "step": 1050 + }, + { + "epoch": 0.9275869612776197, + "grad_norm": 0.8180489540100098, + "learning_rate": 8.723781842759695e-05, + "loss": 1.1632, + "step": 1060 + }, + { + "epoch": 0.9363377816670313, + "grad_norm": 0.816849946975708, + "learning_rate": 8.689588137359732e-05, + "loss": 1.1226, + "step": 1070 + }, + { + "epoch": 0.9450886020564427, + "grad_norm": 0.8028609752655029, + "learning_rate": 8.655011319014216e-05, + "loss": 1.1559, + "step": 1080 + }, + { + "epoch": 0.9538394224458543, + "grad_norm": 0.8719303011894226, + "learning_rate": 8.620054978049829e-05, + "loss": 1.1522, + "step": 1090 + }, + { + "epoch": 0.9625902428352658, + "grad_norm": 0.766177237033844, + "learning_rate": 8.584722744201447e-05, + "loss": 1.1186, + "step": 1100 + }, + { + "epoch": 0.9713410632246773, + "grad_norm": 0.7790910005569458, + "learning_rate": 8.549018286235255e-05, + "loss": 1.1227, + "step": 1110 + }, + { + "epoch": 0.9800918836140888, + "grad_norm": 0.7803717255592346, + "learning_rate": 8.512945311567786e-05, + "loss": 1.1186, + "step": 1120 + }, + { + "epoch": 0.9888427040035004, + "grad_norm": 0.7084935307502747, + "learning_rate": 8.476507565880957e-05, + "loss": 1.1085, + "step": 1130 + }, + { + "epoch": 0.9975935243929118, + "grad_norm": 0.7696670889854431, + "learning_rate": 8.439708832733142e-05, + "loss": 1.1123, + "step": 1140 + } + ], + "logging_steps": 10, + "max_steps": 3426, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500.0, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.7750297385159885e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2286/optimizer_0/.metadata b/checkpoint-2286/optimizer_0/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..93ead5017e96af57531245a5bc1c3584f63e0933 --- /dev/null +++ b/checkpoint-2286/optimizer_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2773be92fb3ede0513f2f27aca8b8ba4505a31612d614008b1aa98ee1a62a3 +size 342948 diff --git a/checkpoint-2286/optimizer_0/__0_0.distcp b/checkpoint-2286/optimizer_0/__0_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..d6b5fda73ae0463e5ba936c987bf42b8d270f409 --- /dev/null +++ b/checkpoint-2286/optimizer_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043869a496a8ff7ce40f8fad38d8a7ef1933dd31415eb2078e48c9ef58be892c +size 2472090861 diff --git a/checkpoint-2286/optimizer_0/__1_0.distcp b/checkpoint-2286/optimizer_0/__1_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..740a9b5a196d7be0a1fb9f3e8474885d5e5a7187 --- /dev/null +++ b/checkpoint-2286/optimizer_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fd1038dc14d3be310e17d4574716f78685a9264608f7471a5ccb2a9645a17c +size 2472174123 diff --git a/checkpoint-2286/optimizer_0/__2_0.distcp b/checkpoint-2286/optimizer_0/__2_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..94626d88f20ecf6615ded6f3fe4398fcc042fbdd --- /dev/null +++ b/checkpoint-2286/optimizer_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448b99f03997542f61a57d0f9c79ac7eb0c54df43a61ec6e86b4cb17dac21393 +size 2472182518 diff --git a/checkpoint-2286/optimizer_0/__3_0.distcp b/checkpoint-2286/optimizer_0/__3_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..fad37dc634e73f91f77cb9fc8be0e858be9eda2c --- /dev/null +++ b/checkpoint-2286/optimizer_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135cfa2dd2b8dfd4e579dd4959853708428ac877d4337968a4c3cd6c50f6cb0b +size 2472179190 diff --git a/checkpoint-2286/pytorch_model_fsdp_0/.metadata b/checkpoint-2286/pytorch_model_fsdp_0/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..1d1d1b7e1411e5c44bed2c9de4dce3edb24b4798 --- /dev/null +++ b/checkpoint-2286/pytorch_model_fsdp_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b22471600c91452508b6a9f609effd598701ef136ebd4135b1feb8d1638ce1 +size 129152 diff --git a/checkpoint-2286/pytorch_model_fsdp_0/__0_0.distcp b/checkpoint-2286/pytorch_model_fsdp_0/__0_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..c3a3f4d22c44489a961cbf9a5103185a495c3536 --- /dev/null +++ b/checkpoint-2286/pytorch_model_fsdp_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81144f312eb9afd64fa13c0ec7eb578328a0ce3544aa94899a7423a6df0f36bb +size 1498714507 diff --git a/checkpoint-2286/pytorch_model_fsdp_0/__1_0.distcp b/checkpoint-2286/pytorch_model_fsdp_0/__1_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..1e7dab9fc77d94782e3f61fbc3aff1e003cedeaf --- /dev/null +++ b/checkpoint-2286/pytorch_model_fsdp_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07cf921bee5c72ddd159fcc15162e0dcbe6089064e9a3c9967163eb73da239b7 +size 1498714507 diff --git a/checkpoint-2286/pytorch_model_fsdp_0/__2_0.distcp b/checkpoint-2286/pytorch_model_fsdp_0/__2_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..317cb16e6776eb912e946eeab337f95a869ff83e --- /dev/null +++ b/checkpoint-2286/pytorch_model_fsdp_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781a06015c2f4ff6faf67c5b24b33b23910cca0723b44d8c4614801f67d4c81f +size 1498714507 diff --git a/checkpoint-2286/pytorch_model_fsdp_0/__3_0.distcp b/checkpoint-2286/pytorch_model_fsdp_0/__3_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..d86db16c3b940509a3fad53efcec7aeaf980023e --- /dev/null +++ b/checkpoint-2286/pytorch_model_fsdp_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f55166c0572f422cc31f2f6f435ba6777a2e7d1440ea2ff0397d2d6b571d7374 +size 1498714507 diff --git a/checkpoint-2286/rng_state_0.pth b/checkpoint-2286/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..25b27f3d8d0be9bbfdcb45cc41d51ce36be94aaa --- /dev/null +++ b/checkpoint-2286/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eee49a2ad561e75c5f0f3e8056308fc27088e19e19620813602767a759d8e5a +size 15429 diff --git a/checkpoint-2286/rng_state_1.pth b/checkpoint-2286/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..381e9a1375ad7446430d932c0ba5979e747fd2f7 --- /dev/null +++ b/checkpoint-2286/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34c5da13614815d740bb91790974fffad60cd4e1e61540d824668f639ceb8c4 +size 15429 diff --git a/checkpoint-2286/rng_state_2.pth b/checkpoint-2286/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ab6bb892e6a0dfb9c48863dc28623c29bac47f8 --- /dev/null +++ b/checkpoint-2286/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cf36eb77e76f4d60fcc92f3755828769fe8aab6a2ca29f9573827e93d0c9f5 +size 15429 diff --git a/checkpoint-2286/rng_state_3.pth b/checkpoint-2286/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef30087d016d97eae53b0cd40498b5c8dee4c1b1 --- /dev/null +++ b/checkpoint-2286/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5001f16e2075ef4f6a1c0dbc75d9121e1906a36d5ad35279fed02e36a6c7d13 +size 15429 diff --git a/checkpoint-2286/scheduler.pt b/checkpoint-2286/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b2bf93b04dda90fa2e85abec92148181f4ead9c8 --- /dev/null +++ b/checkpoint-2286/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c78e6d56e32e42431584c89e071a6b0fbafa0beb69a4fcc15d1b8ed5f44422 +size 1465 diff --git a/checkpoint-2286/trainer_state.json b/checkpoint-2286/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..8ac29d15684765929ac1d8e47a54d8fbf52740fe --- /dev/null +++ b/checkpoint-2286/trainer_state.json @@ -0,0 +1,1644 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 2286, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0, + "eval_loss": 2.1641297340393066, + "eval_runtime": 4.2967, + "eval_samples_per_second": 4.655, + "eval_steps_per_second": 0.465, + "step": 0 + }, + { + "epoch": 0.0008750820389411508, + "grad_norm": 6.37307071685791, + "learning_rate": 2.915451895043732e-07, + "loss": 1.6434, + "step": 1 + }, + { + "epoch": 0.008750820389411508, + "grad_norm": 4.0545759201049805, + "learning_rate": 2.915451895043732e-06, + "loss": 1.6965, + "step": 10 + }, + { + "epoch": 0.017501640778823015, + "grad_norm": 2.363191604614258, + "learning_rate": 5.830903790087464e-06, + "loss": 1.5272, + "step": 20 + }, + { + "epoch": 0.02625246116823452, + "grad_norm": 1.6348848342895508, + "learning_rate": 8.746355685131195e-06, + "loss": 1.389, + "step": 30 + }, + { + "epoch": 0.03500328155764603, + "grad_norm": 1.6716902256011963, + "learning_rate": 1.1661807580174927e-05, + "loss": 1.348, + "step": 40 + }, + { + "epoch": 0.04375410194705753, + "grad_norm": 1.510228157043457, + "learning_rate": 1.457725947521866e-05, + "loss": 1.2997, + "step": 50 + }, + { + "epoch": 0.05250492233646904, + "grad_norm": 1.6153247356414795, + "learning_rate": 1.749271137026239e-05, + "loss": 1.2665, + "step": 60 + }, + { + "epoch": 0.06125574272588055, + "grad_norm": 1.446387767791748, + "learning_rate": 2.0408163265306123e-05, + "loss": 1.237, + "step": 70 + }, + { + "epoch": 0.07000656311529206, + "grad_norm": 1.3039863109588623, + "learning_rate": 2.3323615160349855e-05, + "loss": 1.2341, + "step": 80 + }, + { + "epoch": 0.07875738350470357, + "grad_norm": 1.4866383075714111, + "learning_rate": 2.6239067055393584e-05, + "loss": 1.2338, + "step": 90 + }, + { + "epoch": 0.08750820389411507, + "grad_norm": 1.358859658241272, + "learning_rate": 2.915451895043732e-05, + "loss": 1.2331, + "step": 100 + }, + { + "epoch": 0.09625902428352658, + "grad_norm": 1.847506046295166, + "learning_rate": 3.206997084548105e-05, + "loss": 1.1628, + "step": 110 + }, + { + "epoch": 0.10500984467293809, + "grad_norm": 1.7742356061935425, + "learning_rate": 3.498542274052478e-05, + "loss": 1.1846, + "step": 120 + }, + { + "epoch": 0.1137606650623496, + "grad_norm": 1.3415714502334595, + "learning_rate": 3.790087463556852e-05, + "loss": 1.1699, + "step": 130 + }, + { + "epoch": 0.1225114854517611, + "grad_norm": 1.5319396257400513, + "learning_rate": 4.0816326530612245e-05, + "loss": 1.181, + "step": 140 + }, + { + "epoch": 0.1312623058411726, + "grad_norm": 1.3915642499923706, + "learning_rate": 4.373177842565598e-05, + "loss": 1.189, + "step": 150 + }, + { + "epoch": 0.14001312623058412, + "grad_norm": 1.175917625427246, + "learning_rate": 4.664723032069971e-05, + "loss": 1.1605, + "step": 160 + }, + { + "epoch": 0.14876394661999562, + "grad_norm": 1.3125519752502441, + "learning_rate": 4.956268221574344e-05, + "loss": 1.1734, + "step": 170 + }, + { + "epoch": 0.15751476700940714, + "grad_norm": 1.2966923713684082, + "learning_rate": 5.247813411078717e-05, + "loss": 1.2075, + "step": 180 + }, + { + "epoch": 0.16626558739881864, + "grad_norm": 1.2630099058151245, + "learning_rate": 5.539358600583091e-05, + "loss": 1.1791, + "step": 190 + }, + { + "epoch": 0.17501640778823013, + "grad_norm": 1.306665301322937, + "learning_rate": 5.830903790087464e-05, + "loss": 1.1469, + "step": 200 + }, + { + "epoch": 0.18376722817764166, + "grad_norm": 1.19467031955719, + "learning_rate": 6.122448979591838e-05, + "loss": 1.185, + "step": 210 + }, + { + "epoch": 0.19251804856705315, + "grad_norm": 1.416387677192688, + "learning_rate": 6.41399416909621e-05, + "loss": 1.2061, + "step": 220 + }, + { + "epoch": 0.20126886895646467, + "grad_norm": 1.3546264171600342, + "learning_rate": 6.705539358600583e-05, + "loss": 1.2016, + "step": 230 + }, + { + "epoch": 0.21001968934587617, + "grad_norm": 1.2417850494384766, + "learning_rate": 6.997084548104956e-05, + "loss": 1.1797, + "step": 240 + }, + { + "epoch": 0.2187705097352877, + "grad_norm": 1.2703570127487183, + "learning_rate": 7.28862973760933e-05, + "loss": 1.2059, + "step": 250 + }, + { + "epoch": 0.2275213301246992, + "grad_norm": 1.2479429244995117, + "learning_rate": 7.580174927113704e-05, + "loss": 1.1958, + "step": 260 + }, + { + "epoch": 0.23627215051411068, + "grad_norm": 1.507601261138916, + "learning_rate": 7.871720116618077e-05, + "loss": 1.2151, + "step": 270 + }, + { + "epoch": 0.2450229709035222, + "grad_norm": 1.2083854675292969, + "learning_rate": 8.163265306122449e-05, + "loss": 1.2202, + "step": 280 + }, + { + "epoch": 0.2537737912929337, + "grad_norm": 1.2939566373825073, + "learning_rate": 8.454810495626822e-05, + "loss": 1.1916, + "step": 290 + }, + { + "epoch": 0.2625246116823452, + "grad_norm": 1.2871382236480713, + "learning_rate": 8.746355685131195e-05, + "loss": 1.222, + "step": 300 + }, + { + "epoch": 0.27127543207175675, + "grad_norm": 1.1558256149291992, + "learning_rate": 9.037900874635569e-05, + "loss": 1.2094, + "step": 310 + }, + { + "epoch": 0.28002625246116825, + "grad_norm": 1.0638883113861084, + "learning_rate": 9.329446064139942e-05, + "loss": 1.2, + "step": 320 + }, + { + "epoch": 0.28877707285057974, + "grad_norm": 1.1072458028793335, + "learning_rate": 9.620991253644317e-05, + "loss": 1.224, + "step": 330 + }, + { + "epoch": 0.29752789323999124, + "grad_norm": 1.1332110166549683, + "learning_rate": 9.912536443148688e-05, + "loss": 