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..e1375fa9f177cae664c248f3d76d91cdaebc8862 --- /dev/null +++ b/checkpoint-1143/optimizer_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b855d2662954fceb129a79c5e6ac24e443e74407207c79ceca3520588e4534 +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..c57047f1554e476f0c8f51c8a8d7922dc5cc7a8e --- /dev/null +++ b/checkpoint-1143/optimizer_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150617b53af8b6b3aceff6896c597fe647cbc91246269a9cffe1a08d08aa0a3a +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..0459e9cfcfd697156e6f8ee577b2db51e4848c36 --- /dev/null +++ b/checkpoint-1143/optimizer_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e85ba5f8872d01f6d97181178314da3d6d732e8087dde6ad2a8e4727e5e9e8 +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..f29cf984f60fe9a06e43bb1bec1c1b30ba7d19bd --- /dev/null +++ b/checkpoint-1143/optimizer_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391a83cf4e2a7a8f61fdf23f565b714522f91910370c5cdec4a8dedf5a870fd0 +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..5905c79c73fc98a2691be2ed02e8a02e4182a308 --- /dev/null +++ b/checkpoint-1143/optimizer_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebe83ebbbc82821c1d286b4e6f18f643826d5190cc9fe9a574f3a12c5264065 +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..ed0800f2ff80e03ba614cace518e9cff5ef1f1b1 --- /dev/null +++ b/checkpoint-1143/pytorch_model_fsdp_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac959a9cd92b4b4ae9a37cd34320315a0c5afe58b7a1effc73abd975dfab605b +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..6ca5cc7d38b34fda9198f632f826fe73d2aa6459 --- /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 sha256:8adc9c1295ba6c20e88c04c22fdc77ec8c59424aa962981a9f04a87177537ff0 +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..feae60f9177fa6bfab44ca704abf54f31bbb46f9 --- /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 sha256:1968a21f8dbd8e1b9492a99928fa09cb10c8abd69d88a0fdbf81be383897e233 +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..fe33471d18d107b181c1bfaae9252af8ccc9b3ab --- /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 sha256:119ab7981418c1d6c974e6fc05dca464e47ea0692a0de3864ea0ad64c56942d1 +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..2e3deb56dda10930bab52a2f84381085b3414208 --- /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 sha256:873ef15b1c38e039f61da33ae5db453fa413afbb7e6b5ac9f0265a6c537b2532 +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..e243f6651d3255b3f6fe7d02f21117e14861cb59 --- /dev/null +++ b/checkpoint-1143/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ddbb07fba7ead8a3ab352dd31315c7a538336f468e247e773577e10d3b797ae +size 1465 diff --git a/checkpoint-1143/trainer_state.json b/checkpoint-1143/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1a4525bb22e5aa24170d9319c05a1771a0149db1 --- /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": 0.8244, + "eval_samples_per_second": 24.261, + "eval_steps_per_second": 2.426, + "step": 0 + }, + { + "epoch": 0.0008750820389411508, + "grad_norm": 6.372805118560791, + "learning_rate": 2.915451895043732e-08, + "loss": 1.6434, + "step": 1 + }, + { + "epoch": 0.008750820389411508, + "grad_norm": 6.278440475463867, + "learning_rate": 2.915451895043732e-07, + "loss": 1.7188, + "step": 10 + }, + { + "epoch": 0.017501640778823015, + "grad_norm": 6.023682594299316, + "learning_rate": 5.830903790087464e-07, + "loss": 1.7154, + "step": 20 + }, + { + "epoch": 0.02625246116823452, + "grad_norm": 3.7778327465057373, + "learning_rate": 8.746355685131196e-07, + "loss": 1.6563, + "step": 30 + }, + { + "epoch": 0.03500328155764603, + "grad_norm": 3.8672306537628174, + "learning_rate": 1.1661807580174927e-06, + "loss": 1.5743, + "step": 40 + }, + { + "epoch": 0.04375410194705753, + "grad_norm": 2.53611159324646, + "learning_rate": 1.4577259475218661e-06, + "loss": 1.479, + "step": 50 + }, + { + "epoch": 0.05250492233646904, + "grad_norm": 2.019819974899292, + "learning_rate": 1.7492711370262391e-06, + "loss": 1.4242, + "step": 60 + }, + { + "epoch": 0.06125574272588055, + "grad_norm": 1.7553459405899048, + "learning_rate": 2.0408163265306125e-06, + "loss": 1.3795, + "step": 70 + }, + { + "epoch": 0.07000656311529206, + "grad_norm": 1.4397658109664917, + "learning_rate": 2.3323615160349855e-06, + "loss": 1.3745, + "step": 80 + }, + { + "epoch": 0.07875738350470357, + "grad_norm": 1.5793251991271973, + "learning_rate": 2.6239067055393585e-06, + "loss": 1.3529, + "step": 90 + }, + { + "epoch": 0.08750820389411507, + "grad_norm": 1.5069832801818848, + "learning_rate": 2.9154518950437323e-06, + "loss": 1.3459, + "step": 100 + }, + { + "epoch": 0.09625902428352658, + "grad_norm": 1.4921239614486694, + "learning_rate": 3.2069970845481052e-06, + "loss": 1.2743, + "step": 110 + }, + { + "epoch": 0.10500984467293809, + "grad_norm": 1.4761064052581787, + "learning_rate": 3.4985422740524782e-06, + "loss": 1.2959, + "step": 120 + }, + { + "epoch": 0.1137606650623496, + "grad_norm": 1.4724879264831543, + "learning_rate": 3.790087463556852e-06, + "loss": 1.2773, + "step": 130 + }, + { + "epoch": 0.1225114854517611, + "grad_norm": 1.4954681396484375, + "learning_rate": 4.081632653061225e-06, + "loss": 1.2695, + "step": 140 + }, + { + "epoch": 0.1312623058411726, + "grad_norm": 1.4220881462097168, + "learning_rate": 4.3731778425655976e-06, + "loss": 1.2668, + "step": 150 + }, + { + "epoch": 0.14001312623058412, + "grad_norm": 1.4039027690887451, + "learning_rate": 4.664723032069971e-06, + "loss": 1.2231, + "step": 160 + }, + { + "epoch": 0.14876394661999562, + "grad_norm": 1.468996524810791, + "learning_rate": 4.956268221574344e-06, + "loss": 1.221, + "step": 170 + }, + { + "epoch": 0.15751476700940714, + "grad_norm": 1.5780359506607056, + "learning_rate": 5.247813411078717e-06, + "loss": 1.2403, + "step": 180 + }, + { + "epoch": 0.16626558739881864, + "grad_norm": 1.4090375900268555, + "learning_rate": 5.539358600583091e-06, + "loss": 1.2021, + "step": 190 + }, + { + "epoch": 0.17501640778823013, + "grad_norm": 1.489652395248413, + "learning_rate": 5.8309037900874645e-06, + "loss": 1.1731, + "step": 200 + }, + { + "epoch": 0.18376722817764166, + "grad_norm": 1.3121322393417358, + "learning_rate": 6.122448979591837e-06, + "loss": 1.1924, + "step": 210 + }, + { + "epoch": 0.19251804856705315, + "grad_norm": 1.3954280614852905, + "learning_rate": 6.4139941690962105e-06, + "loss": 1.2121, + "step": 220 + }, + { + "epoch": 0.20126886895646467, + "grad_norm": 1.4191243648529053, + "learning_rate": 6.705539358600584e-06, + "loss": 1.1973, + "step": 230 + }, + { + "epoch": 0.21001968934587617, + "grad_norm": 1.4373400211334229, + "learning_rate": 6.9970845481049564e-06, + "loss": 1.1701, + "step": 240 + }, + { + "epoch": 0.2187705097352877, + "grad_norm": 1.4669713973999023, + "learning_rate": 7.28862973760933e-06, + "loss": 1.1923, + "step": 250 + }, + { + "epoch": 0.2275213301246992, + "grad_norm": 1.4269640445709229, + "learning_rate": 7.580174927113704e-06, + "loss": 1.1713, + "step": 260 + }, + { + "epoch": 0.23627215051411068, + "grad_norm": 1.7535545825958252, + "learning_rate": 7.871720116618077e-06, + "loss": 1.1891, + "step": 270 + }, + { + "epoch": 0.2450229709035222, + "grad_norm": 1.599094271659851, + "learning_rate": 8.16326530612245e-06, + "loss": 1.1827, + "step": 280 + }, + { + "epoch": 0.2537737912929337, + "grad_norm": 1.8278971910476685, + "learning_rate": 