1.2266, + "step": 340 + }, + { + "epoch": 0.30627871362940273, + "grad_norm": 1.0537033081054688, + "learning_rate": 9.999872800049233e-05, + "loss": 1.2173, + "step": 350 + }, + { + "epoch": 0.3150295340188143, + "grad_norm": 1.090928316116333, + "learning_rate": 9.999249795462235e-05, + "loss": 1.2416, + "step": 360 + }, + { + "epoch": 0.3237803544082258, + "grad_norm": 1.0084835290908813, + "learning_rate": 9.998107687592326e-05, + "loss": 1.2094, + "step": 370 + }, + { + "epoch": 0.3325311747976373, + "grad_norm": 1.82576584815979, + "learning_rate": 9.996446595031691e-05, + "loss": 1.2246, + "step": 380 + }, + { + "epoch": 0.34128199518704877, + "grad_norm": 1.2305560111999512, + "learning_rate": 9.994266690261928e-05, + "loss": 1.2647, + "step": 390 + }, + { + "epoch": 0.35003281557646027, + "grad_norm": 1.170067548751831, + "learning_rate": 9.991568199636148e-05, + "loss": 1.1829, + "step": 400 + }, + { + "epoch": 0.3587836359658718, + "grad_norm": 1.0299819707870483, + "learning_rate": 9.988351403355454e-05, + "loss": 1.2471, + "step": 410 + }, + { + "epoch": 0.3675344563552833, + "grad_norm": 0.9742593765258789, + "learning_rate": 9.98461663543987e-05, + "loss": 1.2049, + "step": 420 + }, + { + "epoch": 0.3762852767446948, + "grad_norm": 0.9377045631408691, + "learning_rate": 9.980364283693638e-05, + "loss": 1.1963, + "step": 430 + }, + { + "epoch": 0.3850360971341063, + "grad_norm": 1.0425899028778076, + "learning_rate": 9.97559478966496e-05, + "loss": 1.2167, + "step": 440 + }, + { + "epoch": 0.39378691752351785, + "grad_norm": 0.9749513864517212, + "learning_rate": 9.97030864860014e-05, + "loss": 1.2166, + "step": 450 + }, + { + "epoch": 0.40253773791292935, + "grad_norm": 1.0552780628204346, + "learning_rate": 9.964506409392176e-05, + "loss": 1.2228, + "step": 460 + }, + { + "epoch": 0.41128855830234085, + "grad_norm": 1.0261808633804321, + "learning_rate": 9.958188674523748e-05, + "loss": 1.2252, + "step": 470 + }, + { + "epoch": 0.42003937869175234, + "grad_norm": 0.9530945420265198, + "learning_rate": 9.951356100004665e-05, + "loss": 1.1845, + "step": 480 + }, + { + "epoch": 0.42879019908116384, + "grad_norm": 0.8990481495857239, + "learning_rate": 9.94400939530375e-05, + "loss": 1.2283, + "step": 490 + }, + { + "epoch": 0.4375410194705754, + "grad_norm": 0.9713592529296875, + "learning_rate": 9.936149323275169e-05, + "loss": 1.1945, + "step": 500 + }, + { + "epoch": 0.4462918398599869, + "grad_norm": 1.003854513168335, + "learning_rate": 9.927776700079216e-05, + "loss": 1.2322, + "step": 510 + }, + { + "epoch": 0.4550426602493984, + "grad_norm": 0.935400664806366, + "learning_rate": 9.918892395097572e-05, + "loss": 1.2272, + "step": 520 + }, + { + "epoch": 0.4637934806388099, + "grad_norm": 1.075519323348999, + "learning_rate": 9.90949733084303e-05, + "loss": 1.2069, + "step": 530 + }, + { + "epoch": 0.47254430102822137, + "grad_norm": 0.9949712157249451, + "learning_rate": 9.8995924828637e-05, + "loss": 1.2083, + "step": 540 + }, + { + "epoch": 0.4812951214176329, + "grad_norm": 0.8942195773124695, + "learning_rate": 9.889178879641717e-05, + "loss": 1.2137, + "step": 550 + }, + { + "epoch": 0.4900459418070444, + "grad_norm": 0.9525908827781677, + "learning_rate": 9.878257602486445e-05, + "loss": 1.2348, + "step": 560 + }, + { + "epoch": 0.4987967621964559, + "grad_norm": 0.895167350769043, + "learning_rate": 9.8668297854222e-05, + "loss": 1.2034, + "step": 570 + }, + { + "epoch": 0.5075475825858674, + "grad_norm": 1.0244312286376953, + "learning_rate": 9.854896615070495e-05, + "loss": 1.1942, + "step": 580 + }, + { + "epoch": 0.516298402975279, + "grad_norm": 0.9835163950920105, + "learning_rate": 9.842459330526826e-05, + "loss": 1.2182, + "step": 590 + }, + { + "epoch": 0.5250492233646904, + "grad_norm": 0.9238565564155579, + "learning_rate": 9.829519223232006e-05, + "loss": 1.1992, + "step": 600 + }, + { + "epoch": 0.533800043754102, + "grad_norm": 0.9063233733177185, + "learning_rate": 9.81607763683808e-05, + "loss": 1.2135, + "step": 610 + }, + { + "epoch": 0.5425508641435135, + "grad_norm": 0.9810764193534851, + "learning_rate": 9.802135967068782e-05, + "loss": 1.1909, + "step": 620 + }, + { + "epoch": 0.5513016845329249, + "grad_norm": 0.9388274550437927, + "learning_rate": 9.787695661574632e-05, + "loss": 1.1693, + "step": 630 + }, + { + "epoch": 0.5600525049223365, + "grad_norm": 0.933283805847168, + "learning_rate": 9.772758219782601e-05, + "loss": 1.1857, + "step": 640 + }, + { + "epoch": 0.5688033253117479, + "grad_norm": 0.947989284992218, + "learning_rate": 9.757325192740425e-05, + "loss": 1.1901, + "step": 650 + }, + { + "epoch": 0.5775541457011595, + "grad_norm": 0.8272686004638672, + "learning_rate": 9.741398182955548e-05, + "loss": 1.2087, + "step": 660 + }, + { + "epoch": 0.586304966090571, + "grad_norm": 0.8907813429832458, + "learning_rate": 9.724978844228717e-05, + "loss": 1.201, + "step": 670 + }, + { + "epoch": 0.5950557864799825, + "grad_norm": 0.8374966382980347, + "learning_rate": 9.708068881482271e-05, + "loss": 1.2028, + "step": 680 + }, + { + "epoch": 0.603806606869394, + "grad_norm": 0.9283761382102966, + "learning_rate": 9.690670050583095e-05, + "loss": 1.1995, + "step": 690 + }, + { + "epoch": 0.6125574272588055, + "grad_norm": 0.8573452234268188, + "learning_rate": 9.672784158160307e-05, + "loss": 1.1372, + "step": 700 + }, + { + "epoch": 0.621308247648217, + "grad_norm": 0.8831506371498108, + "learning_rate": 9.654413061417655e-05, + "loss": 1.1626, + "step": 710 + }, + { + "epoch": 0.6300590680376286, + "grad_norm": 0.9180812239646912, + "learning_rate": 9.635558667940683e-05, + "loss": 1.1466, + "step": 720 + }, + { + "epoch": 0.63880988842704, + "grad_norm": 0.8657775521278381, + "learning_rate": 9.616222935498646e-05, + "loss": 1.2052, + "step": 730 + }, + { + "epoch": 0.6475607088164516, + "grad_norm": 0.9488115310668945, + "learning_rate": 9.596407871841229e-05, + "loss": 1.1651, + "step": 740 + }, + { + "epoch": 0.656311529205863, + "grad_norm": 0.8592752814292908, + "learning_rate": 9.57611553449006e-05, + "loss": 1.1953, + "step": 750 + }, + { + "epoch": 0.6650623495952745, + "grad_norm": 0.889445960521698, + "learning_rate": 9.555348030525076e-05, + "loss": 1.1647, + "step": 760 + }, + { + "epoch": 0.6738131699846861, + "grad_norm": 0.8997176885604858, + "learning_rate": 9.534107516365725e-05, + "loss": 1.167, + "step": 770 + }, + { + "epoch": 0.6825639903740975, + "grad_norm": 0.8208065032958984, + "learning_rate": 9.512396197547053e-05, + "loss": 1.1631, + "step": 780 + }, + { + "epoch": 0.6913148107635091, + "grad_norm": 0.8419785499572754, + "learning_rate": 9.490216328490692e-05, + "loss": 1.1857, + "step": 790 + }, + { + "epoch": 0.7000656311529205, + "grad_norm": 0.8125676512718201, + "learning_rate": 9.467570212270767e-05, + "loss": 1.2426, + "step": 800 + }, + { + "epoch": 0.7088164515423321, + "grad_norm": 0.9222508072853088, + "learning_rate": 9.444460200374748e-05, + "loss": 1.1452, + "step": 810 + }, + { + "epoch": 0.7175672719317436, + "grad_norm": 0.8932722210884094, + "learning_rate": 9.420888692459291e-05, + "loss": 1.1647, + "step": 820 + }, + { + "epoch": 0.7263180923211551, + "grad_norm": 0.817932665348053, + "learning_rate": 9.396858136101066e-05, + "loss": 1.1618, + "step": 830 + }, + { + "epoch": 0.7350689127105666, + "grad_norm": 0.8717408180236816, + "learning_rate": 9.372371026542595e-05, + "loss": 1.1517, + "step": 840 + }, + { + "epoch": 0.7438197330999782, + "grad_norm": 0.8578230142593384, + "learning_rate": 9.347429906433174e-05, + "loss": 1.2009, + "step": 850 + }, + { + "epoch": 0.7525705534893896, + "grad_norm": 0.8276301622390747, + "learning_rate": 9.322037365564845e-05, + "loss": 1.1627, + "step": 860 + }, + { + "epoch": 0.7613213738788012, + "grad_norm": 0.7934173941612244, + "learning_rate": 9.296196040603475e-05, + "loss": 1.1735, + "step": 870 + }, + { + "epoch": 0.7700721942682126, + "grad_norm": 0.8270857930183411, + "learning_rate": 9.269908614814995e-05, + "loss": 1.149, + "step": 880 + }, + { + "epoch": 0.7788230146576242, + "grad_norm": 1.0632795095443726, + "learning_rate": 9.243177817786757e-05, + "loss": 1.1937, + "step": 890 + }, + { + "epoch": 0.7875738350470357, + "grad_norm": 0.8449203968048096, + "learning_rate": 9.216006425144118e-05, + "loss": 1.1787, + "step": 900 + }, + { + "epoch": 0.7963246554364471, + "grad_norm": 0.7634311318397522, + "learning_rate": 9.188397258262221e-05, + "loss": 1.1445, + "step": 910 + }, + { + "epoch": 0.8050754758258587, + "grad_norm": 0.7856956720352173, + "learning_rate": 9.160353183973046e-05, + "loss": 1.1519, + "step": 920 + }, + { + "epoch": 0.8138262962152701, + "grad_norm": 0.8162206411361694, + "learning_rate": 9.131877114267711e-05, + "loss": 1.1282, + "step": 930 + }, + { + "epoch": 0.8225771166046817, + "grad_norm": 0.8263719081878662, + "learning_rate": 9.102972005994122e-05, + "loss": 1.1127, + "step": 940 + }, + { + "epoch": 0.8313279369940932, + "grad_norm": 0.831969141960144, + "learning_rate": 9.073640860549931e-05, + "loss": 1.1446, + "step": 950 + }, + { + "epoch": 0.8400787573835047, + "grad_norm": 0.8127765655517578, + "learning_rate": 9.043886723570884e-05, + "loss": 1.1649, + "step": 960 + }, + { + "epoch": 0.8488295777729162, + "grad_norm": 0.7642777562141418, + "learning_rate": 9.013712684614582e-05, + "loss": 1.1656, + "step": 970 + }, + { + "epoch": 0.8575803981623277, + "grad_norm": 0.8071634769439697, + "learning_rate": 8.983121876839657e-05, + "loss": 1.1414, + "step": 980 + }, + { + "epoch": 0.8663312185517392, + "grad_norm": 0.7789682149887085, + "learning_rate": 8.95211747668046e-05, + "loss": 1.1127, + "step": 990 + }, + { + "epoch": 0.8750820389411508, + "grad_norm": 0.7899104356765747, + "learning_rate": 8.920702703517204e-05, + "loss": 1.1218, + "step": 1000 + }, + { + "epoch": 0.8838328593305622, + "grad_norm": 0.726874053478241, + "learning_rate": 8.888880819341702e-05, + "loss": 1.1345, + "step": 1010 + }, + { + "epoch": 0.8925836797199738, + "grad_norm": 0.8020316958427429, + "learning_rate": 8.856655128418637e-05, + "loss": 1.1229, + "step": 1020 + }, + { + "epoch": 0.9013345001093852, + "grad_norm": 0.8466740250587463, + "learning_rate": 8.824028976942465e-05, + "loss": 1.1451, + "step": 1030 + }, + { + "epoch": 0.9100853204987968, + "grad_norm": 0.7729008793830872, + "learning_rate": 8.791005752689958e-05, + "loss": 1.1204, + "step": 1040 + }, + { + "epoch": 0.9188361408882083, + "grad_norm": 0.8055347204208374, + "learning_rate": 8.757588884668434e-05, + "loss": 1.1372, + "step": 1050 + }, + { + "epoch": 0.9275869612776197, + "grad_norm": 0.8180489540100098, + "learning_rate": 8.723781842759695e-05, + "loss": 1.1632, + "step": 1060 + }, + { + "epoch": 0.9363377816670313, + "grad_norm": 0.816849946975708, + "learning_rate": 8.689588137359732e-05, + "loss": 1.1226, + "step": 1070 + }, + { + "epoch": 0.9450886020564427, + "grad_norm": 0.8028609752655029, + "learning_rate": 8.655011319014216e-05, + "loss": 1.1559, + "step": 1080 + }, + { + "epoch": 0.9538394224458543, + "grad_norm": 0.8719303011894226, + "learning_rate": 8.620054978049829e-05, + "loss": 1.1522, + "step": 1090 + }, + { + "epoch": 0.9625902428352658, + "grad_norm": 0.766177237033844, + "learning_rate": 8.584722744201447e-05, + "loss": 1.1186, + "step": 1100 + }, + { + "epoch": 0.9713410632246773, + "grad_norm": 0.7790910005569458, + "learning_rate": 8.549018286235255e-05, + "loss": 1.1227, + "step": 1110 + }, + { + "epoch": 0.9800918836140888, + "grad_norm": 0.7803717255592346, + "learning_rate": 8.512945311567786e-05, + "loss": 1.1186, + "step": 1120 + }, + { + "epoch": 0.9888427040035004, + "grad_norm": 0.7084935307502747, + "learning_rate": 8.476507565880957e-05, + "loss": 1.1085, + "step": 1130 + }, + { + "epoch": 0.9975935243929118, + "grad_norm": 0.7696670889854431, + "learning_rate": 8.439708832733142e-05, + "loss": 1.1123, + "step": 1140 + }, + { + "epoch": 1.006125574272588, + "grad_norm": 0.9948705434799194, + "learning_rate": 8.402552933166288e-05, + "loss": 0.9984, + "step": 1150 + }, + { + "epoch": 1.0148763946619996, + "grad_norm": 0.8488800525665283, + "learning_rate": 8.36504372530916e-05, + "loss": 0.9603, + "step": 1160 + }, + { + "epoch": 1.023627215051411, + "grad_norm": 0.8748326897621155, + "learning_rate": 8.32718510397673e-05, + "loss": 0.9535, + "step": 1170 + }, + { + "epoch": 1.0323780354408225, + "grad_norm": 0.8636799454689026, + "learning_rate": 8.288981000265748e-05, + "loss": 0.9705, + "step": 1180 + }, + { + "epoch": 1.041128855830234, + "grad_norm": 0.7722444534301758, + "learning_rate": 