8.454810495626823e-06, + "loss": 1.1402, + "step": 290 + }, + { + "epoch": 0.2625246116823452, + "grad_norm": 1.5127216577529907, + "learning_rate": 8.746355685131195e-06, + "loss": 1.1597, + "step": 300 + }, + { + "epoch": 0.27127543207175675, + "grad_norm": 1.6015137434005737, + "learning_rate": 9.03790087463557e-06, + "loss": 1.1398, + "step": 310 + }, + { + "epoch": 0.28002625246116825, + "grad_norm": 1.3944435119628906, + "learning_rate": 9.329446064139942e-06, + "loss": 1.1174, + "step": 320 + }, + { + "epoch": 0.28877707285057974, + "grad_norm": 1.2441927194595337, + "learning_rate": 9.620991253644316e-06, + "loss": 1.1416, + "step": 330 + }, + { + "epoch": 0.29752789323999124, + "grad_norm": 1.4111624956130981, + "learning_rate": 9.912536443148689e-06, + "loss": 1.1352, + "step": 340 + }, + { + "epoch": 0.30627871362940273, + "grad_norm": 1.3007830381393433, + "learning_rate": 9.999872800049233e-06, + "loss": 1.1208, + "step": 350 + }, + { + "epoch": 0.3150295340188143, + "grad_norm": 1.3299254179000854, + "learning_rate": 9.999249795462235e-06, + "loss": 1.142, + "step": 360 + }, + { + "epoch": 0.3237803544082258, + "grad_norm": 1.2524114847183228, + "learning_rate": 9.998107687592326e-06, + "loss": 1.1147, + "step": 370 + }, + { + "epoch": 0.3325311747976373, + "grad_norm": 1.4711254835128784, + "learning_rate": 9.996446595031691e-06, + "loss": 1.1182, + "step": 380 + }, + { + "epoch": 0.34128199518704877, + "grad_norm": 1.3600913286209106, + "learning_rate": 9.994266690261928e-06, + "loss": 1.1565, + "step": 390 + }, + { + "epoch": 0.35003281557646027, + "grad_norm": 1.3752756118774414, + "learning_rate": 9.991568199636149e-06, + "loss": 1.0803, + "step": 400 + }, + { + "epoch": 0.3587836359658718, + "grad_norm": 1.2283236980438232, + "learning_rate": 9.988351403355455e-06, + "loss": 1.1371, + "step": 410 + }, + { + "epoch": 0.3675344563552833, + "grad_norm": 1.266762614250183, + "learning_rate": 9.98461663543987e-06, + "loss": 1.1027, + "step": 420 + }, + { + "epoch": 0.3762852767446948, + "grad_norm": 1.2771412134170532, + "learning_rate": 9.980364283693638e-06, + "loss": 1.0891, + "step": 430 + }, + { + "epoch": 0.3850360971341063, + "grad_norm": 1.2226617336273193, + "learning_rate": 9.97559478966496e-06, + "loss": 1.1105, + "step": 440 + }, + { + "epoch": 0.39378691752351785, + "grad_norm": 1.2738267183303833, + "learning_rate": 9.970308648600142e-06, + "loss": 1.114, + "step": 450 + }, + { + "epoch": 0.40253773791292935, + "grad_norm": 1.3344817161560059, + "learning_rate": 9.964506409392178e-06, + "loss": 1.1178, + "step": 460 + }, + { + "epoch": 0.41128855830234085, + "grad_norm": 1.3076369762420654, + "learning_rate": 9.958188674523748e-06, + "loss": 1.1205, + "step": 470 + }, + { + "epoch": 0.42003937869175234, + "grad_norm": 1.251315712928772, + "learning_rate": 9.951356100004666e-06, + "loss": 1.0795, + "step": 480 + }, + { + "epoch": 0.42879019908116384, + "grad_norm": 1.1784945726394653, + "learning_rate": 9.94400939530375e-06, + "loss": 1.1175, + "step": 490 + }, + { + "epoch": 0.4375410194705754, + "grad_norm": 1.219256043434143, + "learning_rate": 9.93614932327517e-06, + "loss": 1.0933, + "step": 500 + }, + { + "epoch": 0.4462918398599869, + "grad_norm": 1.398763656616211, + "learning_rate": 9.927776700079217e-06, + "loss": 1.1267, + "step": 510 + }, + { + "epoch": 0.4550426602493984, + "grad_norm": 1.25184166431427, + "learning_rate": 9.918892395097572e-06, + "loss": 1.1191, + "step": 520 + }, + { + "epoch": 0.4637934806388099, + "grad_norm": 1.3422456979751587, + "learning_rate": 9.90949733084303e-06, + "loss": 1.1003, + "step": 530 + }, + { + "epoch": 0.47254430102822137, + "grad_norm": 1.3312543630599976, + "learning_rate": 9.8995924828637e-06, + "loss": 1.1004, + "step": 540 + }, + { + "epoch": 0.4812951214176329, + "grad_norm": 1.2708804607391357, + "learning_rate": 9.889178879641717e-06, + "loss": 1.1094, + "step": 550 + }, + { + "epoch": 0.4900459418070444, + "grad_norm": 1.3565181493759155, + "learning_rate": 9.878257602486445e-06, + "loss": 1.1252, + "step": 560 + }, + { + "epoch": 0.4987967621964559, + "grad_norm": 1.232021450996399, + "learning_rate": 9.866829785422201e-06, + "loss": 1.0976, + "step": 570 + }, + { + "epoch": 0.5075475825858674, + "grad_norm": 1.371229887008667, + "learning_rate": 9.854896615070495e-06, + "loss": 1.0941, + "step": 580 + }, + { + "epoch": 0.516298402975279, + "grad_norm": 1.35117769241333, + "learning_rate": 9.842459330526826e-06, + "loss": 1.1127, + "step": 590 + }, + { + "epoch": 0.5250492233646904, + "grad_norm": 1.234413504600525, + "learning_rate": 9.829519223232006e-06, + "loss": 1.09, + "step": 600 + }, + { + "epoch": 0.533800043754102, + "grad_norm": 1.2576864957809448, + "learning_rate": 9.816077636838079e-06, + "loss": 1.1094, + "step": 610 + }, + { + "epoch": 0.5425508641435135, + "grad_norm": 1.340950608253479, + "learning_rate": 9.802135967068783e-06, + "loss": 1.0889, + "step": 620 + }, + { + "epoch": 0.5513016845329249, + "grad_norm": 1.350095272064209, + "learning_rate": 9.787695661574632e-06, + "loss": 1.0661, + "step": 630 + }, + { + "epoch": 0.5600525049223365, + "grad_norm": 1.2629624605178833, + "learning_rate": 9.772758219782601e-06, + "loss": 1.0823, + "step": 640 + }, + { + "epoch": 0.5688033253117479, + "grad_norm": 1.234574556350708, + "learning_rate": 9.757325192740425e-06, + "loss": 1.0937, + "step": 650 + }, + { + "epoch": 0.5775541457011595, + "grad_norm": 1.1775031089782715, + "learning_rate": 9.741398182955548e-06, + "loss": 1.1066, + "step": 660 + }, + { + "epoch": 0.586304966090571, + "grad_norm": 1.2653073072433472, + "learning_rate": 9.724978844228717e-06, + "loss": 1.0964, + "step": 670 + }, + { + "epoch": 0.5950557864799825, + "grad_norm": 1.2665278911590576, + "learning_rate": 9.70806888148227e-06, + "loss": 1.1007, + "step": 680 + }, + { + "epoch": 0.603806606869394, + "grad_norm": 1.2909613847732544, + "learning_rate": 9.690670050583095e-06, + "loss": 1.0973, + "step": 690 + }, + { + "epoch": 0.6125574272588055, + "grad_norm": 1.2396572828292847, + "learning_rate": 9.672784158160307e-06, + "loss": 1.0423, + "step": 700 + }, + { + "epoch": 0.621308247648217, + "grad_norm": 1.2569255828857422, + "learning_rate": 9.654413061417655e-06, + "loss": 1.0764, + "step": 710 + }, + { + "epoch": 0.6300590680376286, + "grad_norm": 1.3747756481170654, + "learning_rate": 9.635558667940683e-06, + "loss": 1.0563, + "step": 720 + }, + { + "epoch": 0.63880988842704, + "grad_norm": 1.2752923965454102, + "learning_rate": 9.616222935498647e-06, + "loss": 1.1084, + "step": 730 + }, + { + "epoch": 0.6475607088164516, + "grad_norm": 1.218320369720459, + "learning_rate": 9.596407871841229e-06, + "loss": 1.0674, + "step": 740 + }, + { + "epoch": 0.656311529205863, + "grad_norm": 1.2466013431549072, + "learning_rate": 9.57611553449006e-06, + "loss": 1.1048, + "step": 750 + }, + { + "epoch": 0.6650623495952745, + "grad_norm": 1.2956342697143555, + "learning_rate": 9.555348030525076e-06, + "loss": 1.0723, + "step": 760 + }, + { + "epoch": 0.6738131699846861, + "grad_norm": 1.29911208152771, + "learning_rate": 9.534107516365725e-06, + "loss": 1.0743, + "step": 770 + }, + { + "epoch": 0.6825639903740975, + "grad_norm": 1.2063359022140503, + "learning_rate": 9.512396197547053e-06, + "loss": 1.0717, + "step": 780 + }, + { + "epoch": 0.6913148107635091, + "grad_norm": 1.184462547302246, + "learning_rate": 9.490216328490693e-06, + "loss": 1.0895, + "step": 