8.250435381146549e-05, + "loss": 0.9411, + "step": 1190 + }, + { + "epoch": 1.0498796762196456, + "grad_norm": 0.792931318283081, + "learning_rate": 8.211552249051149e-05, + "loss": 0.9455, + "step": 1200 + }, + { + "epoch": 1.0586304966090572, + "grad_norm": 0.8179608583450317, + "learning_rate": 8.17233564145764e-05, + "loss": 0.9418, + "step": 1210 + }, + { + "epoch": 1.0673813169984685, + "grad_norm": 0.8081513047218323, + "learning_rate": 8.132789630470952e-05, + "loss": 0.9451, + "step": 1220 + }, + { + "epoch": 1.07613213738788, + "grad_norm": 0.8941613435745239, + "learning_rate": 8.092918322400027e-05, + "loss": 0.9336, + "step": 1230 + }, + { + "epoch": 1.0848829577772916, + "grad_norm": 0.8505945801734924, + "learning_rate": 8.052725857331429e-05, + "loss": 0.9432, + "step": 1240 + }, + { + "epoch": 1.0936337781667032, + "grad_norm": 0.7953508496284485, + "learning_rate": 8.012216408699455e-05, + "loss": 0.9608, + "step": 1250 + }, + { + "epoch": 1.1023845985561147, + "grad_norm": 0.9065775871276855, + "learning_rate": 7.971394182852789e-05, + "loss": 0.9583, + "step": 1260 + }, + { + "epoch": 1.1111354189455263, + "grad_norm": 0.8752979040145874, + "learning_rate": 7.930263418617713e-05, + "loss": 0.9752, + "step": 1270 + }, + { + "epoch": 1.1198862393349376, + "grad_norm": 0.8173210024833679, + "learning_rate": 7.888828386857985e-05, + "loss": 0.9505, + "step": 1280 + }, + { + "epoch": 1.1286370597243491, + "grad_norm": 0.7964232563972473, + "learning_rate": 7.84709339003135e-05, + "loss": 0.9346, + "step": 1290 + }, + { + "epoch": 1.1373878801137607, + "grad_norm": 0.8364039063453674, + "learning_rate": 7.805062761742799e-05, + "loss": 0.9606, + "step": 1300 + }, + { + "epoch": 1.1461387005031722, + "grad_norm": 0.8122743964195251, + "learning_rate": 7.76274086629458e-05, + "loss": 0.9455, + "step": 1310 + }, + { + "epoch": 1.1548895208925836, + "grad_norm": 0.8229530453681946, + "learning_rate": 7.720132098233031e-05, + "loss": 0.9465, + "step": 1320 + }, + { + "epoch": 1.1636403412819951, + "grad_norm": 0.7859545946121216, + "learning_rate": 7.677240881892258e-05, + "loss": 0.9421, + "step": 1330 + }, + { + "epoch": 1.1723911616714067, + "grad_norm": 0.8277194499969482, + "learning_rate": 7.634071670934734e-05, + "loss": 0.9541, + "step": 1340 + }, + { + "epoch": 1.1811419820608182, + "grad_norm": 0.7695391774177551, + "learning_rate": 7.590628947888847e-05, + "loss": 0.9433, + "step": 1350 + }, + { + "epoch": 1.1898928024502298, + "grad_norm": 0.82956862449646, + "learning_rate": 7.546917223683453e-05, + "loss": 0.9395, + "step": 1360 + }, + { + "epoch": 1.1986436228396413, + "grad_norm": 0.8398957252502441, + "learning_rate": 7.502941037179474e-05, + "loss": 0.9432, + "step": 1370 + }, + { + "epoch": 1.2073944432290526, + "grad_norm": 0.8232219219207764, + "learning_rate": 7.4587049546986e-05, + "loss": 0.9887, + "step": 1380 + }, + { + "epoch": 1.2161452636184642, + "grad_norm": 0.7886401414871216, + "learning_rate": 7.414213569549145e-05, + "loss": 0.959, + "step": 1390 + }, + { + "epoch": 1.2248960840078758, + "grad_norm": 0.7588061690330505, + "learning_rate": 7.369471501549087e-05, + "loss": 0.9651, + "step": 1400 + }, + { + "epoch": 1.2336469043972873, + "grad_norm": 0.8234547972679138, + "learning_rate": 7.324483396546371e-05, + "loss": 0.9935, + "step": 1410 + }, + { + "epoch": 1.2423977247866986, + "grad_norm": 0.7623049020767212, + "learning_rate": 7.279253925936498e-05, + "loss": 0.95, + "step": 1420 + }, + { + "epoch": 1.2511485451761102, + "grad_norm": 0.7172533869743347, + "learning_rate": 7.233787786177464e-05, + "loss": 0.9441, + "step": 1430 + }, + { + "epoch": 1.2598993655655217, + "grad_norm": 0.7973024249076843, + "learning_rate": 7.188089698302098e-05, + "loss": 0.9682, + "step": 1440 + }, + { + "epoch": 1.2686501859549333, + "grad_norm": 0.7969169020652771, + "learning_rate": 7.14216440742785e-05, + "loss": 0.9541, + "step": 1450 + }, + { + "epoch": 1.2774010063443448, + "grad_norm": 0.8296008110046387, + "learning_rate": 7.096016682264074e-05, + "loss": 0.9597, + "step": 1460 + }, + { + "epoch": 1.2861518267337564, + "grad_norm": 0.8538773655891418, + "learning_rate": 7.049651314616862e-05, + "loss": 0.9225, + "step": 1470 + }, + { + "epoch": 1.2949026471231677, + "grad_norm": 0.8068443536758423, + "learning_rate": 7.003073118891487e-05, + "loss": 0.9282, + "step": 1480 + }, + { + "epoch": 1.3036534675125793, + "grad_norm": 0.8286350965499878, + "learning_rate": 6.956286931592481e-05, + "loss": 0.9645, + "step": 1490 + }, + { + "epoch": 1.3124042879019908, + "grad_norm": 0.796650767326355, + "learning_rate": 6.909297610821443e-05, + "loss": 0.934, + "step": 1500 + }, + { + "epoch": 1.3211551082914024, + "grad_norm": 0.7479636073112488, + "learning_rate": 6.862110035772589e-05, + "loss": 0.9319, + "step": 1510 + }, + { + "epoch": 1.3299059286808137, + "grad_norm": 0.7734546065330505, + "learning_rate": 6.81472910622611e-05, + "loss": 0.9577, + "step": 1520 + }, + { + "epoch": 1.3386567490702252, + "grad_norm": 0.821553647518158, + "learning_rate": 6.7671597420394e-05, + "loss": 0.966, + "step": 1530 + }, + { + "epoch": 1.3474075694596368, + "grad_norm": 0.8141497373580933, + "learning_rate": 6.719406882636196e-05, + "loss": 0.9593, + "step": 1540 + }, + { + "epoch": 1.3561583898490484, + "grad_norm": 0.7738481163978577, + "learning_rate": 6.671475486493691e-05, + "loss": 0.9474, + "step": 1550 + }, + { + "epoch": 1.36490921023846, + "grad_norm": 0.7933306694030762, + "learning_rate": 6.62337053062766e-05, + "loss": 0.9297, + "step": 1560 + }, + { + "epoch": 1.3736600306278715, + "grad_norm": 0.7921035885810852, + "learning_rate": 6.575097010075664e-05, + "loss": 0.9283, + "step": 1570 + }, + { + "epoch": 1.382410851017283, + "grad_norm": 0.7895304560661316, + "learning_rate": 6.526659937378392e-05, + "loss": 0.9559, + "step": 1580 + }, + { + "epoch": 1.3911616714066943, + "grad_norm": 0.8518770933151245, + "learning_rate": 6.478064342059164e-05, + "loss": 0.9571, + "step": 1590 + }, + { + "epoch": 1.3999124917961059, + "grad_norm": 0.8479484915733337, + "learning_rate": 6.429315270101701e-05, + "loss": 0.9578, + "step": 1600 + }, + { + "epoch": 1.4086633121855174, + "grad_norm": 0.763520359992981, + "learning_rate": 6.380417783426153e-05, + "loss": 0.9304, + "step": 1610 + }, + { + "epoch": 1.4174141325749288, + "grad_norm": 0.7657537460327148, + "learning_rate": 6.3313769593635e-05, + "loss": 0.9541, + "step": 1620 + }, + { + "epoch": 1.4261649529643403, + "grad_norm": 0.7461577653884888, + "learning_rate": 6.282197890128338e-05, + "loss": 0.9331, + "step": 1630 + }, + { + "epoch": 1.4349157733537519, + "grad_norm": 0.7814643383026123, + "learning_rate": 6.23288568229012e-05, + "loss": 0.9431, + "step": 1640 + }, + { + "epoch": 1.4436665937431634, + "grad_norm": 0.7600048184394836, + "learning_rate": 6.183445456242904e-05, + "loss": 0.9549, + "step": 1650 + }, + { + "epoch": 1.452417414132575, + "grad_norm": 0.7684770226478577, + "learning_rate": 6.13388234567369e-05, + "loss": 0.9074, + "step": 1660 + }, + { + "epoch": 1.4611682345219865, + "grad_norm": 0.7696465849876404, + "learning_rate": 6.084201497029333e-05, + "loss": 0.9449, + "step": 1670 + }, + { + "epoch": 1.469919054911398, + "grad_norm": 0.818397045135498, + "learning_rate": 6.034408068982172e-05, + "loss": 0.9396, + "step": 1680 + }, + { + "epoch": 1.4786698753008094, + "grad_norm": 0.7443113923072815, + "learning_rate": 5.984507231894364e-05, + "loss": 0.928, + "step": 1690 + }, + { + "epoch": 1.487420695690221, + "grad_norm": 0.8166981339454651, + "learning_rate": 5.934504167281022e-05, + "loss": 0.9323, + "step": 1700 + }, + { + "epoch": 1.4961715160796325, + "grad_norm": 0.8331442475318909, + "learning_rate": 5.884404067272174e-05, + "loss": 0.9458, + "step": 1710 + }, + { + "epoch": 1.5049223364690438, + "grad_norm": 0.7990359663963318, + "learning_rate": 5.834212134073644e-05, + "loss": 0.9094, + "step": 1720 + }, + { + "epoch": 1.5136731568584554, + "grad_norm": 0.768055260181427, + "learning_rate": 5.7839335794268666e-05, + "loss": 0.9385, + "step": 1730 + }, + { + "epoch": 1.522423977247867, + "grad_norm": 0.7425386309623718, + "learning_rate": 5.7335736240677174e-05, + "loss": 0.9446, + "step": 1740 + }, + { + "epoch": 1.5311747976372785, + "grad_norm": 0.7698354721069336, + "learning_rate": 5.683137497184424e-05, + "loss": 0.9057, + "step": 1750 + }, + { + "epoch": 1.53992561802669, + "grad_norm": 0.8186885118484497, + "learning_rate": 5.6326304358745694e-05, + "loss": 0.9758, + "step": 1760 + }, + { + "epoch": 1.5486764384161016, + "grad_norm": 0.8006178736686707, + "learning_rate": 5.5820576846013086e-05, + "loss": 0.9424, + "step": 1770 + }, + { + "epoch": 1.5574272588055131, + "grad_norm": 0.7572160363197327, + "learning_rate": 5.531424494648789e-05, + "loss": 0.945, + "step": 1780 + }, + { + "epoch": 1.5661780791949247, + "grad_norm": 0.8019212484359741, + "learning_rate": 5.480736123576886e-05, + "loss": 0.9528, + "step": 1790 + }, + { + "epoch": 1.574928899584336, + "grad_norm": 0.7867367267608643, + "learning_rate": 5.4299978346752756e-05, + "loss": 0.9499, + "step": 1800 + }, + { + "epoch": 1.5836797199737476, + "grad_norm": 0.7404739856719971, + "learning_rate": 5.379214896416907e-05, + "loss": 0.9177, + "step": 1810 + }, + { + "epoch": 1.592430540363159, + "grad_norm": 0.712374746799469, + "learning_rate": 5.328392581910961e-05, + "loss": 0.9212, + "step": 1820 + }, + { + "epoch": 1.6011813607525704, + "grad_norm": 0.7724602222442627, + "learning_rate": 5.277536168355293e-05, + "loss": 0.9402, + "step": 1830 + }, + { + "epoch": 1.609932181141982, + "grad_norm": 0.8452624678611755, + "learning_rate": 5.226650936488474e-05, + "loss": 0.9193, + "step": 1840 + }, + { + "epoch": 1.6186830015313936, + "grad_norm": 0.7993892431259155, + "learning_rate": 5.1757421700414645e-05, + "loss": 0.9328, + "step": 1850 + }, + { + "epoch": 1.627433821920805, + "grad_norm": 0.7931053042411804, + "learning_rate": 5.124815155188966e-05, + "loss": 0.9759, + "step": 1860 + }, + { + "epoch": 1.6361846423102167, + "grad_norm": 0.7516879439353943, + "learning_rate": 5.0738751800005226e-05, + "loss": 0.9229, + "step": 1870 + }, + { + "epoch": 1.6449354626996282, + "grad_norm": 0.6935803890228271, + "learning_rate": 5.022927533891434e-05, + "loss": 0.9234, + "step": 1880 + }, + { + "epoch": 1.6536862830890398, + "grad_norm": 0.8120819926261902, + "learning_rate": 4.9719775070735196e-05, + "loss": 0.9582, + "step": 1890 + }, + { + "epoch": 1.662437103478451, + "grad_norm": 0.781491219997406, + "learning_rate": 4.921030390005802e-05, + "loss": 0.9177, + "step": 1900 + }, + { + "epoch": 1.6711879238678626, + "grad_norm": 0.7723197340965271, + "learning_rate": 4.870091472845166e-05, + "loss": 0.9382, + "step": 1910 + }, + { + "epoch": 1.679938744257274, + "grad_norm": 0.751848578453064, + "learning_rate": 4.819166044897047e-05, + "loss": 0.9148, + "step": 1920 + }, + { + "epoch": 1.6886895646466855, + "grad_norm": 0.8265687823295593, + "learning_rate": 4.768259394066216e-05, + "loss": 0.9386, + "step": 1930 + }, + { + "epoch": 1.697440385036097, + "grad_norm": 0.7489150762557983, + "learning_rate": 4.7173768063076956e-05, + "loss": 0.9337, + "step": 1940 + }, + { + "epoch": 1.7061912054255086, + "grad_norm": 0.8112419247627258, + "learning_rate": 4.666523565077889e-05, + "loss": 0.917, + "step": 1950 + }, + { + "epoch": 1.7149420258149202, + "grad_norm": 0.7611903548240662, + "learning_rate": 4.615704950785965e-05, + "loss": 0.9338, + "step": 1960 + }, + { + "epoch": 1.7236928462043317, + "grad_norm": 0.7738552093505859, + "learning_rate": 4.5649262402455704e-05, + "loss": 0.9359, + "step": 1970 + }, + { + "epoch": 1.7324436665937433, + "grad_norm": 0.7741129994392395, + "learning_rate": 4.5141927061268844e-05, + "loss": 0.9209, + "step": 1980 + }, + { + "epoch": 1.7411944869831548, + "grad_norm": 0.7815123200416565, + "learning_rate": 4.463509616409144e-05, + "loss": 0.916, + "step": 1990 + }, + { + "epoch": 1.7499453073725662, + "grad_norm": 0.6793907284736633, + "learning_rate": 4.412882233833629e-05, + "loss": 0.9042, + "step": 2000 + }, + { + "epoch": 1.7586961277619777, + "grad_norm": 0.711877167224884, + "learning_rate": 4.362315815357197e-05, + "loss": 0.9072, + "step": 2010 + }, + { + "epoch": 1.767446948151389, + "grad_norm": 0.7671152353286743, + "learning_rate": 4.311815611606423e-05, + "loss": 0.9226, + "step": 2020 + }, + { + "epoch": 1.7761977685408006, + "grad_norm": 0.7221760153770447, + "learning_rate": 4.261386866332397e-05, + "loss": 0.9077, + "step": 2030 + }, + { + "epoch": 1.7849485889302121, + "grad_norm": 0.7419185042381287, + "learning_rate": 4.211034815866228e-05, + "loss": 0.9017, + "step": 2040 + }, + { + "epoch": 1.7936994093196237, + "grad_norm": 0.740652859210968, + "learning_rate": 4.1607646885753206e-05, + "loss": 0.9159, + "step": 2050 + }, + { + "epoch": 1.8024502297090352, + "grad_norm": 0.7923645377159119, + "learning_rate": 4.110581704320495e-05, + "loss": 0.9135, + "step": 2060 + }, + { + "epoch": 1.8112010500984468, + "grad_norm": 0.7528581023216248, + "learning_rate": 4.060491073913957e-05, + "loss": 0.9291, + "step": 2070 + }, + { + "epoch": 1.8199518704878583, + "grad_norm": 0.7974929809570312, + "learning_rate": 4.010497998578239e-05, + "loss": 0.9208, + "step": 2080 + }, + { + "epoch": 1.8287026908772699, + "grad_norm": 0.7388021349906921, + "learning_rate": 3.960607669406129e-05, + "loss": 0.9155, + "step": 2090 + }, + { + "epoch": 1.8374535112666812, + "grad_norm": 0.7927631735801697, + "learning_rate": 3.910825266821629e-05, + "loss": 0.9156, + "step": 2100 + }, + { + "epoch": 1.8462043316560928, + "grad_norm": 0.7545862793922424, + "learning_rate": 3.861155960042057e-05, + "loss": 0.877, + "step": 2110 + }, + { + "epoch": 1.8549551520455043, + "grad_norm": 0.8433863520622253, + "learning_rate": 3.8116049065412864e-05, + "loss": 0.9107, + "step": 2120 + }, + { + "epoch": 1.8637059724349156, + "grad_norm": 0.7610001564025879, + "learning_rate": 3.762177251514218e-05, + "loss": 0.9068, + "step": 2130 + }, + { + "epoch": 1.8724567928243272, + "grad_norm": 0.7452635765075684, + "learning_rate": 3.712878127342515e-05, + "loss": 0.9113, + "step": 2140 + }, + { + "epoch": 1.8812076132137387, + "grad_norm": 0.7530847787857056, + "learning_rate": 3.663712653061682e-05, + "loss": 0.8881, + "step": 2150 + }, + { + "epoch": 1.8899584336031503, + "grad_norm": 0.7940835356712341, + "learning_rate": 3.614685933829525e-05, + "loss": 0.8807, + "step": 2160 + }, + { + "epoch": 1.8987092539925619, + "grad_norm": 0.7291942834854126, + "learning_rate": 3.5658030603960436e-05, + "loss": 0.9112, + "step": 2170 + }, + { + "epoch": 1.9074600743819734, + "grad_norm": 0.7321741580963135, + "learning_rate": 3.5170691085748324e-05, + "loss": 0.8835, + "step": 2180 + }, + { + "epoch": 1.916210894771385, + "grad_norm": 0.7166718244552612, + "learning_rate": 3.468489138716029e-05, + "loss": 0.9115, + "step": 2190 + }, + { + "epoch": 1.9249617151607963, + "grad_norm": 0.741908848285675, + "learning_rate": 3.42006819518086e-05, + "loss": 0.9198, + "step": 2200 + }, + { + "epoch": 1.9337125355502078, + "grad_norm": 0.8034552931785583, + "learning_rate": 3.371811305817858e-05, + "loss": 0.8952, + "step": 2210 + }, + { + "epoch": 1.9424633559396194, + "grad_norm": 0.6716712713241577, + "learning_rate": 3.32372348144079e-05, + "loss": 0.9197, + "step": 2220 + }, + { + "epoch": 1.9512141763290307, + "grad_norm": 0.6731935739517212, + "learning_rate": 3.275809715308349e-05, + "loss": 0.8949, + "step": 2230 + }, + { + "epoch": 1.9599649967184423, + "grad_norm": 0.7521949410438538, + "learning_rate": 3.228074982605673e-05, + "loss": 0.8949, + "step": 2240 + }, + { + "epoch": 1.9687158171078538, + "grad_norm": 0.6889147162437439, + "learning_rate": 3.180524239927749e-05, + "loss": 0.8941, + "step": 2250 + }, + { + "epoch": 1.9774666374972654, + "grad_norm": 0.7169541716575623, + "learning_rate": 3.1331624247647276e-05, + "loss": 0.8922, + "step": 2260 + }, + { + "epoch": 1.986217457886677, + "grad_norm": 0.7812347412109375, + "learning_rate": 3.0859944549892325e-05, + "loss": 0.8915, + "step": 2270 + }, + { + "epoch": 1.9949682782760885, + "grad_norm": 0.7609400153160095, + "learning_rate": 3.039025228345725e-05, + "loss": 0.9227, + "step": 2280 + } + ], + "logging_steps": 10, + "max_steps": 3426, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500.0, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.5506578379505664e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3426/optimizer_0/.metadata b/checkpoint-3426/optimizer_0/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..6f0ba7eb30dec0413506967eb55b607527536116 --- /dev/null +++ b/checkpoint-3426/optimizer_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c2ae482a23462ab828266f49e94c90bc98f16eca9d704c846e15ff326036b0 +size 342948 diff --git a/checkpoint-3426/optimizer_0/__0_0.distcp b/checkpoint-3426/optimizer_0/__0_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..8482e937598a910310b742b8a996b0f7f1858803 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28eb80ae17acea6cbbdffde797c2e073087dc3258069919cf6a739dd4a2606a +size 2472090861 diff --git a/checkpoint-3426/optimizer_0/__1_0.distcp b/checkpoint-3426/optimizer_0/__1_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..114fe76cbc36810757b4bcddce4548c4198100d1 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedc6e67a3192909e8d053106409582eee53e87398139e38da601372c295bc88 +size 2472174123 diff --git a/checkpoint-3426/optimizer_0/__2_0.distcp b/checkpoint-3426/optimizer_0/__2_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..e9f754b842e99ea7c71de70fc2eda8f5eea1dbf5 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58737096141869c1f119f831ee45d25f462ff4b15cb51e34484b5c1730af49c6 +size 2472182518 diff --git a/checkpoint-3426/optimizer_0/__3_0.distcp b/checkpoint-3426/optimizer_0/__3_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..ae621a9a1be79dc0044e63cdd7e254b97a64c3b0 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b84184914149b14fc5d90e5021a1b98b7ac08960f9da0bf4c8e48a2f7f4f772 +size 2472179190 diff --git a/checkpoint-3426/pytorch_model_fsdp_0/.metadata b/checkpoint-3426/pytorch_model_fsdp_0/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..c7b0b6a70f31b63c86577f6d78e184258210d27e --- /dev/null +++ b/checkpoint-3426/pytorch_model_fsdp_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7fe491a7e31c2a3293024e7e8c6bb3c374a7ae061edb5959cd282a1d48309a +size 129152 diff --git a/checkpoint-3426/pytorch_model_fsdp_0/__0_0.distcp b/checkpoint-3426/pytorch_model_fsdp_0/__0_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..60fc0c23a7c4112c857791beccc2bbb0d9c62be4 --- /dev/null +++ b/checkpoint-3426/pytorch_model_fsdp_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e46456f9526b1dce3f4498f59cbc2f39ae998e04e5517452b26a8ca91d98dc5 +size 1498714507 diff --git a/checkpoint-3426/pytorch_model_fsdp_0/__1_0.distcp b/checkpoint-3426/pytorch_model_fsdp_0/__1_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..eb9306967f7fbf9dc6049684535e14c098c6d9fe --- /dev/null +++ b/checkpoint-3426/pytorch_model_fsdp_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d1e8dd555862fcabaca1e467beb02b04255a0bbc3427ffc10a486d84d77baca +size 1498714507 diff --git a/checkpoint-3426/pytorch_model_fsdp_0/__2_0.distcp b/checkpoint-3426/pytorch_model_fsdp_0/__2_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..f830f1a0ddc0c3a6ad9c19f9d9d43844377f8852 --- /dev/null +++ b/checkpoint-3426/pytorch_model_fsdp_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07ba245dadc9525c6c7941939f8b0e8a20a18d7ca34c7694c3bf8b42676725e +size 1498714507 diff --git a/checkpoint-3426/pytorch_model_fsdp_0/__3_0.distcp b/checkpoint-3426/pytorch_model_fsdp_0/__3_0.distcp new file mode 100644 index 0000000000000000000000000000000000000000..3cf1b5c3642b897b759e25c98b4d6c75ca094c23 --- /dev/null +++ b/checkpoint-3426/pytorch_model_fsdp_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e31a24d8dba9da94fd11387994bba3028c37c6ba3c977afcde97ac7dfbd4f07 +size 1498714507 diff --git a/checkpoint-3426/rng_state_0.pth b/checkpoint-3426/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..3cd72c974e82825e0615a259e4bcca95a3a3273c --- /dev/null +++ b/checkpoint-3426/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80829a78a755ba0cf5e985f9212f164229ce25f7c02fa877b4cdebf230922b5 +size 15429 diff --git a/checkpoint-3426/rng_state_1.pth b/checkpoint-3426/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..2749e3e0a290757087922def08bd7cfa7e218b5e --- /dev/null +++ b/checkpoint-3426/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6f4074cb5241eff8959c1f45b18c23c893119f6c03fa2da27359dbe7dba66c +size 15429 diff --git a/checkpoint-3426/rng_state_2.pth b/checkpoint-3426/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4dcd559098a83c8196eebb4aa54e5ee6c3f2a8f --- /dev/null +++ b/checkpoint-3426/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e84026d823a1c04897f710cd119a65b654c08ad443e97c4486fc7a26f6e64b +size 15429 diff --git a/checkpoint-3426/rng_state_3.pth b/checkpoint-3426/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..57161b2dc15e410494ead6a7f9ba4524f334abae --- /dev/null +++ b/checkpoint-3426/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b60a41c989678f542cc75416e61e7a43f81d6221d259490134253d1f38a920 +size 15429 diff --git a/checkpoint-3426/scheduler.pt b/checkpoint-3426/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd587e88165f3974aaeab800495877fa629e9bad --- /dev/null +++ b/checkpoint-3426/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932ccc456461adf32cd26dd5fb4d85a4d38f69661d41fe9883bf9a5066a53c7d +size 1465 diff --git a/checkpoint-3426/trainer_state.json b/checkpoint-3426/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..8d7cf54b0eeadf60bbc2d1e1e8efea4e199cc71b --- /dev/null +++ b/checkpoint-3426/trainer_state.json @@ -0,0 +1,2442 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.997593524392912, + "eval_steps": 500, + "global_step": 3426, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0, + "eval_loss": 2.1641297340393066, + "eval_runtime": 4.2967, + "eval_samples_per_second": 4.655, + "eval_steps_per_second": 0.465, + "step": 0 + }, + { + "epoch": 0.0008750820389411508, + "grad_norm": 6.37307071685791, + "learning_rate": 2.915451895043732e-07, + "loss": 1.6434, + "step": 1 + }, + { + "epoch": 0.008750820389411508, + "grad_norm": 4.0545759201049805, + "learning_rate": 2.915451895043732e-06, + "loss": 1.6965, + "step": 10 + }, + { + "epoch": 0.017501640778823015, + "grad_norm": 2.363191604614258, + "learning_rate": 5.830903790087464e-06, + "loss": 1.5272, + "step": 20 + }, + { + "epoch": 0.02625246116823452, + "grad_norm": 1.6348848342895508, + "learning_rate": 8.746355685131195e-06, + "loss": 1.389, + "step": 30 + }, + { + "epoch": 0.03500328155764603, + "grad_norm": 1.6716902256011963, + "learning_rate": 1.1661807580174927e-05, + "loss": 1.348, + "step": 40 + }, + { + "epoch": 0.04375410194705753, + "grad_norm": 1.510228157043457, + "learning_rate": 1.457725947521866e-05, + "loss": 1.2997, + "step": 50 + }, + { + "epoch": 0.05250492233646904, + "grad_norm": 1.6153247356414795, + "learning_rate": 1.749271137026239e-05, + "loss": 1.2665, + "step": 60 + }, + { + "epoch": 0.06125574272588055, + "grad_norm": 1.446387767791748, + "learning_rate": 2.0408163265306123e-05, + "loss": 1.237, + "step": 70 + }, + { + "epoch": 0.07000656311529206, + "grad_norm": 1.3039863109588623, + "learning_rate": 2.3323615160349855e-05, + "loss": 1.2341, + "step": 80 + }, + { + "epoch": 0.07875738350470357, + "grad_norm": 1.4866383075714111, + "learning_rate": 2.6239067055393584e-05, + "loss": 1.2338, + "step": 90 + }, + { + "epoch": 0.08750820389411507, + "grad_norm": 1.358859658241272, + "learning_rate": 2.915451895043732e-05, + "loss": 1.2331, + "step": 100 + }, + { + "epoch": 0.09625902428352658, + "grad_norm": 1.847506046295166, + "learning_rate": 3.206997084548105e-05, + "loss": 1.1628, + "step": 110 + }, + { + "epoch": 0.10500984467293809, + "grad_norm": 1.7742356061935425, + "learning_rate": 3.498542274052478e-05, + "loss": 1.1846, + "step": 120 + }, + { + "epoch": 0.1137606650623496, + "grad_norm": 1.3415714502334595, + "learning_rate": 3.790087463556852e-05, + "loss": 1.1699, + "step": 130 + }, + { + "epoch": 0.1225114854517611, + "grad_norm": 1.5319396257400513, + "learning_rate": 4.0816326530612245e-05, + "loss": 1.181, + "step": 140 + }, + { + "epoch": 0.1312623058411726, + "grad_norm": 1.3915642499923706, + "learning_rate": 4.373177842565598e-05, + "loss": 1.189, + "step": 150 + }, + { + "epoch": 0.14001312623058412, + "grad_norm": 1.175917625427246, + "learning_rate": 4.664723032069971e-05, + "loss": 1.1605, + "step": 160 + }, + { + "epoch": 0.14876394661999562, + "grad_norm": 1.3125519752502441, + "learning_rate": 4.956268221574344e-05, + "loss": 1.1734, + "step": 170 + }, + { + "epoch": 0.15751476700940714, + "grad_norm": 1.2966923713684082, + "learning_rate": 5.247813411078717e-05, + "loss": 1.2075, + "step": 180 + }, + { + "epoch": 0.16626558739881864, + "grad_norm": 1.2630099058151245, + "learning_rate": 