790 + }, + { + "epoch": 0.7000656311529205, + "grad_norm": 1.186874270439148, + "learning_rate": 9.467570212270767e-06, + "loss": 1.1476, + "step": 800 + }, + { + "epoch": 0.7088164515423321, + "grad_norm": 1.2901315689086914, + "learning_rate": 9.444460200374747e-06, + "loss": 1.0538, + "step": 810 + }, + { + "epoch": 0.7175672719317436, + "grad_norm": 1.2175313234329224, + "learning_rate": 9.42088869245929e-06, + "loss": 1.079, + "step": 820 + }, + { + "epoch": 0.7263180923211551, + "grad_norm": 1.1771786212921143, + "learning_rate": 9.396858136101066e-06, + "loss": 1.0756, + "step": 830 + }, + { + "epoch": 0.7350689127105666, + "grad_norm": 1.2814205884933472, + "learning_rate": 9.372371026542595e-06, + "loss": 1.0697, + "step": 840 + }, + { + "epoch": 0.7438197330999782, + "grad_norm": 1.2603764533996582, + "learning_rate": 9.347429906433175e-06, + "loss": 1.1079, + "step": 850 + }, + { + "epoch": 0.7525705534893896, + "grad_norm": 1.2228299379348755, + "learning_rate": 9.322037365564844e-06, + "loss": 1.0746, + "step": 860 + }, + { + "epoch": 0.7613213738788012, + "grad_norm": 1.1895763874053955, + "learning_rate": 9.296196040603476e-06, + "loss": 1.0831, + "step": 870 + }, + { + "epoch": 0.7700721942682126, + "grad_norm": 1.2288453578948975, + "learning_rate": 9.269908614814995e-06, + "loss": 1.0649, + "step": 880 + }, + { + "epoch": 0.7788230146576242, + "grad_norm": 1.1580345630645752, + "learning_rate": 9.243177817786757e-06, + "loss": 1.1053, + "step": 890 + }, + { + "epoch": 0.7875738350470357, + "grad_norm": 1.1613861322402954, + "learning_rate": 9.216006425144118e-06, + "loss": 1.0854, + "step": 900 + }, + { + "epoch": 0.7963246554364471, + "grad_norm": 1.0809310674667358, + "learning_rate": 9.188397258262221e-06, + "loss": 1.059, + "step": 910 + }, + { + "epoch": 0.8050754758258587, + "grad_norm": 1.2021125555038452, + "learning_rate": 9.160353183973045e-06, + "loss": 1.064, + "step": 920 + }, + { + "epoch": 0.8138262962152701, + "grad_norm": 1.286584496498108, + "learning_rate": 9.131877114267711e-06, + "loss": 1.0516, + "step": 930 + }, + { + "epoch": 0.8225771166046817, + "grad_norm": 1.177673578262329, + "learning_rate": 9.102972005994123e-06, + "loss": 1.0358, + "step": 940 + }, + { + "epoch": 0.8313279369940932, + "grad_norm": 1.2117091417312622, + "learning_rate": 9.073640860549931e-06, + "loss": 1.0701, + "step": 950 + }, + { + "epoch": 0.8400787573835047, + "grad_norm": 1.2018595933914185, + "learning_rate": 9.043886723570885e-06, + "loss": 1.0833, + "step": 960 + }, + { + "epoch": 0.8488295777729162, + "grad_norm": 1.1337984800338745, + "learning_rate": 9.013712684614582e-06, + "loss": 1.0785, + "step": 970 + }, + { + "epoch": 0.8575803981623277, + "grad_norm": 1.2217832803726196, + "learning_rate": 8.983121876839658e-06, + "loss": 1.0623, + "step": 980 + }, + { + "epoch": 0.8663312185517392, + "grad_norm": 1.2249287366867065, + "learning_rate": 8.95211747668046e-06, + "loss": 1.0285, + "step": 990 + }, + { + "epoch": 0.8750820389411508, + "grad_norm": 1.1673548221588135, + "learning_rate": 8.920702703517205e-06, + "loss": 1.0354, + "step": 1000 + }, + { + "epoch": 0.8838328593305622, + "grad_norm": 1.1298819780349731, + "learning_rate": 8.888880819341703e-06, + "loss": 1.0538, + "step": 1010 + }, + { + "epoch": 0.8925836797199738, + "grad_norm": 1.1600337028503418, + "learning_rate": 8.856655128418638e-06, + "loss": 1.0527, + "step": 1020 + }, + { + "epoch": 0.9013345001093852, + "grad_norm": 1.2292169332504272, + "learning_rate": 8.824028976942465e-06, + "loss": 1.0613, + "step": 1030 + }, + { + "epoch": 0.9100853204987968, + "grad_norm": 1.1878681182861328, + "learning_rate": 8.791005752689958e-06, + "loss": 1.0489, + "step": 1040 + }, + { + "epoch": 0.9188361408882083, + "grad_norm": 1.2165477275848389, + "learning_rate": 8.757588884668435e-06, + "loss": 1.0675, + "step": 1050 + }, + { + "epoch": 0.9275869612776197, + "grad_norm": 1.1682305335998535, + "learning_rate": 8.723781842759696e-06, + "loss": 1.084, + "step": 1060 + }, + { + "epoch": 0.9363377816670313, + "grad_norm": 1.3387882709503174, + "learning_rate": 8.689588137359731e-06, + "loss": 1.0564, + "step": 1070 + }, + { + "epoch": 0.9450886020564427, + "grad_norm": 1.2144585847854614, + "learning_rate": 8.655011319014217e-06, + "loss": 1.08, + "step": 1080 + }, + { + "epoch": 0.9538394224458543, + "grad_norm": 1.2637611627578735, + "learning_rate": 8.620054978049828e-06, + "loss": 1.0716, + "step": 1090 + }, + { + "epoch": 0.9625902428352658, + "grad_norm": 1.230635404586792, + "learning_rate": 8.584722744201448e-06, + "loss": 1.0429, + "step": 1100 + }, + { + "epoch": 0.9713410632246773, + "grad_norm": 1.2495629787445068, + "learning_rate": 8.549018286235255e-06, + "loss": 1.0464, + "step": 1110 + }, + { + "epoch": 0.9800918836140888, + "grad_norm": 1.1702367067337036, + "learning_rate": 8.512945311567786e-06, + "loss": 1.0476, + "step": 1120 + }, + { + "epoch": 0.9888427040035004, + "grad_norm": 1.1367738246917725, + "learning_rate": 8.476507565880959e-06, + "loss": 1.0392, + "step": 1130 + }, + { + "epoch": 0.9975935243929118, + "grad_norm": 1.1903005838394165, + "learning_rate": 8.439708832733142e-06, + "loss": 1.0414, + "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..ef3679fc02a9e00b25efce50aa585c789136fbe1 --- /dev/null +++ b/checkpoint-2286/optimizer_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832596a9b4a95dc8d19b2429cc7735a9b11a9131d7452ae2298aef2b316bccb9 +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..eab2deb59f5277282c9ca1020207443cce0c5908 --- /dev/null +++ b/checkpoint-2286/optimizer_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c893da735e17a501e6be9aaeb5336723cc530fb430317d6d3552bbefc35d44 +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..bd155a5f6997f40a27a96b26da2d67a032564a53 --- /dev/null +++ b/checkpoint-2286/optimizer_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d5f86d0e6b7aeaa34bd79d483ed1223ee8c6de98c9f813595f88257d4acd7b +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..2673f32c55a52d8b8b7dd64518af21b972ff5a4d --- /dev/null +++ b/checkpoint-2286/optimizer_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5e39e82106cbd99b06cb0418b3d33aa1c4f4599d180a56ac89c756e75d2ffa +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..76f14a9c856f4a18f0a8a1325d3ccf1bbe4cade9 --- /dev/null +++ b/checkpoint-2286/optimizer_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64175613ee851c54fb1e76fa75c85e3b89d192f625045a951c58b182d9099b3a +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..f95b1b96bf4d911f9039a184b1c3230f37eb5990 --- /dev/null +++ b/checkpoint-2286/pytorch_model_fsdp_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:909e4a9349539cfe0c0eb9f9789a02d1be64fcdae99a5f750c52f82df3fcc175 +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..39e065f3d5979139db1ddaa0c1a0d9c218deeab1 --- /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:ff0231e8ab7a33b95f87025fea9c359ccb0b935e46aad0604c48b1ecca178860 +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..ed7e01c22b35265bcd0791742c3005cac77abaa0 --- /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 sha256:56f346fe28c1f50d92c00a48fb8f14d29a9bb47fa40371708b89eca2b1475d49 +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..70ab268bfe86edd4d9b1db02b482e31983a353a8 --- /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:bedbf4535d816fa164640c49955149ac0cd0e01f2eeb5eb8f186cc67784f8528 +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..d2ac2cb9f38b2babb8a18953d74ed660c636e637 --- /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:b872ce25c1f25ccab23ed7ee5da4ea1a78d5bcd0709990eec6ea43a5b5c9ee7f +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..1d44467beb05d7d09f44343019e6eabdde2a889b --- /dev/null +++ b/checkpoint-2286/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135d81a4bd51a021ff9c597843c18ead1042037e41e977db16b5209695d08db1 +size 1465 diff --git a/checkpoint-2286/trainer_state.json b/checkpoint-2286/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e1761401f0fe37ff0689d4364a2759bbfe5482ff --- /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": 0.8244, + "eval_samples_per_second": 24.261, + "eval_steps_per_second": 2.426, + "step": 0 + }, + { + "epoch": 0.0008750820389411508, + "grad_norm": 6.372805118560791, + "learning_rate": 2.915451895043732e-08, + "loss": 1.6434, + "step": 1 + }, + { + "epoch": 0.008750820389411508, + "grad_norm": 6.278440475463867, + "learning_rate": 2.915451895043732e-07, + "loss": 1.7188, + "step": 10 + }, + { + "epoch": 0.017501640778823015, + "grad_norm": 6.023682594299316, + "learning_rate": 5.830903790087464e-07, + "loss": 1.7154, + "step": 20 + }, + { + "epoch": 0.02625246116823452, + "grad_norm": 3.7778327465057373, + "learning_rate": 8.746355685131196e-07, + "loss": 1.6563, + "step": 30 + }, + { + "epoch": 0.03500328155764603, + "grad_norm": 3.8672306537628174, + "learning_rate": 1.1661807580174927e-06, + "loss": 1.5743, + "step": 40 + }, + { + "epoch": 0.04375410194705753, + "grad_norm": 2.53611159324646, + "learning_rate": 1.4577259475218661e-06, + "loss": 1.479, + "step": 50 + }, + { + "epoch": 0.05250492233646904, + "grad_norm": 2.019819974899292, + "learning_rate": 1.7492711370262391e-06, + "loss": 1.4242, + "step": 60 + }, + { + "epoch": 0.06125574272588055, + "grad_norm": 1.7553459405899048, + "learning_rate": 2.0408163265306125e-06, + "loss": 1.3795, + "step": 70 + }, + { + "epoch": 0.07000656311529206, + "grad_norm": 1.4397658109664917, + "learning_rate": 2.3323615160349855e-06, + "loss": 1.3745, + "step": 80 + }, + { + "epoch": 0.07875738350470357, + "grad_norm": 1.5793251991271973, + "learning_rate": 2.6239067055393585e-06, + "loss": 1.3529, + "step": 90 + }, + { + "epoch": 0.08750820389411507, + "grad_norm": 1.5069832801818848, + "learning_rate": 2.9154518950437323e-06, + "loss": 1.3459, + "step": 100 + }, + { + "epoch": 0.09625902428352658, + "grad_norm": 1.4921239614486694, + "learning_rate": 3.2069970845481052e-06, + "loss": 1.2743, + "step": 110 + }, + { + "epoch": 0.10500984467293809, + "grad_norm": 1.4761064052581787, + "learning_rate": 3.4985422740524782e-06, + "loss": 1.2959, + "step": 120 + }, + { + "epoch": 0.1137606650623496, + "grad_norm": 1.4724879264831543, + "learning_rate": 3.790087463556852e-06, + "loss": 1.2773, + "step": 130 + }, + { + "epoch": 0.1225114854517611, + "grad_norm": 1.4954681396484375, + "learning_rate": 4.081632653061225e-06, + "loss": 1.2695, + "step": 140 + }, + { + "epoch": 0.1312623058411726, + "grad_norm": 1.4220881462097168, + "learning_rate": 4.3731778425655976e-06, + "loss": 1.2668, + "step": 150 + }, + { + "epoch": 0.14001312623058412, + "grad_norm": 1.4039027690887451, + "learning_rate": 4.664723032069971e-06, + "loss": 1.2231, + "step": 160 + }, + { + "epoch": 0.14876394661999562, + "grad_norm": 1.468996524810791, + "learning_rate": 4.956268221574344e-06, + "loss": 1.221, + "step": 170 + }, + { + "epoch": 0.15751476700940714, + "grad_norm": 1.5780359506607056, + "learning_rate": 5.247813411078717e-06, + "loss": 1.2403, + "step": 180 + }, + { + "epoch": 0.16626558739881864, + "grad_norm": 1.4090375900268555, + "learning_rate": 5.539358600583091e-06, + "loss": 1.2021, + "step": 190 + }, + { + "epoch": 0.17501640778823013, + "grad_norm": 1.489652395248413, + "learning_rate": 5.8309037900874645e-06, + "loss": 1.1731, + "step": 200 + }, + { + "epoch": 0.18376722817764166, + "grad_norm": 1.3121322393417358, + "learning_rate": 6.122448979591837e-06, + "loss": 1.1924, + "step": 210 + }, + { + "epoch": 0.19251804856705315, + "grad_norm": 1.3954280614852905, + "learning_rate": 6.4139941690962105e-06, + "loss": 1.2121, + "step": 220 + }, + { + "epoch": 0.20126886895646467, + "grad_norm": 1.4191243648529053, + "learning_rate": 6.705539358600584e-06, + "loss": 1.1973, + "step": 230 + }, + { + "epoch": 0.21001968934587617, + "grad_norm": 1.4373400211334229, + "learning_rate": 6.9970845481049564e-06, + "loss": 1.1701, + "step": 240 + }, + { + "epoch": 0.2187705097352877, + "grad_norm": 1.4669713973999023, + "learning_rate": 7.28862973760933e-06, + "loss": 1.1923, + "step": 250 + }, + { + "epoch": 0.2275213301246992, + "grad_norm": 1.4269640445709229, + "learning_rate": 7.580174927113704e-06, + "loss": 1.1713, + "step": 260 + }, + { + "epoch": 0.23627215051411068, + "grad_norm": 1.7535545825958252, + "learning_rate": 7.871720116618077e-06, + "loss": 1.1891, + "step": 270 + }, + { + "epoch": 0.2450229709035222, + "grad_norm": 1.599094271659851, + "learning_rate": 8.16326530612245e-06, + "loss": 1.1827, + "step": 280 + }, + { + "epoch": 0.2537737912929337, + "grad_norm": 1.8278971910476685, + "learning_rate": 8.454810495626823e-06, + "loss": 1.1402, + "step": 290 + }, + { + "epoch": 0.2625246116823452, + "grad_norm": 1.5127216577529907, + "learning_rate": 8.746355685131195e-06, + "loss": 1.1597, + "step": 300 + }, + { + "epoch": 0.27127543207175675, + "grad_norm": 1.6015137434005737, + "learning_rate": 9.03790087463557e-06, + "loss": 1.1398, + "step": 310 + }, + { + "epoch": 0.28002625246116825, + "grad_norm": 1.3944435119628906, + "learning_rate": 9.329446064139942e-06, + "loss": 1.1174, + "step": 320 + }, + { + "epoch": 0.28877707285057974, + "grad_norm": 1.2441927194595337, + "learning_rate": 9.620991253644316e-06, + "loss": 1.1416, + "step": 330 + }, + { + "epoch": 0.29752789323999124, + "grad_norm": 1.4111624956130981, + "learning_rate": 9.912536443148689e-06, + "loss": 1.1352, + "step": 340 + }, + { + "epoch": 0.30627871362940273, + "grad_norm": 1.3007830381393433, + "learning_rate": 9.999872800049233e-06, + "loss": 1.1208, + "step": 350 + }, + { + "epoch": 0.3150295340188143, + "grad_norm": 1.3299254179000854, + "learning_rate": 9.999249795462235e-06, + "loss": 1.142, + "step": 360 + }, + { + "epoch": 0.3237803544082258, + "grad_norm": 1.2524114847183228, + "learning_rate": 9.998107687592326e-06, + "loss": 1.1147, + "step": 370 + }, + { + "epoch": 0.3325311747976373, + "grad_norm": 1.4711254835128784, + "learning_rate": 9.996446595031691e-06, + "loss": 1.1182, + "step": 380 + }, + { + "epoch": 0.34128199518704877, + "grad_norm": 1.3600913286209106, + "learning_rate": 9.994266690261928e-06, + "loss": 1.1565, + "step": 390 + }, + { + "epoch": 0.35003281557646027, + "grad_norm": 1.3752756118774414, + "learning_rate": 9.991568199636149e-06, + "loss": 1.0803, + "step": 400 + }, + { + "epoch": 0.3587836359658718, + "grad_norm": 1.2283236980438232, + "learning_rate": 9.988351403355455e-06, + "loss": 1.1371, + "step": 410 + }, + { + "epoch": 0.3675344563552833, + "grad_norm": 1.266762614250183, + "learning_rate": 9.98461663543987e-06, + "loss": 1.1027, + "step": 420 + }, + { + "epoch": 0.3762852767446948, + "grad_norm": 1.2771412134170532, + "learning_rate": 9.980364283693638e-06, + "loss": 1.0891, + "step": 430 + }, + { + "epoch": 0.3850360971341063, + "grad_norm": 1.2226617336273193, + "learning_rate": 9.97559478966496e-06, + "loss": 