5.539358600583091e-05, + "loss": 1.1791, + "step": 190 + }, + { + "epoch": 0.17501640778823013, + "grad_norm": 1.306665301322937, + "learning_rate": 5.830903790087464e-05, + "loss": 1.1469, + "step": 200 + }, + { + "epoch": 0.18376722817764166, + "grad_norm": 1.19467031955719, + "learning_rate": 6.122448979591838e-05, + "loss": 1.185, + "step": 210 + }, + { + "epoch": 0.19251804856705315, + "grad_norm": 1.416387677192688, + "learning_rate": 6.41399416909621e-05, + "loss": 1.2061, + "step": 220 + }, + { + "epoch": 0.20126886895646467, + "grad_norm": 1.3546264171600342, + "learning_rate": 6.705539358600583e-05, + "loss": 1.2016, + "step": 230 + }, + { + "epoch": 0.21001968934587617, + "grad_norm": 1.2417850494384766, + "learning_rate": 6.997084548104956e-05, + "loss": 1.1797, + "step": 240 + }, + { + "epoch": 0.2187705097352877, + "grad_norm": 1.2703570127487183, + "learning_rate": 7.28862973760933e-05, + "loss": 1.2059, + "step": 250 + }, + { + "epoch": 0.2275213301246992, + "grad_norm": 1.2479429244995117, + "learning_rate": 7.580174927113704e-05, + "loss": 1.1958, + "step": 260 + }, + { + "epoch": 0.23627215051411068, + "grad_norm": 1.507601261138916, + "learning_rate": 7.871720116618077e-05, + "loss": 1.2151, + "step": 270 + }, + { + "epoch": 0.2450229709035222, + "grad_norm": 1.2083854675292969, + "learning_rate": 8.163265306122449e-05, + "loss": 1.2202, + "step": 280 + }, + { + "epoch": 0.2537737912929337, + "grad_norm": 1.2939566373825073, + "learning_rate": 8.454810495626822e-05, + "loss": 1.1916, + "step": 290 + }, + { + "epoch": 0.2625246116823452, + "grad_norm": 1.2871382236480713, + "learning_rate": 8.746355685131195e-05, + "loss": 1.222, + "step": 300 + }, + { + "epoch": 0.27127543207175675, + "grad_norm": 1.1558256149291992, + "learning_rate": 9.037900874635569e-05, + "loss": 1.2094, + "step": 310 + }, + { + "epoch": 0.28002625246116825, + "grad_norm": 1.0638883113861084, + "learning_rate": 9.329446064139942e-05, + "loss": 1.2, + "step": 320 + }, + { + "epoch": 0.28877707285057974, + "grad_norm": 1.1072458028793335, + "learning_rate": 9.620991253644317e-05, + "loss": 1.224, + "step": 330 + }, + { + "epoch": 0.29752789323999124, + "grad_norm": 1.1332110166549683, + "learning_rate": 9.912536443148688e-05, + "loss": 1.2266, + "step": 340 + }, + { + "epoch": 0.30627871362940273, + "grad_norm": 1.0537033081054688, + "learning_rate": 9.999872800049233e-05, + "loss": 1.2173, + "step": 350 + }, + { + "epoch": 0.3150295340188143, + "grad_norm": 1.090928316116333, + "learning_rate": 9.999249795462235e-05, + "loss": 1.2416, + "step": 360 + }, + { + "epoch": 0.3237803544082258, + "grad_norm": 1.0084835290908813, + "learning_rate": 9.998107687592326e-05, + "loss": 1.2094, + "step": 370 + }, + { + "epoch": 0.3325311747976373, + "grad_norm": 1.82576584815979, + "learning_rate": 9.996446595031691e-05, + "loss": 1.2246, + "step": 380 + }, + { + "epoch": 0.34128199518704877, + "grad_norm": 1.2305560111999512, + "learning_rate": 9.994266690261928e-05, + "loss": 1.2647, + "step": 390 + }, + { + "epoch": 0.35003281557646027, + "grad_norm": 1.170067548751831, + "learning_rate": 9.991568199636148e-05, + "loss": 1.1829, + "step": 400 + }, + { + "epoch": 0.3587836359658718, + "grad_norm": 1.0299819707870483, + "learning_rate": 9.988351403355454e-05, + "loss": 1.2471, + "step": 410 + }, + { + "epoch": 0.3675344563552833, + "grad_norm": 0.9742593765258789, + "learning_rate": 9.98461663543987e-05, + "loss": 1.2049, + "step": 420 + }, + { + "epoch": 0.3762852767446948, + "grad_norm": 0.9377045631408691, + "learning_rate": 9.980364283693638e-05, + "loss": 1.1963, + "step": 430 + }, + { + "epoch": 0.3850360971341063, + "grad_norm": 1.0425899028778076, + "learning_rate": 9.97559478966496e-05, + "loss": 1.2167, + "step": 440 + }, + { + "epoch": 0.39378691752351785, + "grad_norm": 0.9749513864517212, + "learning_rate": 9.97030864860014e-05, + "loss": 1.2166, + "step": 450 + }, + { + "epoch": 0.40253773791292935, + "grad_norm": 1.0552780628204346, + "learning_rate": 9.964506409392176e-05, + "loss": 1.2228, + "step": 460 + }, + { + "epoch": 0.41128855830234085, + "grad_norm": 1.0261808633804321, + "learning_rate": 9.958188674523748e-05, + "loss": 1.2252, + "step": 470 + }, + { + "epoch": 0.42003937869175234, + "grad_norm": 0.9530945420265198, + "learning_rate": 9.951356100004665e-05, + "loss": 1.1845, + "step": 480 + }, + { + "epoch": 0.42879019908116384, + "grad_norm": 0.8990481495857239, + "learning_rate": 9.94400939530375e-05, + "loss": 1.2283, + "step": 490 + }, + { + "epoch": 0.4375410194705754, + "grad_norm": 0.9713592529296875, + "learning_rate": 9.936149323275169e-05, + "loss": 1.1945, + "step": 500 + }, + { + "epoch": 0.4462918398599869, + "grad_norm": 1.003854513168335, + "learning_rate": 9.927776700079216e-05, + "loss": 1.2322, + "step": 510 + }, + { + "epoch": 0.4550426602493984, + "grad_norm": 0.935400664806366, + "learning_rate": 9.918892395097572e-05, + "loss": 1.2272, + "step": 520 + }, + { + "epoch": 0.4637934806388099, + "grad_norm": 1.075519323348999, + "learning_rate": 9.90949733084303e-05, + "loss": 1.2069, + "step": 530 + }, + { + "epoch": 0.47254430102822137, + "grad_norm": 0.9949712157249451, + "learning_rate": 9.8995924828637e-05, + "loss": 1.2083, + "step": 540 + }, + { + "epoch": 0.4812951214176329, + "grad_norm": 0.8942195773124695, + "learning_rate": 9.889178879641717e-05, + "loss": 1.2137, + "step": 550 + }, + { + "epoch": 0.4900459418070444, + "grad_norm": 0.9525908827781677, + "learning_rate": 9.878257602486445e-05, + "loss": 1.2348, + "step": 560 + }, + { + "epoch": 0.4987967621964559, + "grad_norm": 0.895167350769043, + "learning_rate": 9.8668297854222e-05, + "loss": 1.2034, + "step": 570 + }, + { + "epoch": 0.5075475825858674, + "grad_norm": 1.0244312286376953, + "learning_rate": 9.854896615070495e-05, + "loss": 1.1942, + "step": 580 + }, + { + "epoch": 0.516298402975279, + "grad_norm": 0.9835163950920105, + "learning_rate": 9.842459330526826e-05, + "loss": 1.2182, + "step": 590 + }, + { + "epoch": 0.5250492233646904, + "grad_norm": 0.9238565564155579, + "learning_rate": 9.829519223232006e-05, + "loss": 1.1992, + "step": 600 + }, + { + "epoch": 0.533800043754102, + "grad_norm": 0.9063233733177185, + "learning_rate": 9.81607763683808e-05, + "loss": 1.2135, + "step": 610 + }, + { + "epoch": 0.5425508641435135, + "grad_norm": 0.9810764193534851, + "learning_rate": 9.802135967068782e-05, + "loss": 1.1909, + "step": 620 + }, + { + "epoch": 0.5513016845329249, + "grad_norm": 0.9388274550437927, + "learning_rate": 9.787695661574632e-05, + "loss": 1.1693, + "step": 630 + }, + { + "epoch": 0.5600525049223365, + "grad_norm": 0.933283805847168, + "learning_rate": 9.772758219782601e-05, + "loss": 1.1857, + "step": 640 + }, + { + "epoch": 0.5688033253117479, + "grad_norm": 0.947989284992218, + "learning_rate": 9.757325192740425e-05, + "loss": 1.1901, + "step": 650 + }, + { + "epoch": 0.5775541457011595, + "grad_norm": 0.8272686004638672, + "learning_rate": 9.741398182955548e-05, + "loss": 1.2087, + "step": 660 + }, + { + "epoch": 0.586304966090571, + "grad_norm": 0.8907813429832458, + "learning_rate": 9.724978844228717e-05, + "loss": 1.201, + "step": 670 + }, + { + "epoch": 0.5950557864799825, + "grad_norm": 0.8374966382980347, + "learning_rate": 9.708068881482271e-05, + "loss": 1.2028, + "step": 680 + }, + { + "epoch": 0.603806606869394, + "grad_norm": 0.9283761382102966, + "learning_rate": 9.690670050583095e-05, + "loss": 1.1995, + "step": 690 + }, + { + "epoch": 0.6125574272588055, + "grad_norm": 0.8573452234268188, + "learning_rate": 9.672784158160307e-05, + "loss": 1.1372, + "step": 700 + }, + { + "epoch": 0.621308247648217, + "grad_norm": 0.8831506371498108, + "learning_rate": 9.654413061417655e-05, + "loss": 1.1626, + "step": 710 + }, + { + "epoch": 0.6300590680376286, + "grad_norm": 0.9180812239646912, + "learning_rate": 9.635558667940683e-05, + "loss": 1.1466, + "step": 720 + }, + { + "epoch": 0.63880988842704, + "grad_norm": 0.8657775521278381, + "learning_rate": 9.616222935498646e-05, + "loss": 1.2052, + "step": 730 + }, + { + "epoch": 0.6475607088164516, + "grad_norm": 0.9488115310668945, + "learning_rate": 9.596407871841229e-05, + "loss": 1.1651, + "step": 740 + }, + { + "epoch": 0.656311529205863, + "grad_norm": 0.8592752814292908, + "learning_rate": 9.57611553449006e-05, + "loss": 1.1953, + "step": 750 + }, + { + "epoch": 0.6650623495952745, + "grad_norm": 0.889445960521698, + "learning_rate": 9.555348030525076e-05, + "loss": 1.1647, + "step": 760 + }, + { + "epoch": 0.6738131699846861, + "grad_norm": 0.8997176885604858, + "learning_rate": 9.534107516365725e-05, + "loss": 1.167, + "step": 770 + }, + { + "epoch": 0.6825639903740975, + "grad_norm": 0.8208065032958984, + "learning_rate": 9.512396197547053e-05, + "loss": 1.1631, + "step": 780 + }, + { + "epoch": 0.6913148107635091, + "grad_norm": 0.8419785499572754, + "learning_rate": 9.490216328490692e-05, + "loss": 1.1857, + "step": 790 + }, + { + "epoch": 0.7000656311529205, + "grad_norm": 0.8125676512718201, + "learning_rate": 9.467570212270767e-05, + "loss": 1.2426, + "step": 800 + }, + { + "epoch": 0.7088164515423321, + "grad_norm": 0.9222508072853088, + "learning_rate": 9.444460200374748e-05, + "loss": 1.1452, + "step": 810 + }, + { + "epoch": 0.7175672719317436, + "grad_norm": 0.8932722210884094, + "learning_rate": 9.420888692459291e-05, + "loss": 1.1647, + "step": 820 + }, + { + "epoch": 0.7263180923211551, + "grad_norm": 0.817932665348053, + "learning_rate": 9.396858136101066e-05, + "loss": 1.1618, + "step": 830 + }, + { + "epoch": 0.7350689127105666, + "grad_norm": 0.8717408180236816, + "learning_rate": 9.372371026542595e-05, + "loss": 1.1517, + "step": 840 + }, + { + "epoch": 0.7438197330999782, + "grad_norm": 0.8578230142593384, + "learning_rate": 9.347429906433174e-05, + "loss": 1.2009, + "step": 850 + }, + { + "epoch": 0.7525705534893896, + "grad_norm": 0.8276301622390747, + "learning_rate": 9.322037365564845e-05, + "loss": 1.1627, + "step": 860 + }, + { + "epoch": 0.7613213738788012, + "grad_norm": 0.7934173941612244, + "learning_rate": 9.296196040603475e-05, + "loss": 1.1735, + "step": 870 + }, + { + "epoch": 0.7700721942682126, + "grad_norm": 0.8270857930183411, + "learning_rate": 9.269908614814995e-05, + "loss": 1.149, + "step": 880 + }, + { + "epoch": 0.7788230146576242, + "grad_norm": 1.0632795095443726, + "learning_rate": 9.243177817786757e-05, + "loss": 1.1937, + "step": 890 + }, + { + "epoch": 0.7875738350470357, + "grad_norm": 0.8449203968048096, + "learning_rate": 9.216006425144118e-05, + "loss": 1.1787, + "step": 900 + }, + { + "epoch": 0.7963246554364471, + "grad_norm": 0.7634311318397522, + "learning_rate": 9.188397258262221e-05, + "loss": 1.1445, + "step": 910 + }, + { + "epoch": 0.8050754758258587, + "grad_norm": 0.7856956720352173, + "learning_rate": 9.160353183973046e-05, + "loss": 1.1519, + "step": 920 + }, + { + "epoch": 0.8138262962152701, + "grad_norm": 0.8162206411361694, + "learning_rate": 9.131877114267711e-05, + "loss": 1.1282, + "step": 930 + }, + { + "epoch": 0.8225771166046817, + "grad_norm": 0.8263719081878662, + "learning_rate": 9.102972005994122e-05, + "loss": 1.1127, + "step": 940 + }, + { + "epoch": 0.8313279369940932, + "grad_norm": 0.831969141960144, + "learning_rate": 9.073640860549931e-05, + "loss": 1.1446, + "step": 950 + }, + { + "epoch": 0.8400787573835047, + "grad_norm": 0.8127765655517578, + "learning_rate": 9.043886723570884e-05, + "loss": 1.1649, + "step": 960 + }, + { + "epoch": 0.8488295777729162, + "grad_norm": 0.7642777562141418, + "learning_rate": 9.013712684614582e-05, + "loss": 1.1656, + "step": 970 + }, + { + "epoch": 0.8575803981623277, + "grad_norm": 0.8071634769439697, + "learning_rate": 8.983121876839657e-05, + "loss": 1.1414, + "step": 980 + }, + { + "epoch": 0.8663312185517392, + "grad_norm": 0.7789682149887085, + "learning_rate": 8.95211747668046e-05, + "loss": 1.1127, + "step": 990 + }, + { + "epoch": 0.8750820389411508, + "grad_norm": 0.7899104356765747, + "learning_rate": 8.920702703517204e-05, + "loss": 1.1218, + "step": 1000 + }, + { + "epoch": 0.8838328593305622, + "grad_norm": 0.726874053478241, + "learning_rate": 8.888880819341702e-05, + "loss": 1.1345, + "step": 1010 + }, + { + "epoch": 0.8925836797199738, + "grad_norm": 0.8020316958427429, + "learning_rate": 8.856655128418637e-05, + "loss": 1.1229, + "step": 1020 + }, + { + "epoch": 0.9013345001093852, + "grad_norm": 0.8466740250587463, + "learning_rate": 8.824028976942465e-05, + "loss": 1.1451, + "step": 1030 + }, + { + "epoch": 0.9100853204987968, + "grad_norm": 0.7729008793830872, + "learning_rate": 8.791005752689958e-05, + "loss": 1.1204, + "step": 1040 + }, + { + "epoch": 0.9188361408882083, + "grad_norm": 0.8055347204208374, + "learning_rate": 8.757588884668434e-05, + "loss": 1.1372, + "step": 1050 + }, + { + "epoch": 0.9275869612776197, + "grad_norm": 0.8180489540100098, + "learning_rate": 8.723781842759695e-05, + "loss": 1.1632, + "step": 1060 + }, + { + "epoch": 0.9363377816670313, + "grad_norm": 0.816849946975708, + "learning_rate": 8.689588137359732e-05, + "loss": 1.1226, + "step": 1070 + }, + { + "epoch": 0.9450886020564427, + "grad_norm": 0.8028609752655029, + "learning_rate": 8.655011319014216e-05, + "loss": 1.1559, + "step": 1080 + }, + { + "epoch": 0.9538394224458543, + "grad_norm": 0.8719303011894226, + "learning_rate": 8.620054978049829e-05, + "loss": 1.1522, + "step": 1090 + }, + { + "epoch": 0.9625902428352658, + "grad_norm": 0.766177237033844, + "learning_rate": 8.584722744201447e-05, + "loss": 1.1186, + "step": 1100 + }, + { + "epoch": 0.9713410632246773, + "grad_norm": 0.7790910005569458, + "learning_rate": 8.549018286235255e-05, + "loss": 1.1227, + "step": 1110 + }, + { + "epoch": 0.9800918836140888, + "grad_norm": 0.7803717255592346, + "learning_rate": 8.512945311567786e-05, + "loss": 1.1186, + "step": 1120 + }, + { + "epoch": 0.9888427040035004, + "grad_norm": 0.7084935307502747, + "learning_rate": 8.476507565880957e-05, + "loss": 1.1085, + "step": 1130 + }, + { + "epoch": 0.9975935243929118, + "grad_norm": 0.7696670889854431, + "learning_rate": 8.439708832733142e-05, + "loss": 1.1123, + "step": 1140 + }, + { + "epoch": 1.006125574272588, + "grad_norm": 0.9948705434799194, + "learning_rate": 8.402552933166288e-05, + "loss": 0.9984, + "step": 1150 + }, + { + "epoch": 1.0148763946619996, + "grad_norm": 0.8488800525665283, + "learning_rate": 8.36504372530916e-05, + "loss": 0.9603, + "step": 1160 + }, + { + "epoch": 1.023627215051411, + "grad_norm": 0.8748326897621155, + "learning_rate": 8.32718510397673e-05, + "loss": 0.9535, + "step": 1170 + }, + { + "epoch": 1.0323780354408225, + "grad_norm": 0.8636799454689026, + "learning_rate": 8.288981000265748e-05, + "loss": 0.9705, + "step": 1180 + }, + { + "epoch": 1.041128855830234, + "grad_norm": 0.7722444534301758, + "learning_rate": 8.250435381146549e-05, + "loss": 0.9411, + "step": 1190 + }, + { + "epoch": 1.0498796762196456, + "grad_norm": 0.792931318283081, + "learning_rate": 8.211552249051149e-05, + "loss": 0.9455, + "step": 1200 + }, + { + "epoch": 1.0586304966090572, + "grad_norm": 0.8179608583450317, + "learning_rate": 8.17233564145764e-05, + "loss": 0.9418, + "step": 1210 + }, + { + "epoch": 1.0673813169984685, + "grad_norm": 0.8081513047218323, + "learning_rate": 8.132789630470952e-05, + "loss": 0.9451, + "step": 1220 + }, + { + "epoch": 1.07613213738788, + "grad_norm": 0.8941613435745239, + "learning_rate": 8.092918322400027e-05, + "loss": 0.9336, + "step": 1230 + }, + { + "epoch": 1.0848829577772916, + "grad_norm": 0.8505945801734924, + "learning_rate": 8.052725857331429e-05, + "loss": 0.9432, + "step": 1240 + }, + { + "epoch": 1.0936337781667032, + "grad_norm": 0.7953508496284485, + "learning_rate": 8.012216408699455e-05, + "loss": 0.9608, + "step": 1250 + }, + { + "epoch": 1.1023845985561147, + "grad_norm": 0.9065775871276855, + "learning_rate": 7.971394182852789e-05, + "loss": 0.9583, + "step": 1260 + }, + { + "epoch": 1.1111354189455263, + "grad_norm": 0.8752979040145874, + "learning_rate": 7.930263418617713e-05, + "loss": 0.9752, + "step": 1270 + }, + { + "epoch": 1.1198862393349376, + "grad_norm": 0.8173210024833679, + "learning_rate": 7.888828386857985e-05, + "loss": 0.9505, + "step": 1280 + }, + { + "epoch": 1.1286370597243491, + "grad_norm": 0.7964232563972473, + "learning_rate": 7.84709339003135e-05, + "loss": 0.9346, + "step": 1290 + }, + { + "epoch": 1.1373878801137607, + "grad_norm": 0.8364039063453674, + "learning_rate": 7.805062761742799e-05, + "loss": 0.9606, + "step": 1300 + }, + { + "epoch": 1.1461387005031722, + "grad_norm": 0.8122743964195251, + "learning_rate": 7.76274086629458e-05, + "loss": 0.9455, + "step": 1310 + }, + { + "epoch": 1.1548895208925836, + "grad_norm": 0.8229530453681946, + "learning_rate": 7.720132098233031e-05, + "loss": 0.9465, + "step": 1320 + }, + { + "epoch": 1.1636403412819951, + "grad_norm": 0.7859545946121216, + "learning_rate": 7.677240881892258e-05, + "loss": 0.9421, + "step": 1330 + }, + { + "epoch": 1.1723911616714067, + "grad_norm": 0.8277194499969482, + "learning_rate": 7.634071670934734e-05, + "loss": 0.9541, + "step": 1340 + }, + { + "epoch": 1.1811419820608182, + "grad_norm": 0.7695391774177551, + "learning_rate": 7.590628947888847e-05, + "loss": 0.9433, + "step": 1350 + }, + { + "epoch": 1.1898928024502298, + "grad_norm": 0.82956862449646, + "learning_rate": 7.546917223683453e-05, + "loss": 0.9395, + "step": 1360 + }, + { + "epoch": 1.1986436228396413, + "grad_norm": 0.8398957252502441, + "learning_rate": 7.502941037179474e-05, + "loss": 0.9432, + "step": 1370 + }, + { + "epoch": 1.2073944432290526, + "grad_norm": 0.8232219219207764, + "learning_rate": 7.4587049546986e-05, + "loss": 0.9887, + "step": 1380 + }, + { + "epoch": 1.2161452636184642, + "grad_norm": 0.7886401414871216, + "learning_rate": 7.414213569549145e-05, + "loss": 0.959, + "step": 1390 + }, + { + "epoch": 1.2248960840078758, + "grad_norm": 0.7588061690330505, + "learning_rate": 7.369471501549087e-05, + "loss": 0.9651, + "step": 1400 + }, + { + "epoch": 1.2336469043972873, + "grad_norm": 0.8234547972679138, + "learning_rate": 7.324483396546371e-05, + "loss": 0.9935, + "step": 1410 + }, + { + "epoch": 1.2423977247866986, + "grad_norm": 0.7623049020767212, + "learning_rate": 7.279253925936498e-05, + "loss": 0.95, + "step": 1420 + }, + { + "epoch": 1.2511485451761102, + "grad_norm": 0.7172533869743347, + "learning_rate": 7.233787786177464e-05, + "loss": 0.9441, + "step": 1430 + }, + { + "epoch": 1.2598993655655217, + "grad_norm": 0.7973024249076843, + "learning_rate": 7.188089698302098e-05, + "loss": 0.9682, + "step": 1440 + }, + { + "epoch": 1.2686501859549333, + "grad_norm": 0.7969169020652771, + "learning_rate": 7.14216440742785e-05, + "loss": 0.9541, + "step": 1450 + }, + { + "epoch": 1.2774010063443448, + "grad_norm": 0.8296008110046387, + "learning_rate": 7.096016682264074e-05, + "loss": 0.9597, + "step": 1460 + }, + { + "epoch": 1.2861518267337564, + "grad_norm": 0.8538773655891418, + "learning_rate": 7.049651314616862e-05, + "loss": 0.9225, + "step": 1470 + }, + { + "epoch": 1.2949026471231677, + "grad_norm": 0.8068443536758423, + "learning_rate": 7.003073118891487e-05, + "loss": 0.9282, + "step": 1480 + }, + { + "epoch": 1.3036534675125793, + "grad_norm": 0.8286350965499878, + "learning_rate": 6.956286931592481e-05, + "loss": 0.9645, + "step": 1490 + }, + { + "epoch": 1.3124042879019908, + "grad_norm": 0.796650767326355, + "learning_rate": 6.909297610821443e-05, + "loss": 0.934, + "step": 1500 + }, + { + "epoch": 1.3211551082914024, + "grad_norm": 0.7479636073112488, + "learning_rate": 6.862110035772589e-05, + "loss": 0.9319, + "step": 1510 + }, + { + "epoch": 1.3299059286808137, + "grad_norm": 0.7734546065330505, + "learning_rate": 6.81472910622611e-05, + "loss": 0.9577, + "step": 1520 + }, + { + "epoch": 1.3386567490702252, + "grad_norm": 0.821553647518158, + "learning_rate": 6.7671597420394e-05, + "loss": 0.966, + "step": 1530 + }, + { + "epoch": 1.3474075694596368, + "grad_norm": 0.8141497373580933, + "learning_rate": 6.719406882636196e-05, + "loss": 0.9593, + "step": 1540 + }, + { + "epoch": 1.3561583898490484, + "grad_norm": 0.7738481163978577, + "learning_rate": 6.671475486493691e-05, + "loss": 0.9474, + "step": 1550 + }, + { + "epoch": 1.36490921023846, + "grad_norm": 0.7933306694030762, + "learning_rate": 6.62337053062766e-05, + "loss": 0.9297, + "step": 1560 + }, + { + "epoch": 1.3736600306278715, + "grad_norm": 0.7921035885810852, + "learning_rate": 6.575097010075664e-05, + "loss": 0.9283, + "step": 1570 + }, + { + "epoch": 1.382410851017283, + "grad_norm": 0.7895304560661316, + "learning_rate": 6.526659937378392e-05, + "loss": 0.9559, + "step": 1580 + }, + { + "epoch": 1.3911616714066943, + "grad_norm": 0.8518770933151245, + "learning_rate": 6.478064342059164e-05, + "loss": 0.9571, + "step": 1590 + }, + { + "epoch": 1.3999124917961059, + "grad_norm": 0.8479484915733337, + "learning_rate": 6.429315270101701e-05, + "loss": 0.9578, + "step": 1600 + }, + { + "epoch": 1.4086633121855174, + "grad_norm": 0.763520359992981, + "learning_rate": 6.380417783426153e-05, + "loss": 0.9304, + "step": 1610 + }, + { + "epoch": 1.4174141325749288, + "grad_norm": 0.7657537460327148, + "learning_rate": 6.3313769593635e-05, + "loss": 0.9541, + "step": 1620 + }, + { + "epoch": 1.4261649529643403, + "grad_norm": 0.7461577653884888, + "learning_rate": 6.282197890128338e-05, + "loss": 0.9331, + "step": 1630 + }, + { + "epoch": 1.4349157733537519, + "grad_norm": 0.7814643383026123, + "learning_rate": 6.23288568229012e-05, + "loss": 0.9431, + "step": 1640 + }, + { + "epoch": 1.4436665937431634, + "grad_norm": 0.7600048184394836, + "learning_rate": 6.183445456242904e-05, + "loss": 0.9549, + "step": 1650 + }, + { + "epoch": 1.452417414132575, + "grad_norm": 0.7684770226478577, + "learning_rate": 6.13388234567369e-05, + "loss": 0.9074, + "step": 1660 + }, + { + "epoch": 1.4611682345219865, + "grad_norm": 0.7696465849876404, + "learning_rate": 6.084201497029333e-05, + "loss": 0.9449, + "step": 1670 + }, + { + "epoch": 1.469919054911398, + "grad_norm": 0.818397045135498, + "learning_rate": 6.034408068982172e-05, + "loss": 0.9396, + "step": 1680 + }, + { + "epoch": 1.4786698753008094, + "grad_norm": 0.7443113923072815, + "learning_rate": 5.984507231894364e-05, + "loss": 0.928, + "step": 1690 + }, + { + "epoch": 1.487420695690221, + "grad_norm": 0.8166981339454651, + "learning_rate": 5.934504167281022e-05, + "loss": 0.9323, + "step": 1700 + }, + { + "epoch": 1.4961715160796325, + "grad_norm": 0.8331442475318909, + "learning_rate": 5.884404067272174e-05, + "loss": 0.9458, + "step": 1710 + }, + { + "epoch": 1.5049223364690438, + "grad_norm": 0.7990359663963318, + "learning_rate": 5.834212134073644e-05, + "loss": 0.9094, + "step": 1720 + }, + { + "epoch": 1.5136731568584554, + "grad_norm": 0.768055260181427, + "learning_rate": 5.7839335794268666e-05, + "loss": 0.9385, + "step": 1730 + }, + { + "epoch": 1.522423977247867, + "grad_norm": 0.7425386309623718, + "learning_rate": 5.7335736240677174e-05, + "loss": 0.9446, + "step": 1740 + }, + { + "epoch": 1.5311747976372785, + "grad_norm": 0.7698354721069336, + "learning_rate": 5.683137497184424e-05, + "loss": 0.9057, + "step": 1750 + }, + { + "epoch": 1.53992561802669, + "grad_norm": 0.8186885118484497, + "learning_rate": 5.6326304358745694e-05, + "loss": 0.9758, + "step": 1760 + }, + { + "epoch": 1.5486764384161016, + "grad_norm": 0.8006178736686707, + "learning_rate": 5.5820576846013086e-05, + "loss": 0.9424, + "step": 1770 + }, + { + "epoch": 1.5574272588055131, + "grad_norm": 0.7572160363197327, + "learning_rate": 5.531424494648789e-05, + "loss": 0.945, + "step": 1780 + }, + { + "epoch": 1.5661780791949247, + "grad_norm": 0.8019212484359741, + "learning_rate": 5.480736123576886e-05, + "loss": 0.9528, + "step": 1790 + }, + { + "epoch": 1.574928899584336, + "grad_norm": 0.7867367267608643, + "learning_rate": 5.4299978346752756e-05, + "loss": 0.9499, + "step": 1800 + }, + { + "epoch": 1.5836797199737476, + "grad_norm": 0.7404739856719971, + "learning_rate": 5.379214896416907e-05, + "loss": 0.9177, + "step": 1810 + }, + { + "epoch": 1.592430540363159, + "grad_norm": 0.712374746799469, + "learning_rate": 5.328392581910961e-05, + "loss": 0.9212, + "step": 1820 + }, + { + "epoch": 1.6011813607525704, + "grad_norm": 0.7724602222442627, + "learning_rate": 5.277536168355293e-05, + "loss": 0.9402, + "step": 1830 + }, + { + "epoch": 1.609932181141982, + "grad_norm": 0.8452624678611755, + "learning_rate": 5.226650936488474e-05, + "loss": 0.9193, + "step": 1840 + }, + { + "epoch": 1.6186830015313936, + "grad_norm": 0.7993892431259155, + "learning_rate": 5.1757421700414645e-05, + "loss": 0.9328, + "step": 1850 + }, + { + "epoch": 1.627433821920805, + "grad_norm": 0.7931053042411804, + "learning_rate": 5.124815155188966e-05, + "loss": 0.9759, + "step": 1860 + }, + { + "epoch": 1.6361846423102167, + "grad_norm": 0.7516879439353943, + "learning_rate": 5.0738751800005226e-05, + "loss": 0.9229, + "step": 1870 + }, + { + "epoch": 1.6449354626996282, + "grad_norm": 0.6935803890228271, + "learning_rate": 5.022927533891434e-05, + "loss": 0.9234, + "step": 