1.1105, + "step": 440 + }, + { + "epoch": 0.39378691752351785, + "grad_norm": 1.2738267183303833, + "learning_rate": 9.970308648600142e-06, + "loss": 1.114, + "step": 450 + }, + { + "epoch": 0.40253773791292935, + "grad_norm": 1.3344817161560059, + "learning_rate": 9.964506409392178e-06, + "loss": 1.1178, + "step": 460 + }, + { + "epoch": 0.41128855830234085, + "grad_norm": 1.3076369762420654, + "learning_rate": 9.958188674523748e-06, + "loss": 1.1205, + "step": 470 + }, + { + "epoch": 0.42003937869175234, + "grad_norm": 1.251315712928772, + "learning_rate": 9.951356100004666e-06, + "loss": 1.0795, + "step": 480 + }, + { + "epoch": 0.42879019908116384, + "grad_norm": 1.1784945726394653, + "learning_rate": 9.94400939530375e-06, + "loss": 1.1175, + "step": 490 + }, + { + "epoch": 0.4375410194705754, + "grad_norm": 1.219256043434143, + "learning_rate": 9.93614932327517e-06, + "loss": 1.0933, + "step": 500 + }, + { + "epoch": 0.4462918398599869, + "grad_norm": 1.398763656616211, + "learning_rate": 9.927776700079217e-06, + "loss": 1.1267, + "step": 510 + }, + { + "epoch": 0.4550426602493984, + "grad_norm": 1.25184166431427, + "learning_rate": 9.918892395097572e-06, + "loss": 1.1191, + "step": 520 + }, + { + "epoch": 0.4637934806388099, + "grad_norm": 1.3422456979751587, + "learning_rate": 9.90949733084303e-06, + "loss": 1.1003, + "step": 530 + }, + { + "epoch": 0.47254430102822137, + "grad_norm": 1.3312543630599976, + "learning_rate": 9.8995924828637e-06, + "loss": 1.1004, + "step": 540 + }, + { + "epoch": 0.4812951214176329, + "grad_norm": 1.2708804607391357, + "learning_rate": 9.889178879641717e-06, + "loss": 1.1094, + "step": 550 + }, + { + "epoch": 0.4900459418070444, + "grad_norm": 1.3565181493759155, + "learning_rate": 9.878257602486445e-06, + "loss": 1.1252, + "step": 560 + }, + { + "epoch": 0.4987967621964559, + "grad_norm": 1.232021450996399, + "learning_rate": 9.866829785422201e-06, + "loss": 1.0976, + "step": 570 + }, + { + "epoch": 0.5075475825858674, + "grad_norm": 1.371229887008667, + "learning_rate": 9.854896615070495e-06, + "loss": 1.0941, + "step": 580 + }, + { + "epoch": 0.516298402975279, + "grad_norm": 1.35117769241333, + "learning_rate": 9.842459330526826e-06, + "loss": 1.1127, + "step": 590 + }, + { + "epoch": 0.5250492233646904, + "grad_norm": 1.234413504600525, + "learning_rate": 9.829519223232006e-06, + "loss": 1.09, + "step": 600 + }, + { + "epoch": 0.533800043754102, + "grad_norm": 1.2576864957809448, + "learning_rate": 9.816077636838079e-06, + "loss": 1.1094, + "step": 610 + }, + { + "epoch": 0.5425508641435135, + "grad_norm": 1.340950608253479, + "learning_rate": 9.802135967068783e-06, + "loss": 1.0889, + "step": 620 + }, + { + "epoch": 0.5513016845329249, + "grad_norm": 1.350095272064209, + "learning_rate": 9.787695661574632e-06, + "loss": 1.0661, + "step": 630 + }, + { + "epoch": 0.5600525049223365, + "grad_norm": 1.2629624605178833, + "learning_rate": 9.772758219782601e-06, + "loss": 1.0823, + "step": 640 + }, + { + "epoch": 0.5688033253117479, + "grad_norm": 1.234574556350708, + "learning_rate": 9.757325192740425e-06, + "loss": 1.0937, + "step": 650 + }, + { + "epoch": 0.5775541457011595, + "grad_norm": 1.1775031089782715, + "learning_rate": 9.741398182955548e-06, + "loss": 1.1066, + "step": 660 + }, + { + "epoch": 0.586304966090571, + "grad_norm": 1.2653073072433472, + "learning_rate": 9.724978844228717e-06, + "loss": 1.0964, + "step": 670 + }, + { + "epoch": 0.5950557864799825, + "grad_norm": 1.2665278911590576, + "learning_rate": 9.70806888148227e-06, + "loss": 1.1007, + "step": 680 + }, + { + "epoch": 0.603806606869394, + "grad_norm": 1.2909613847732544, + "learning_rate": 9.690670050583095e-06, + "loss": 1.0973, + "step": 690 + }, + { + "epoch": 0.6125574272588055, + "grad_norm": 1.2396572828292847, + "learning_rate": 9.672784158160307e-06, + "loss": 1.0423, + "step": 700 + }, + { + "epoch": 0.621308247648217, + "grad_norm": 1.2569255828857422, + "learning_rate": 9.654413061417655e-06, + "loss": 1.0764, + "step": 710 + }, + { + "epoch": 0.6300590680376286, + "grad_norm": 1.3747756481170654, + "learning_rate": 9.635558667940683e-06, + "loss": 1.0563, + "step": 720 + }, + { + "epoch": 0.63880988842704, + "grad_norm": 1.2752923965454102, + "learning_rate": 9.616222935498647e-06, + "loss": 1.1084, + "step": 730 + }, + { + "epoch": 0.6475607088164516, + "grad_norm": 1.218320369720459, + "learning_rate": 9.596407871841229e-06, + "loss": 1.0674, + "step": 740 + }, + { + "epoch": 0.656311529205863, + "grad_norm": 1.2466013431549072, + "learning_rate": 9.57611553449006e-06, + "loss": 1.1048, + "step": 750 + }, + { + "epoch": 0.6650623495952745, + "grad_norm": 1.2956342697143555, + "learning_rate": 9.555348030525076e-06, + "loss": 1.0723, + "step": 760 + }, + { + "epoch": 0.6738131699846861, + "grad_norm": 1.29911208152771, + "learning_rate": 9.534107516365725e-06, + "loss": 1.0743, + "step": 770 + }, + { + "epoch": 0.6825639903740975, + "grad_norm": 1.2063359022140503, + "learning_rate": 9.512396197547053e-06, + "loss": 1.0717, + "step": 780 + }, + { + "epoch": 0.6913148107635091, + "grad_norm": 1.184462547302246, + "learning_rate": 9.490216328490693e-06, + "loss": 1.0895, + "step": 790 + }, + { + "epoch": 0.7000656311529205, + "grad_norm": 1.186874270439148, + "learning_rate": 9.467570212270767e-06, + "loss": 1.1476, + "step": 800 + }, + { + "epoch": 0.7088164515423321, + "grad_norm": 1.2901315689086914, + "learning_rate": 9.444460200374747e-06, + "loss": 1.0538, + "step": 810 + }, + { + "epoch": 0.7175672719317436, + "grad_norm": 1.2175313234329224, + "learning_rate": 9.42088869245929e-06, + "loss": 1.079, + "step": 820 + }, + { + "epoch": 0.7263180923211551, + "grad_norm": 1.1771786212921143, + "learning_rate": 9.396858136101066e-06, + "loss": 1.0756, + "step": 830 + }, + { + "epoch": 0.7350689127105666, + "grad_norm": 1.2814205884933472, + "learning_rate": 9.372371026542595e-06, + "loss": 1.0697, + "step": 840 + }, + { + "epoch": 0.7438197330999782, + "grad_norm": 1.2603764533996582, + "learning_rate": 9.347429906433175e-06, + "loss": 1.1079, + "step": 850 + }, + { + "epoch": 0.7525705534893896, + "grad_norm": 1.2228299379348755, + "learning_rate": 9.322037365564844e-06, + "loss": 1.0746, + "step": 860 + }, + { + "epoch": 0.7613213738788012, + "grad_norm": 1.1895763874053955, + "learning_rate": 9.296196040603476e-06, + "loss": 1.0831, + "step": 870 + }, + { + "epoch": 0.7700721942682126, + "grad_norm": 1.2288453578948975, + "learning_rate": 9.269908614814995e-06, + "loss": 1.0649, + "step": 880 + }, + { + "epoch": 0.7788230146576242, + "grad_norm": 1.1580345630645752, + "learning_rate": 9.243177817786757e-06, + "loss": 1.1053, + "step": 890 + }, + { + "epoch": 0.7875738350470357, + "grad_norm": 1.1613861322402954, + "learning_rate": 9.216006425144118e-06, + "loss": 1.0854, + "step": 900 + }, + { + "epoch": 0.7963246554364471, + "grad_norm": 1.0809310674667358, + "learning_rate": 9.188397258262221e-06, + "loss": 1.059, + "step": 910 + }, + { + "epoch": 0.8050754758258587, + "grad_norm": 1.2021125555038452, + "learning_rate": 9.160353183973045e-06, + "loss": 1.064, + "step": 920 + }, + { + "epoch": 0.8138262962152701, + "grad_norm": 1.286584496498108, + "learning_rate": 9.131877114267711e-06, + "loss": 1.0516, + "step": 930 + }, + { + "epoch": 0.8225771166046817, + "grad_norm": 1.177673578262329, + "learning_rate": 9.102972005994123e-06, + "loss": 1.0358, + "step": 940 + }, + { + "epoch": 0.8313279369940932, + "grad_norm": 1.2117091417312622, + "learning_rate": 9.073640860549931e-06, + "loss": 1.0701, + "step": 950 + }, + { + "epoch": 0.8400787573835047, + "grad_norm": 1.2018595933914185, + "learning_rate": 9.043886723570885e-06, + "loss": 1.0833, + "step": 960 + }, + { + "epoch": 0.8488295777729162, + "grad_norm": 1.1337984800338745, + "learning_rate": 9.013712684614582e-06, + "loss": 1.0785, + "step": 970 + }, + { + "epoch": 0.8575803981623277, + "grad_norm": 1.2217832803726196, + "learning_rate": 8.983121876839658e-06, + "loss": 1.0623, + "step": 980 + }, + { + "epoch": 0.8663312185517392, + "grad_norm": 1.2249287366867065, + "learning_rate": 8.95211747668046e-06, + "loss": 1.0285, + "step": 990 + }, + { + "epoch": 0.8750820389411508, + "grad_norm": 1.1673548221588135, + "learning_rate": 8.920702703517205e-06, + "loss": 1.0354, + "step": 1000 + }, + { + "epoch": 0.8838328593305622, + "grad_norm": 1.1298819780349731, + "learning_rate": 8.888880819341703e-06, + "loss": 1.0538, + "step": 1010 + }, + { + "epoch": 0.8925836797199738, + "grad_norm": 1.1600337028503418, + "learning_rate": 8.856655128418638e-06, + "loss": 1.0527, + "step": 1020 + }, + { + "epoch": 0.9013345001093852, + "grad_norm": 1.2292169332504272, + "learning_rate": 8.824028976942465e-06, + "loss": 1.0613, + "step": 1030 + }, + { + "epoch": 0.9100853204987968, + "grad_norm": 1.1878681182861328, + "learning_rate": 8.791005752689958e-06, + "loss": 1.0489, + "step": 1040 + }, + { + "epoch": 0.9188361408882083, + "grad_norm": 1.2165477275848389, + "learning_rate": 8.757588884668435e-06, + "loss": 1.0675, + "step": 1050 + }, + { + "epoch": 0.9275869612776197, + "grad_norm": 1.1682305335998535, + "learning_rate": 8.723781842759696e-06, + "loss": 1.084, + "step": 1060 + }, + { + "epoch": 0.9363377816670313, + "grad_norm": 1.3387882709503174, + "learning_rate": 8.689588137359731e-06, + "loss": 1.0564, + "step": 1070 + }, + { + "epoch": 0.9450886020564427, + "grad_norm": 1.2144585847854614, + "learning_rate": 8.655011319014217e-06, + "loss": 1.08, + "step": 1080 + }, + { + "epoch": 0.9538394224458543, + "grad_norm": 1.2637611627578735, + "learning_rate": 8.620054978049828e-06, + "loss": 1.0716, + "step": 1090 + }, + { + "epoch": 0.9625902428352658, + "grad_norm": 1.230635404586792, + "learning_rate": 8.584722744201448e-06, + "loss": 1.0429, + "step": 1100 + }, + { + "epoch": 0.9713410632246773, + "grad_norm": 1.2495629787445068, + "learning_rate": 8.549018286235255e-06, + "loss": 1.0464, + "step": 1110 + }, + { + "epoch": 0.9800918836140888, + "grad_norm": 1.1702367067337036, + "learning_rate": 8.512945311567786e-06, + "loss": 1.0476, + "step": 1120 + }, + { + "epoch": 0.9888427040035004, + "grad_norm": 1.1367738246917725, + "learning_rate": 8.476507565880959e-06, + "loss": 1.0392, + "step": 1130 + }, + { + "epoch": 0.9975935243929118, + "grad_norm": 1.1903005838394165, + "learning_rate": 8.439708832733142e-06, + "loss": 1.0414, + "step": 1140 + }, + { + "epoch": 1.006125574272588, + "grad_norm": 1.310563325881958, + "learning_rate": 8.402552933166288e-06, + "loss": 0.9966, + "step": 1150 + }, + { + "epoch": 1.0148763946619996, + "grad_norm": 1.2823761701583862, + "learning_rate": 8.36504372530916e-06, + "loss": 0.9961, + "step": 1160 + }, + { + "epoch": 1.023627215051411, + "grad_norm": 1.340758204460144, + "learning_rate": 8.327185103976731e-06, + "loss": 0.9904, + "step": 1170 + }, + { + "epoch": 1.0323780354408225, + "grad_norm": 1.2751260995864868, + "learning_rate": 8.288981000265748e-06, + "loss": 1.004, + "step": 1180 + }, + { + "epoch": 1.041128855830234, + "grad_norm": 1.1516119241714478, + "learning_rate": 8.25043538114655e-06, + "loss": 0.9757, + "step": 1190 + }, + { + "epoch": 1.0498796762196456, + "grad_norm": 1.206026315689087, + "learning_rate": 8.211552249051149e-06, + "loss": 0.9799, + "step": 1200 + }, + { + "epoch": 1.0586304966090572, + "grad_norm": 1.2714760303497314, + "learning_rate": 8.17233564145764e-06, + "loss": 0.9731, + "step": 1210 + }, + { + "epoch": 1.0673813169984685, + "grad_norm": 1.2047169208526611, + "learning_rate": 8.132789630470952e-06, + "loss": 0.971, + "step": 1220 + }, + { + "epoch": 1.07613213738788, + "grad_norm": 1.282832384109497, + "learning_rate": 8.092918322400028e-06, + "loss": 0.9695, + "step": 1230 + }, + { + "epoch": 1.0848829577772916, + "grad_norm": 1.2463730573654175, + "learning_rate": 8.05272585733143e-06, + "loss": 0.9727, + "step": 1240 + }, + { + "epoch": 1.0936337781667032, + "grad_norm": 1.230220079421997, + "learning_rate": 8.012216408699456e-06, + "loss": 0.9909, + "step": 1250 + }, + { + "epoch": 1.1023845985561147, + "grad_norm": 1.3110296726226807, + "learning_rate": 7.97139418285279e-06, + "loss": 0.9887, + "step": 1260 + }, + { + "epoch": 1.1111354189455263, + "grad_norm": 1.234381914138794, + "learning_rate": 7.930263418617714e-06, + "loss": 1.0014, + "step": 1270 + }, + { + "epoch": 1.1198862393349376, + "grad_norm": 1.2342872619628906, + "learning_rate": 7.888828386857985e-06, + "loss": 0.9795, + "step": 1280 + }, + { + "epoch": 1.1286370597243491, + "grad_norm": 1.279505729675293, + "learning_rate": 7.847093390031351e-06, + "loss": 0.9647, + "step": 1290 + }, + { + "epoch": 1.1373878801137607, + "grad_norm": 1.3248056173324585, + "learning_rate": 7.8050627617428e-06, + "loss": 0.9881, + "step": 1300 + }, + { + "epoch": 1.1461387005031722, + "grad_norm": 1.234870433807373, + "learning_rate": 7.76274086629458e-06, + "loss": 0.9728, + "step": 1310 + }, + { + "epoch": 1.1548895208925836, + "grad_norm": 1.2661969661712646, + "learning_rate": 7.72013209823303e-06, + "loss": 0.9716, + "step": 1320 + }, + { + "epoch": 1.1636403412819951, + "grad_norm": 1.180408239364624, + "learning_rate": 7.677240881892259e-06, + "loss": 0.9641, + "step": 1330 + }, + { + "epoch": 1.1723911616714067, + "grad_norm": 1.2939667701721191, + "learning_rate": 7.634071670934734e-06, + "loss": 0.9832, + "step": 1340 + }, + { + "epoch": 1.1811419820608182, + "grad_norm": 1.1289607286453247, + "learning_rate": 7.5906289478888475e-06, + "loss": 0.9733, + "step": 1350 + }, + { + "epoch": 1.1898928024502298, + "grad_norm": 1.2281969785690308, + "learning_rate": 7.546917223683453e-06, + "loss": 0.9645, + "step": 1360 + }, + { + "epoch": 1.1986436228396413, + "grad_norm": 1.226364254951477, + "learning_rate": 7.502941037179474e-06, + "loss": 0.9668, + "step": 1370 + }, + { + "epoch": 1.2073944432290526, + "grad_norm": 1.2580183744430542, + "learning_rate": 7.4587049546986e-06, + "loss": 1.0167, + "step": 1380 + }, + { + "epoch": 1.2161452636184642, + "grad_norm": 1.261915683746338, + "learning_rate": 7.414213569549145e-06, + "loss": 0.9896, + "step": 1390 + }, + { + "epoch": 1.2248960840078758, + "grad_norm": 1.2158194780349731, + "learning_rate": 7.369471501549087e-06, + "loss": 0.9893, + "step": 1400 + }, + { + "epoch": 1.2336469043972873, + "grad_norm": 1.2699130773544312, + "learning_rate": 7.324483396546371e-06, + "loss": 1.0171, + "step": 1410 + }, + { + "epoch": 1.2423977247866986, + "grad_norm": 1.1923282146453857, + "learning_rate": 7.279253925936498e-06, + "loss": 0.9802, + "step": 1420 + }, + { + "epoch": 1.2511485451761102, + "grad_norm": 1.1498876810073853, + "learning_rate": 7.233787786177464e-06, + "loss": 0.9683, + "step": 1430 + }, + { + "epoch": 1.2598993655655217, + "grad_norm": 1.2153609991073608, + "learning_rate": 7.188089698302097e-06, + "loss": 0.9916, + "step": 1440 + }, + { + "epoch": 1.2686501859549333, + "grad_norm": 