1880 + }, + { + "epoch": 1.6536862830890398, + "grad_norm": 0.8120819926261902, + "learning_rate": 4.9719775070735196e-05, + "loss": 0.9582, + "step": 1890 + }, + { + "epoch": 1.662437103478451, + "grad_norm": 0.781491219997406, + "learning_rate": 4.921030390005802e-05, + "loss": 0.9177, + "step": 1900 + }, + { + "epoch": 1.6711879238678626, + "grad_norm": 0.7723197340965271, + "learning_rate": 4.870091472845166e-05, + "loss": 0.9382, + "step": 1910 + }, + { + "epoch": 1.679938744257274, + "grad_norm": 0.751848578453064, + "learning_rate": 4.819166044897047e-05, + "loss": 0.9148, + "step": 1920 + }, + { + "epoch": 1.6886895646466855, + "grad_norm": 0.8265687823295593, + "learning_rate": 4.768259394066216e-05, + "loss": 0.9386, + "step": 1930 + }, + { + "epoch": 1.697440385036097, + "grad_norm": 0.7489150762557983, + "learning_rate": 4.7173768063076956e-05, + "loss": 0.9337, + "step": 1940 + }, + { + "epoch": 1.7061912054255086, + "grad_norm": 0.8112419247627258, + "learning_rate": 4.666523565077889e-05, + "loss": 0.917, + "step": 1950 + }, + { + "epoch": 1.7149420258149202, + "grad_norm": 0.7611903548240662, + "learning_rate": 4.615704950785965e-05, + "loss": 0.9338, + "step": 1960 + }, + { + "epoch": 1.7236928462043317, + "grad_norm": 0.7738552093505859, + "learning_rate": 4.5649262402455704e-05, + "loss": 0.9359, + "step": 1970 + }, + { + "epoch": 1.7324436665937433, + "grad_norm": 0.7741129994392395, + "learning_rate": 4.5141927061268844e-05, + "loss": 0.9209, + "step": 1980 + }, + { + "epoch": 1.7411944869831548, + "grad_norm": 0.7815123200416565, + "learning_rate": 4.463509616409144e-05, + "loss": 0.916, + "step": 1990 + }, + { + "epoch": 1.7499453073725662, + "grad_norm": 0.6793907284736633, + "learning_rate": 4.412882233833629e-05, + "loss": 0.9042, + "step": 2000 + }, + { + "epoch": 1.7586961277619777, + "grad_norm": 0.711877167224884, + "learning_rate": 4.362315815357197e-05, + "loss": 0.9072, + "step": 2010 + }, + { + "epoch": 1.767446948151389, + "grad_norm": 0.7671152353286743, + "learning_rate": 4.311815611606423e-05, + "loss": 0.9226, + "step": 2020 + }, + { + "epoch": 1.7761977685408006, + "grad_norm": 0.7221760153770447, + "learning_rate": 4.261386866332397e-05, + "loss": 0.9077, + "step": 2030 + }, + { + "epoch": 1.7849485889302121, + "grad_norm": 0.7419185042381287, + "learning_rate": 4.211034815866228e-05, + "loss": 0.9017, + "step": 2040 + }, + { + "epoch": 1.7936994093196237, + "grad_norm": 0.740652859210968, + "learning_rate": 4.1607646885753206e-05, + "loss": 0.9159, + "step": 2050 + }, + { + "epoch": 1.8024502297090352, + "grad_norm": 0.7923645377159119, + "learning_rate": 4.110581704320495e-05, + "loss": 0.9135, + "step": 2060 + }, + { + "epoch": 1.8112010500984468, + "grad_norm": 0.7528581023216248, + "learning_rate": 4.060491073913957e-05, + "loss": 0.9291, + "step": 2070 + }, + { + "epoch": 1.8199518704878583, + "grad_norm": 0.7974929809570312, + "learning_rate": 4.010497998578239e-05, + "loss": 0.9208, + "step": 2080 + }, + { + "epoch": 1.8287026908772699, + "grad_norm": 0.7388021349906921, + "learning_rate": 3.960607669406129e-05, + "loss": 0.9155, + "step": 2090 + }, + { + "epoch": 1.8374535112666812, + "grad_norm": 0.7927631735801697, + "learning_rate": 3.910825266821629e-05, + "loss": 0.9156, + "step": 2100 + }, + { + "epoch": 1.8462043316560928, + "grad_norm": 0.7545862793922424, + "learning_rate": 3.861155960042057e-05, + "loss": 0.877, + "step": 2110 + }, + { + "epoch": 1.8549551520455043, + "grad_norm": 0.8433863520622253, + "learning_rate": 3.8116049065412864e-05, + "loss": 0.9107, + "step": 2120 + }, + { + "epoch": 1.8637059724349156, + "grad_norm": 0.7610001564025879, + "learning_rate": 3.762177251514218e-05, + "loss": 0.9068, + "step": 2130 + }, + { + "epoch": 1.8724567928243272, + "grad_norm": 0.7452635765075684, + "learning_rate": 3.712878127342515e-05, + "loss": 0.9113, + "step": 2140 + }, + { + "epoch": 1.8812076132137387, + "grad_norm": 0.7530847787857056, + "learning_rate": 3.663712653061682e-05, + "loss": 0.8881, + "step": 2150 + }, + { + "epoch": 1.8899584336031503, + "grad_norm": 0.7940835356712341, + "learning_rate": 3.614685933829525e-05, + "loss": 0.8807, + "step": 2160 + }, + { + "epoch": 1.8987092539925619, + "grad_norm": 0.7291942834854126, + "learning_rate": 3.5658030603960436e-05, + "loss": 0.9112, + "step": 2170 + }, + { + "epoch": 1.9074600743819734, + "grad_norm": 0.7321741580963135, + "learning_rate": 3.5170691085748324e-05, + "loss": 0.8835, + "step": 2180 + }, + { + "epoch": 1.916210894771385, + "grad_norm": 0.7166718244552612, + "learning_rate": 3.468489138716029e-05, + "loss": 0.9115, + "step": 2190 + }, + { + "epoch": 1.9249617151607963, + "grad_norm": 0.741908848285675, + "learning_rate": 3.42006819518086e-05, + "loss": 0.9198, + "step": 2200 + }, + { + "epoch": 1.9337125355502078, + "grad_norm": 0.8034552931785583, + "learning_rate": 3.371811305817858e-05, + "loss": 0.8952, + "step": 2210 + }, + { + "epoch": 1.9424633559396194, + "grad_norm": 0.6716712713241577, + "learning_rate": 3.32372348144079e-05, + "loss": 0.9197, + "step": 2220 + }, + { + "epoch": 1.9512141763290307, + "grad_norm": 0.6731935739517212, + "learning_rate": 3.275809715308349e-05, + "loss": 0.8949, + "step": 2230 + }, + { + "epoch": 1.9599649967184423, + "grad_norm": 0.7521949410438538, + "learning_rate": 3.228074982605673e-05, + "loss": 0.8949, + "step": 2240 + }, + { + "epoch": 1.9687158171078538, + "grad_norm": 0.6889147162437439, + "learning_rate": 3.180524239927749e-05, + "loss": 0.8941, + "step": 2250 + }, + { + "epoch": 1.9774666374972654, + "grad_norm": 0.7169541716575623, + "learning_rate": 3.1331624247647276e-05, + "loss": 0.8922, + "step": 2260 + }, + { + "epoch": 1.986217457886677, + "grad_norm": 0.7812347412109375, + "learning_rate": 3.0859944549892325e-05, + "loss": 0.8915, + "step": 2270 + }, + { + "epoch": 1.9949682782760885, + "grad_norm": 0.7609400153160095, + "learning_rate": 3.039025228345725e-05, + "loss": 0.9227, + "step": 2280 + }, + { + "epoch": 2.0035003281557646, + "grad_norm": 0.7317432165145874, + "learning_rate": 2.9922596219419158e-05, + "loss": 0.8076, + "step": 2290 + }, + { + "epoch": 2.012251148545176, + "grad_norm": 0.8811588883399963, + "learning_rate": 2.9457024917423593e-05, + "loss": 0.6705, + "step": 2300 + }, + { + "epoch": 2.0210019689345877, + "grad_norm": 0.856757640838623, + "learning_rate": 2.8993586720642307e-05, + "loss": 0.6602, + "step": 2310 + }, + { + "epoch": 2.0297527893239993, + "grad_norm": 0.791458249092102, + "learning_rate": 2.85323297507534e-05, + "loss": 0.6417, + "step": 2320 + }, + { + "epoch": 2.038503609713411, + "grad_norm": 0.8533851504325867, + "learning_rate": 2.8073301902944515e-05, + "loss": 0.6673, + "step": 2330 + }, + { + "epoch": 2.047254430102822, + "grad_norm": 0.8373380899429321, + "learning_rate": 2.7616550840939757e-05, + "loss": 0.6674, + "step": 2340 + }, + { + "epoch": 2.0560052504922335, + "grad_norm": 0.8470285534858704, + "learning_rate": 2.7162123992050316e-05, + "loss": 0.6611, + "step": 2350 + }, + { + "epoch": 2.064756070881645, + "grad_norm": 0.8354354500770569, + "learning_rate": 2.671006854224982e-05, + "loss": 0.6449, + "step": 2360 + }, + { + "epoch": 2.0735068912710566, + "grad_norm": 0.8518164157867432, + "learning_rate": 2.626043143127477e-05, + "loss": 0.6387, + "step": 2370 + }, + { + "epoch": 2.082257711660468, + "grad_norm": 0.9259853959083557, + "learning_rate": 2.5813259347750447e-05, + "loss": 0.6864, + "step": 2380 + }, + { + "epoch": 2.0910085320498797, + "grad_norm": 0.8142094612121582, + "learning_rate": 2.5368598724342974e-05, + "loss": 0.6668, + "step": 2390 + }, + { + "epoch": 2.0997593524392912, + "grad_norm": 0.8513460755348206, + "learning_rate": 2.4926495732937876e-05, + "loss": 0.6588, + "step": 2400 + }, + { + "epoch": 2.108510172828703, + "grad_norm": 0.8699485063552856, + "learning_rate": 2.4486996279845862e-05, + "loss": 0.681, + "step": 2410 + }, + { + "epoch": 2.1172609932181143, + "grad_norm": 0.8531279563903809, + "learning_rate": 2.4050146001035983e-05, + "loss": 0.6548, + "step": 2420 + }, + { + "epoch": 2.126011813607526, + "grad_norm": 0.8686200976371765, + "learning_rate": 2.3615990257396946e-05, + "loss": 0.6546, + "step": 2430 + }, + { + "epoch": 2.134762633996937, + "grad_norm": 0.8861080408096313, + "learning_rate": 2.318457413002718e-05, + "loss": 0.655, + "step": 2440 + }, + { + "epoch": 2.1435134543863485, + "grad_norm": 0.8589378595352173, + "learning_rate": 2.2755942415553593e-05, + "loss": 0.6359, + "step": 2450 + }, + { + "epoch": 2.15226427477576, + "grad_norm": 0.784140944480896, + "learning_rate": 2.233013962148016e-05, + "loss": 0.6206, + "step": 2460 + }, + { + "epoch": 2.1610150951651717, + "grad_norm": 0.9516744613647461, + "learning_rate": 2.1907209961566415e-05, + "loss": 0.671, + "step": 2470 + }, + { + "epoch": 2.169765915554583, + "grad_norm": 0.8857921957969666, + "learning_rate": 2.1487197351236443e-05, + "loss": 0.6435, + "step": 2480 + }, + { + "epoch": 2.1785167359439948, + "grad_norm": 0.8351215124130249, + "learning_rate": 2.107014540301886e-05, + "loss": 0.6536, + "step": 2490 + }, + { + "epoch": 2.1872675563334063, + "grad_norm": 0.8609489798545837, + "learning_rate": 2.0656097422018346e-05, + "loss": 0.652, + "step": 2500 + }, + { + "epoch": 2.196018376722818, + "grad_norm": 0.8463150858879089, + "learning_rate": 2.024509640141885e-05, + "loss": 0.6601, + "step": 2510 + }, + { + "epoch": 2.2047691971122294, + "grad_norm": 0.8469570279121399, + "learning_rate": 1.9837185018019467e-05, + "loss": 0.6646, + "step": 2520 + }, + { + "epoch": 2.213520017501641, + "grad_norm": 0.870857298374176, + "learning_rate": 1.9432405627802963e-05, + "loss": 0.6429, + "step": 2530 + }, + { + "epoch": 2.2222708378910525, + "grad_norm": 0.865593671798706, + "learning_rate": 1.903080026153774e-05, + "loss": 0.649, + "step": 2540 + }, + { + "epoch": 2.2310216582804636, + "grad_norm": 0.8608151078224182, + "learning_rate": 1.8632410620413503e-05, + "loss": 0.6564, + "step": 2550 + }, + { + "epoch": 2.239772478669875, + "grad_norm": 0.8044232726097107, + "learning_rate": 1.823727807171115e-05, + "loss": 0.6786, + "step": 2560 + }, + { + "epoch": 2.2485232990592867, + "grad_norm": 0.8390374779701233, + "learning_rate": 1.7845443644507354e-05, + "loss": 0.6385, + "step": 2570 + }, + { + "epoch": 2.2572741194486983, + "grad_norm": 0.8899725079536438, + "learning_rate": 1.745694802541429e-05, + "loss": 0.6674, + "step": 2580 + }, + { + "epoch": 2.26602493983811, + "grad_norm": 0.8680664300918579, + "learning_rate": 1.7071831554354823e-05, + "loss": 0.6337, + "step": 2590 + }, + { + "epoch": 2.2747757602275214, + "grad_norm": 0.843752384185791, + "learning_rate": 1.6690134220373864e-05, + "loss": 0.6582, + "step": 2600 + }, + { + "epoch": 2.283526580616933, + "grad_norm": 0.8479620814323425, + "learning_rate": 1.631189565748596e-05, + "loss": 0.6531, + "step": 2610 + }, + { + "epoch": 2.2922774010063445, + "grad_norm": 0.8540963530540466, + "learning_rate": 1.5937155140559884e-05, + "loss": 0.6386, + "step": 2620 + }, + { + "epoch": 2.301028221395756, + "grad_norm": 0.8910626769065857, + "learning_rate": 1.556595158124049e-05, + "loss": 0.6533, + "step": 2630 + }, + { + "epoch": 2.309779041785167, + "grad_norm": 0.8980609178543091, + "learning_rate": 1.5198323523908265e-05, + "loss": 0.6487, + "step": 2640 + }, + { + "epoch": 2.3185298621745787, + "grad_norm": 0.8651220202445984, + "learning_rate": 1.483430914167701e-05, + "loss": 0.6598, + "step": 2650 + }, + { + "epoch": 2.3272806825639902, + "grad_norm": 0.9363301396369934, + "learning_rate": 1.447394623243018e-05, + "loss": 0.678, + "step": 2660 + }, + { + "epoch": 2.336031502953402, + "grad_norm": 0.8213711977005005, + "learning_rate": 1.4117272214895899e-05, + "loss": 0.6359, + "step": 2670 + }, + { + "epoch": 2.3447823233428133, + "grad_norm": 0.8319981694221497, + "learning_rate": 1.3764324124761735e-05, + "loss": 0.6698, + "step": 2680 + }, + { + "epoch": 2.353533143732225, + "grad_norm": 0.8644684553146362, + "learning_rate": 1.3415138610828988e-05, + "loss": 0.6499, + "step": 2690 + }, + { + "epoch": 2.3622839641216364, + "grad_norm": 0.8030415773391724, + "learning_rate": 1.3069751931207164e-05, + "loss": 0.6219, + "step": 2700 + }, + { + "epoch": 2.371034784511048, + "grad_norm": 0.717867374420166, + "learning_rate": 1.2728199949549142e-05, + "loss": 0.6315, + "step": 2710 + }, + { + "epoch": 2.3797856049004595, + "grad_norm": 0.790641188621521, + "learning_rate": 1.2390518131327172e-05, + "loss": 0.6273, + "step": 2720 + }, + { + "epoch": 