1.1934350728988647, + "learning_rate": 7.142164407427849e-06, + "loss": 0.9788, + "step": 1450 + }, + { + "epoch": 1.2774010063443448, + "grad_norm": 1.2987148761749268, + "learning_rate": 7.096016682264074e-06, + "loss": 0.9865, + "step": 1460 + }, + { + "epoch": 1.2861518267337564, + "grad_norm": 1.2581541538238525, + "learning_rate": 7.049651314616862e-06, + "loss": 0.9494, + "step": 1470 + }, + { + "epoch": 1.2949026471231677, + "grad_norm": 1.257711410522461, + "learning_rate": 7.003073118891487e-06, + "loss": 0.9534, + "step": 1480 + }, + { + "epoch": 1.3036534675125793, + "grad_norm": 1.3140227794647217, + "learning_rate": 6.956286931592481e-06, + "loss": 0.9888, + "step": 1490 + }, + { + "epoch": 1.3124042879019908, + "grad_norm": 1.2232003211975098, + "learning_rate": 6.909297610821444e-06, + "loss": 0.9632, + "step": 1500 + }, + { + "epoch": 1.3211551082914024, + "grad_norm": 1.190757393836975, + "learning_rate": 6.86211003577259e-06, + "loss": 0.9598, + "step": 1510 + }, + { + "epoch": 1.3299059286808137, + "grad_norm": 1.180031657218933, + "learning_rate": 6.81472910622611e-06, + "loss": 0.9804, + "step": 1520 + }, + { + "epoch": 1.3386567490702252, + "grad_norm": 1.2404285669326782, + "learning_rate": 6.7671597420394e-06, + "loss": 0.9915, + "step": 1530 + }, + { + "epoch": 1.3474075694596368, + "grad_norm": 1.2322285175323486, + "learning_rate": 6.719406882636196e-06, + "loss": 0.9908, + "step": 1540 + }, + { + "epoch": 1.3561583898490484, + "grad_norm": 1.1908921003341675, + "learning_rate": 6.671475486493691e-06, + "loss": 0.9716, + "step": 1550 + }, + { + "epoch": 1.36490921023846, + "grad_norm": 1.2217786312103271, + "learning_rate": 6.623370530627661e-06, + "loss": 0.9602, + "step": 1560 + }, + { + "epoch": 1.3736600306278715, + "grad_norm": 1.2622575759887695, + "learning_rate": 6.575097010075665e-06, + "loss": 0.9509, + "step": 1570 + }, + { + "epoch": 1.382410851017283, + "grad_norm": 1.2419332265853882, + "learning_rate": 6.526659937378392e-06, + "loss": 0.9821, + "step": 1580 + }, + { + "epoch": 1.3911616714066943, + "grad_norm": 1.3119240999221802, + "learning_rate": 6.478064342059165e-06, + "loss": 0.9823, + "step": 1590 + }, + { + "epoch": 1.3999124917961059, + "grad_norm": 1.3174080848693848, + "learning_rate": 6.429315270101702e-06, + "loss": 0.9844, + "step": 1600 + }, + { + "epoch": 1.4086633121855174, + "grad_norm": 1.2387707233428955, + "learning_rate": 6.380417783426154e-06, + "loss": 0.9545, + "step": 1610 + }, + { + "epoch": 1.4174141325749288, + "grad_norm": 1.1914652585983276, + "learning_rate": 6.331376959363501e-06, + "loss": 0.9792, + "step": 1620 + }, + { + "epoch": 1.4261649529643403, + "grad_norm": 1.2240160703659058, + "learning_rate": 6.2821978901283386e-06, + "loss": 0.9573, + "step": 1630 + }, + { + "epoch": 1.4349157733537519, + "grad_norm": 1.2401772737503052, + "learning_rate": 6.232885682290119e-06, + "loss": 0.9669, + "step": 1640 + }, + { + "epoch": 1.4436665937431634, + "grad_norm": 1.2027502059936523, + "learning_rate": 6.183445456242905e-06, + "loss": 0.9815, + "step": 1650 + }, + { + "epoch": 1.452417414132575, + "grad_norm": 1.2344744205474854, + "learning_rate": 6.13388234567369e-06, + "loss": 0.9361, + "step": 1660 + }, + { + "epoch": 1.4611682345219865, + "grad_norm": 1.2103825807571411, + "learning_rate": 6.084201497029333e-06, + "loss": 0.9744, + "step": 1670 + }, + { + "epoch": 1.469919054911398, + "grad_norm": 1.3063782453536987, + "learning_rate": 6.034408068982171e-06, + "loss": 0.9681, + "step": 1680 + }, + { + "epoch": 1.4786698753008094, + "grad_norm": 1.2130053043365479, + "learning_rate": 5.984507231894364e-06, + "loss": 0.9586, + "step": 1690 + }, + { + "epoch": 1.487420695690221, + "grad_norm": 1.2866191864013672, + "learning_rate": 5.934504167281022e-06, + "loss": 0.9681, + "step": 1700 + }, + { + "epoch": 1.4961715160796325, + "grad_norm": 1.3027279376983643, + "learning_rate": 5.884404067272175e-06, + "loss": 0.975, + "step": 1710 + }, + { + "epoch": 1.5049223364690438, + "grad_norm": 1.2601852416992188, + "learning_rate": 5.834212134073645e-06, + "loss": 0.9388, + "step": 1720 + }, + { + "epoch": 1.5136731568584554, + "grad_norm": 1.2413978576660156, + "learning_rate": 5.783933579426867e-06, + "loss": 0.9723, + "step": 1730 + }, + { + "epoch": 1.522423977247867, + "grad_norm": 1.2116490602493286, + "learning_rate": 5.733573624067717e-06, + "loss": 0.973, + "step": 1740 + }, + { + "epoch": 1.5311747976372785, + "grad_norm": 1.2060950994491577, + "learning_rate": 5.683137497184424e-06, + "loss": 0.9375, + "step": 1750 + }, + { + "epoch": 1.53992561802669, + "grad_norm": 1.2472314834594727, + "learning_rate": 5.63263043587457e-06, + "loss": 1.0112, + "step": 1760 + }, + { + "epoch": 1.5486764384161016, + "grad_norm": 1.2653073072433472, + "learning_rate": 5.582057684601308e-06, + "loss": 0.9778, + "step": 1770 + }, + { + "epoch": 1.5574272588055131, + "grad_norm": 1.2270764112472534, + "learning_rate": 5.531424494648789e-06, + "loss": 0.9807, + "step": 1780 + }, + { + "epoch": 1.5661780791949247, + "grad_norm": 1.2816975116729736, + "learning_rate": 5.480736123576886e-06, + "loss": 0.9847, + "step": 1790 + }, + { + "epoch": 1.574928899584336, + "grad_norm": 1.2429735660552979, + "learning_rate": 5.429997834675276e-06, + "loss": 0.9886, + "step": 1800 + }, + { + "epoch": 1.5836797199737476, + "grad_norm": 1.3056929111480713, + "learning_rate": 5.379214896416908e-06, + "loss": 0.9514, + "step": 1810 + }, + { + "epoch": 1.592430540363159, + "grad_norm": 1.155527949333191, + "learning_rate": 5.328392581910962e-06, + "loss": 0.9593, + "step": 1820 + }, + { + "epoch": 1.6011813607525704, + "grad_norm": 1.2867212295532227, + "learning_rate": 5.277536168355293e-06, + "loss": 0.9722, + "step": 1830 + }, + { + "epoch": 1.609932181141982, + "grad_norm": 1.3213430643081665, + "learning_rate": 5.226650936488474e-06, + "loss": 0.9588, + "step": 1840 + }, + { + "epoch": 1.6186830015313936, + "grad_norm": 1.2772150039672852, + "learning_rate": 5.1757421700414645e-06, + "loss": 0.9729, + "step": 1850 + }, + { + "epoch": 1.627433821920805, + "grad_norm": 1.2589421272277832, + "learning_rate": 5.124815155188966e-06, + "loss": 1.0171, + "step": 1860 + }, + { + "epoch": 1.6361846423102167, + "grad_norm": 1.2326509952545166, + "learning_rate": 5.073875180000523e-06, + "loss": 0.9622, + "step": 1870 + }, + { + "epoch": 1.6449354626996282, + "grad_norm": 1.1593009233474731, + "learning_rate": 5.022927533891434e-06, + "loss": 0.9584, + "step": 1880 + }, + { + "epoch": 1.6536862830890398, + "grad_norm": 1.303597331047058, + "learning_rate": 4.97197750707352e-06, + "loss": 0.9994, + "step": 1890 + }, + { + "epoch": 1.662437103478451, + "grad_norm": 1.2183244228363037, + "learning_rate": 4.9210303900058025e-06, + "loss": 0.9582, + "step": 1900 + }, + { + "epoch": 1.6711879238678626, + "grad_norm": 1.2271572351455688, + "learning_rate": 4.870091472845166e-06, + "loss": 0.9775, + "step": 1910 + }, + { + "epoch": 1.679938744257274, + "grad_norm": 1.222212791442871, + "learning_rate": 4.819166044897047e-06, + "loss": 0.9578, + "step": 1920 + }, + { + "epoch": 1.6886895646466855, + "grad_norm": 1.2827479839324951, + "learning_rate": 4.7682593940662156e-06, + "loss": 0.982, + "step": 1930 + }, + { + "epoch": 1.697440385036097, + "grad_norm": 1.2533340454101562, + "learning_rate": 4.717376806307696e-06, + "loss": 0.9735, + "step": 1940 + }, + { + "epoch": 1.7061912054255086, + "grad_norm": 