2.388536425289871, + "grad_norm": 0.7971424460411072, + "learning_rate": 1.2056741540150328e-05, + "loss": 0.6415, + "step": 2730 + }, + { + "epoch": 2.3972872456792826, + "grad_norm": 0.8711332678794861, + "learning_rate": 1.1726904834123581e-05, + "loss": 0.6474, + "step": 2740 + }, + { + "epoch": 2.4060380660686937, + "grad_norm": 0.9122375249862671, + "learning_rate": 1.1401042262249057e-05, + "loss": 0.656, + "step": 2750 + }, + { + "epoch": 2.4147888864581053, + "grad_norm": 0.9008005261421204, + "learning_rate": 1.10791876608698e-05, + "loss": 0.6204, + "step": 2760 + }, + { + "epoch": 2.423539706847517, + "grad_norm": 0.7929515838623047, + "learning_rate": 1.0761374450156202e-05, + "loss": 0.6271, + "step": 2770 + }, + { + "epoch": 2.4322905272369284, + "grad_norm": 0.8115386962890625, + "learning_rate": 1.04476356306359e-05, + "loss": 0.63, + "step": 2780 + }, + { + "epoch": 2.44104134762634, + "grad_norm": 0.8349243402481079, + "learning_rate": 1.0138003779767103e-05, + "loss": 0.6557, + "step": 2790 + }, + { + "epoch": 2.4497921680157515, + "grad_norm": 0.8012370467185974, + "learning_rate": 9.832511048555826e-06, + "loss": 0.6668, + "step": 2800 + }, + { + "epoch": 2.458542988405163, + "grad_norm": 0.885390043258667, + "learning_rate": 9.53118915821748e-06, + "loss": 0.6331, + "step": 2810 + }, + { + "epoch": 2.4672938087945746, + "grad_norm": 0.8025451302528381, + "learning_rate": 9.234069396883066e-06, + "loss": 0.6539, + "step": 2820 + }, + { + "epoch": 2.476044629183986, + "grad_norm": 0.8048675060272217, + "learning_rate": 8.941182616350318e-06, + "loss": 0.6396, + "step": 2830 + }, + { + "epoch": 2.4847954495733973, + "grad_norm": 0.8225316405296326, + "learning_rate": 8.65255922888017e-06, + "loss": 0.6491, + "step": 2840 + }, + { + "epoch": 2.493546269962809, + "grad_norm": 0.8796355128288269, + "learning_rate": 8.368229204038897e-06, + "loss": 0.665, + "step": 2850 + }, + { + "epoch": 2.5022970903522204, + "grad_norm": 0.8243616223335266, + "learning_rate": 8.088222065586132e-06, + "loss": 0.6448, + "step": 2860 + }, + { + "epoch": 2.511047910741632, + "grad_norm": 0.873279333114624, + "learning_rate": 7.812566888409228e-06, + "loss": 0.6534, + "step": 2870 + }, + { + "epoch": 2.5197987311310435, + "grad_norm": 0.9333387017250061, + "learning_rate": 7.541292295504327e-06, + "loss": 0.6393, + "step": 2880 + }, + { + "epoch": 2.528549551520455, + "grad_norm": 0.800175666809082, + "learning_rate": 7.274426455004129e-06, + "loss": 0.6389, + "step": 2890 + }, + { + "epoch": 2.5373003719098666, + "grad_norm": 0.8389214873313904, + "learning_rate": 7.011997077253113e-06, + "loss": 0.6337, + "step": 2900 + }, + { + "epoch": 2.546051192299278, + "grad_norm": 0.8694761395454407, + "learning_rate": 6.754031411930139e-06, + "loss": 0.6512, + "step": 2910 + }, + { + "epoch": 2.5548020126886897, + "grad_norm": 0.8349895477294922, + "learning_rate": 6.5005562452189865e-06, + "loss": 0.6452, + "step": 2920 + }, + { + "epoch": 2.5635528330781012, + "grad_norm": 0.8583366274833679, + "learning_rate": 6.251597897026951e-06, + "loss": 0.6462, + "step": 2930 + }, + { + "epoch": 2.5723036534675128, + "grad_norm": 0.7806413173675537, + "learning_rate": 6.007182218251883e-06, + "loss": 0.6168, + "step": 2940 + }, + { + "epoch": 2.5810544738569243, + "grad_norm": 0.8689520955085754, + "learning_rate": 5.7673345880979775e-06, + "loss": 0.6336, + "step": 2950 + }, + { + "epoch": 2.5898052942463354, + "grad_norm": 0.7911117672920227, + "learning_rate": 5.532079911440419e-06, + "loss": 0.6244, + "step": 2960 + }, + { + "epoch": 2.598556114635747, + "grad_norm": 0.8084582686424255, + "learning_rate": 5.301442616239372e-06, + "loss": 0.6187, + "step": 2970 + }, + { + "epoch": 2.6073069350251585, + "grad_norm": 0.8228966593742371, + "learning_rate": 5.075446651003535e-06, + "loss": 0.6187, + "step": 2980 + }, + { + "epoch": 2.61605775541457, + "grad_norm": 0.8767485022544861, + "learning_rate": 4.854115482303345e-06, + "loss": 0.617, + "step": 2990 + }, + { + "epoch": 2.6248085758039816, + "grad_norm": 0.8234701752662659, + "learning_rate": 4.637472092334327e-06, + "loss": 0.653, + "step": 3000 + }, + { + "epoch": 2.633559396193393, + "grad_norm": 0.8716809749603271, + "learning_rate": 4.425538976530708e-06, + "loss": 0.6382, + "step": 3010 + }, + { + "epoch": 2.6423102165828047, + "grad_norm": 0.8220137357711792, + "learning_rate": 4.218338141229566e-06, + "loss": 0.6273, + "step": 3020 + }, + { + "epoch": 2.6510610369722163, + "grad_norm": 0.7726868987083435, + "learning_rate": 4.015891101385794e-06, + "loss": 0.631, + "step": 3030 + }, + { + "epoch": 2.6598118573616274, + "grad_norm": 0.8567168116569519, + "learning_rate": 3.818218878338054e-06, + "loss": 0.6436, + "step": 3040 + }, + { + "epoch": 2.668562677751039, + "grad_norm": 0.8137094378471375, + "learning_rate": 3.6253419976260027e-06, + "loss": 0.6439, + "step": 3050 + }, + { + "epoch": 2.6773134981404505, + "grad_norm": 0.835558295249939, + "learning_rate": 3.437280486858996e-06, + "loss": 0.6324, + "step": 3060 + }, + { + "epoch": 2.686064318529862, + "grad_norm": 0.8575820326805115, + "learning_rate": 3.254053873636498e-06, + "loss": 0.6339, + "step": 3070 + }, + { + "epoch": 2.6948151389192736, + "grad_norm": 0.8318324685096741, + "learning_rate": 3.075681183520407e-06, + "loss": 0.6386, + "step": 3080 + }, + { + "epoch": 2.703565959308685, + "grad_norm": 0.8100464940071106, + "learning_rate": 2.9021809380595066e-06, + "loss": 0.6362, + "step": 3090 + }, + { + "epoch": 2.7123167796980967, + "grad_norm": 0.7721264362335205, + "learning_rate": 2.7335711528663046e-06, + "loss": 0.639, + "step": 3100 + }, + { + "epoch": 2.7210676000875083, + "grad_norm": 0.8360996842384338, + "learning_rate": 2.5698693357462665e-06, + "loss": 0.625, + "step": 3110 + }, + { + "epoch": 2.72981842047692, + "grad_norm": 0.859639048576355, + "learning_rate": 2.4110924848799566e-06, + "loss": 0.6159, + "step": 3120 + }, + { + "epoch": 2.7385692408663314, + "grad_norm": 0.9522019624710083, + "learning_rate": 2.2572570870579848e-06, + "loss": 0.6437, + "step": 3130 + }, + { + "epoch": 2.747320061255743, + "grad_norm": 0.8836742639541626, + "learning_rate": 2.1083791159690613e-06, + "loss": 0.6294, + "step": 3140 + }, + { + "epoch": 2.7560708816451545, + "grad_norm": 0.901431143283844, + "learning_rate": 1.9644740305413633e-06, + "loss": 0.6387, + "step": 3150 + }, + { + "epoch": 2.764821702034566, + "grad_norm": 0.8418229818344116, + "learning_rate": 1.825556773337339e-06, + "loss": 0.6355, + "step": 3160 + }, + { + "epoch": 2.773572522423977, + "grad_norm": 0.854288637638092, + "learning_rate": 1.691641769002139e-06, + "loss": 0.6357, + "step": 3170 + }, + { + "epoch": 2.7823233428133887, + "grad_norm": 0.897578239440918, + "learning_rate": 1.5627429227657863e-06, + "loss": 0.6584, + "step": 3180 + }, + { + "epoch": 2.7910741632028, + "grad_norm": 0.94583660364151, + "learning_rate": 1.4388736189993258e-06, + "loss": 0.6333, + "step": 3190 + }, + { + "epoch": 2.7998249835922118, + "grad_norm": 0.8198401927947998, + "learning_rate": 1.3200467198250688e-06, + "loss": 0.6343, + "step": 3200 + }, + { + "epoch": 2.8085758039816233, + "grad_norm": 0.8177739381790161, + "learning_rate": 1.2062745637809736e-06, + "loss": 0.6351, + "step": 3210 + }, + { + "epoch": 2.817326624371035, + "grad_norm": 0.8060468435287476, + "learning_rate": 1.0975689645395193e-06, + "loss": 0.616, + "step": 3220 + }, + { + "epoch": 2.8260774447604464, + "grad_norm": 0.8761562705039978, + "learning_rate": 9.939412096809986e-07, + "loss": 0.6426, + "step": 3230 + }, + { + "epoch": 2.8348282651498575, + "grad_norm": 0.8060517311096191, + "learning_rate": 8.954020595214441e-07, + "loss": 0.6432, + "step": 3240 + }, + { + "epoch": 2.843579085539269, + "grad_norm": 0.8677119016647339, + "learning_rate": 8.019617459953332e-07, + "loss": 0.6246, + "step": 3250 + }, + { + "epoch": 2.8523299059286806, + "grad_norm": 0.8648504018783569, + "learning_rate": 7.136299715931438e-07, + "loss": 0.6246, + "step": 3260 + }, + { + "epoch": 2.861080726318092, + "grad_norm": 0.8173497319221497, + "learning_rate": 6.304159083538652e-07, + "loss": 0.6188, + "step": 3270 + }, + { + "epoch": 2.8698315467075037, + "grad_norm": 0.8254984617233276, + "learning_rate": 5.523281969126271e-07, + "loss": 0.6365, + "step": 3280 + }, + { + "epoch": 2.8785823670969153, + "grad_norm": 0.8288102746009827, + "learning_rate": 4.793749456034946e-07, + "loss": 0.6199, + "step": 3290 + }, + { + "epoch": 2.887333187486327, + "grad_norm": 0.8244780898094177, + "learning_rate": 4.115637296174979e-07, + "loss": 0.6438, + "step": 3300 + }, + { + "epoch": 2.8960840078757384, + "grad_norm": 0.8321549296379089, + "learning_rate": 3.4890159021608303e-07, + "loss": 0.623, + "step": 3310 + }, + { + "epoch": 2.90483482826515, + "grad_norm": 0.748741865158081, + "learning_rate": 2.913950339999638e-07, + "loss": 0.6297, + "step": 3320 + }, + { + "epoch": 2.9135856486545615, + "grad_norm": 0.8655825853347778, + "learning_rate": 2.390500322334954e-07, + "loss": 0.6257, + "step": 3330 + }, + { + "epoch": 2.922336469043973, + "grad_norm": 0.8270664215087891, + "learning_rate": 1.9187202022464823e-07, + "loss": 0.6356, + "step": 3340 + }, + { + "epoch": 2.9310872894333846, + "grad_norm": 0.892652153968811, + "learning_rate": 1.4986589676063145e-07, + "loss": 0.6228, + "step": 3350 + }, + { + "epoch": 2.939838109822796, + "grad_norm": 0.9109422564506531, + "learning_rate": 1.1303602359919452e-07, + "loss": 0.6493, + "step": 3360 + }, + { + "epoch": 2.9485889302122072, + "grad_norm": 0.820085883140564, + "learning_rate": 8.138622501575598e-08, + "loss": 0.5908, + "step": 3370 + }, + { + "epoch": 2.957339750601619, + "grad_norm": 0.8783090114593506, + "learning_rate": 5.491978740627679e-08, + "loss": 0.6305, + "step": 3380 + }, + { + "epoch": 2.9660905709910304, + "grad_norm": 0.8442906141281128, + "learning_rate": 3.36394589460276e-08, + "loss": 0.6265, + "step": 3390 + }, + { + "epoch": 2.974841391380442, + "grad_norm": 0.8543626666069031, + "learning_rate": 1.7547449304222695e-08, + "loss": 0.627, + "step": 3400 + }, + { + "epoch": 2.9835922117698535, + "grad_norm": 0.8204004168510437, + "learning_rate": 6.645429414570137e-09, + "loss": 0.6266, + "step": 3410 + }, + { + "epoch": 2.992343032159265, + "grad_norm": 0.804568350315094, + "learning_rate": 9.34531301793884e-10, + "loss": 0.6332, + "step": 3420 + } + ], + "logging_steps": 10, + "max_steps": 3426, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500.0, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5.3232347449707725e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9f52e2a66c16b0530c7ae36ca438e9b16efac056 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "meta-llama/Llama-3.2-1B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "torch_dtype": "float32", + "transformers_version": "4.48.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..007106e0406b742111f308137a375db48601f26b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.48.1" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00f9dcac3d744806c7904527070594083040e680 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734d2aeb5e154b994fd155feaf57b6525afd1eae019d8905917234a561b21de5 +size 4943274328 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2b049cb645f34e2469590d9c69e2ba406deea7e --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a72045d9f88c05632461100a3e77a33ca8c5aa2ef51ccdb52e4296009bc3a6 +size 1050673280 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..1488fb7da24de8301e39ed4f015bbf4c09693523 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,154 @@ +{ + "metadata": { + "total_size": 5993930752 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|end_of_text|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..aaa72c0bbec93e13707e57ccd48b04be0e28b06f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "\n {{- bos_token }}\n {%- for message in messages %}\n {%- if message['role'] == 'assistant' %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' }}\n {%- generation %}\n {{- message['content'] + '<|eot_id|>' }}\n {%- endgeneration %}\n {{- '\n' }}\n {%- else %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '\n' + message['content'] + '<|eot_id|>' + '\n' }}\n {%- endif %}\n {%- endfor %}\n {%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n' }}\n {%- endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..070a22fd03420bb3151d896a6dafb8d53aa8401c --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551b681dfe4c1a264070f954d2300db3d13ddcf62fc9b45a5d346380ff32f843 +size 6353