1.267432451248169, + "learning_rate": 4.666523565077889e-06, + "loss": 0.9598, + "step": 1950 + }, + { + "epoch": 1.7149420258149202, + "grad_norm": 1.2450517416000366, + "learning_rate": 4.615704950785965e-06, + "loss": 0.9751, + "step": 1960 + }, + { + "epoch": 1.7236928462043317, + "grad_norm": 1.2049565315246582, + "learning_rate": 4.5649262402455705e-06, + "loss": 0.9737, + "step": 1970 + }, + { + "epoch": 1.7324436665937433, + "grad_norm": 1.2524805068969727, + "learning_rate": 4.514192706126885e-06, + "loss": 0.9662, + "step": 1980 + }, + { + "epoch": 1.7411944869831548, + "grad_norm": 1.2566184997558594, + "learning_rate": 4.463509616409144e-06, + "loss": 0.9618, + "step": 1990 + }, + { + "epoch": 1.7499453073725662, + "grad_norm": 1.176069736480713, + "learning_rate": 4.4128822338336295e-06, + "loss": 0.9521, + "step": 2000 + }, + { + "epoch": 1.7586961277619777, + "grad_norm": 1.1588139533996582, + "learning_rate": 4.362315815357197e-06, + "loss": 0.9488, + "step": 2010 + }, + { + "epoch": 1.767446948151389, + "grad_norm": 1.1984119415283203, + "learning_rate": 4.311815611606423e-06, + "loss": 0.9702, + "step": 2020 + }, + { + "epoch": 1.7761977685408006, + "grad_norm": 1.1387180089950562, + "learning_rate": 4.261386866332397e-06, + "loss": 0.9528, + "step": 2030 + }, + { + "epoch": 1.7849485889302121, + "grad_norm": 1.1617263555526733, + "learning_rate": 4.211034815866228e-06, + "loss": 0.951, + "step": 2040 + }, + { + "epoch": 1.7936994093196237, + "grad_norm": 1.1776400804519653, + "learning_rate": 4.160764688575321e-06, + "loss": 0.9634, + "step": 2050 + }, + { + "epoch": 1.8024502297090352, + "grad_norm": 1.25057852268219, + "learning_rate": 4.110581704320495e-06, + "loss": 0.9633, + "step": 2060 + }, + { + "epoch": 1.8112010500984468, + "grad_norm": 1.2121225595474243, + "learning_rate": 4.0604910739139575e-06, + "loss": 0.9749, + "step": 2070 + }, + { + "epoch": 1.8199518704878583, + "grad_norm": 1.3024873733520508, + "learning_rate": 4.0104979985782394e-06, + "loss": 0.9744, + "step": 2080 + }, + { + "epoch": 1.8287026908772699, + "grad_norm": 1.1998348236083984, + "learning_rate": 3.960607669406129e-06, + "loss": 0.9622, + "step": 2090 + }, + { + "epoch": 1.8374535112666812, + "grad_norm": 1.2691677808761597, + "learning_rate": 3.9108252668216294e-06, + "loss": 0.9702, + "step": 2100 + }, + { + "epoch": 1.8462043316560928, + "grad_norm": 1.2797294855117798, + "learning_rate": 3.861155960042057e-06, + "loss": 0.9294, + "step": 2110 + }, + { + "epoch": 1.8549551520455043, + "grad_norm": 1.2609057426452637, + "learning_rate": 3.811604906541287e-06, + "loss": 0.9624, + "step": 2120 + }, + { + "epoch": 1.8637059724349156, + "grad_norm": 1.2273874282836914, + "learning_rate": 3.762177251514218e-06, + "loss": 0.9563, + "step": 2130 + }, + { + "epoch": 1.8724567928243272, + "grad_norm": 1.225128173828125, + "learning_rate": 3.7128781273425156e-06, + "loss": 0.9587, + "step": 2140 + }, + { + "epoch": 1.8812076132137387, + "grad_norm": 1.2284705638885498, + "learning_rate": 3.6637126530616816e-06, + "loss": 0.9401, + "step": 2150 + }, + { + "epoch": 1.8899584336031503, + "grad_norm": 1.2802456617355347, + "learning_rate": 3.6146859338295248e-06, + "loss": 0.9386, + "step": 2160 + }, + { + "epoch": 1.8987092539925619, + "grad_norm": 1.22531259059906, + "learning_rate": 3.5658030603960437e-06, + "loss": 0.9652, + "step": 2170 + }, + { + "epoch": 1.9074600743819734, + "grad_norm": 1.2205225229263306, + "learning_rate": 3.5170691085748325e-06, + "loss": 0.9418, + "step": 2180 + }, + { + "epoch": 1.916210894771385, + "grad_norm": 1.1588237285614014, + "learning_rate": 3.4684891387160292e-06, + "loss": 0.9624, + "step": 2190 + }, + { + "epoch": 1.9249617151607963, + "grad_norm": 1.2422109842300415, + "learning_rate": 3.42006819518086e-06, + "loss": 0.9714, + "step": 2200 + }, + { + "epoch": 1.9337125355502078, + "grad_norm": 1.2960257530212402, + "learning_rate": 3.371811305817858e-06, + "loss": 0.9521, + "step": 2210 + }, + { + "epoch": 1.9424633559396194, + "grad_norm": 1.1022367477416992, + "learning_rate": 3.3237234814407904e-06, + "loss": 0.9775, + "step": 2220 + }, + { + "epoch": 1.9512141763290307, + "grad_norm": 1.160735011100769, + "learning_rate": 3.275809715308349e-06, + "loss": 0.9497, + "step": 2230 + }, + { + "epoch": 1.9599649967184423, + "grad_norm": 1.2306522130966187, + "learning_rate": 3.2280749826056736e-06, + "loss": 0.9544, + "step": 2240 + }, + { + "epoch": 1.9687158171078538, + "grad_norm": 1.1739164590835571, + "learning_rate": 3.180524239927749e-06, + "loss": 0.9526, + "step": 2250 + }, + { + "epoch": 1.9774666374972654, + "grad_norm": 1.2096645832061768, + "learning_rate": 3.1331624247647276e-06, + "loss": 0.9503, + "step": 2260 + }, + { + "epoch": 1.986217457886677, + "grad_norm": 1.2347972393035889, + "learning_rate": 3.085994454989232e-06, + "loss": 0.9473, + "step": 2270 + }, + { + "epoch": 1.9949682782760885, + "grad_norm": 1.28371000289917, + "learning_rate": 3.039025228345725e-06, + "loss": 0.9787, + "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..00682db3f3d43885331aaf583dce09c91255c6d1 --- /dev/null +++ b/checkpoint-3426/optimizer_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc217d8087950d9fd3494f1be8c7d71105ef0db7962bc2fbe0ffa2af67311f0a +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..5229535db9856175ad69c94fc317a34e97a27cb2 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__0_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3b54aecafadb646fe43709d0b21be2b2c95bebeedff7db139e9110a4e59286 +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..68409a4bbbf2c252081f68eb2eccfc1f1ffffbe4 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__1_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9487d7f0d45d7aa0fa387e90ef4d800019a6c9b6a85c8afccac576c3216848 +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..2d23f5bf949cca8994aa835c9276d79b30b575ff --- /dev/null +++ b/checkpoint-3426/optimizer_0/__2_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f7bdd934df86e4ed787c672d8e800952066f83c1bb81956ba58ef8edb9e9a3 +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..b5bd40cde411ffdd26ebb0d462c21b4eb6f525f3 --- /dev/null +++ b/checkpoint-3426/optimizer_0/__3_0.distcp @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544c5ca4086cf3fee147d0bd7e7aa450ddec0a2e6edc47805b9414fa803adbc9 +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..a110ffc49df5844102cd3849fb196de769645007 --- /dev/null +++ b/checkpoint-3426/pytorch_model_fsdp_0/.metadata @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb748955dc46c10f37c98e83382abe618e4e38fe2a97531a64de73bde4f2b93 +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..19f445e9671826d85e84da3a6afc5cb112c5676c --- /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 sha256:6193561445270385149bb372e15ca4a608b1a8b9f7c8fcb69585a622a7193b8d +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..b7d0d27218ba5590c70b802230625584322e3bd8 --- /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:f7f27a6999461b877a0f4fab2e274cd5b739b0602342058edede1198a9292405 +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..d20b7e47364f66663dfcd80d9e3c0a2e94e2e320 --- /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:bdca2f25501a0c69f21b417a89e61656d810066ae4fdedcb4dadd8abc6be4aab +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..1e2b2f4dca56fdabb34bd371c07a901479bada88 --- /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 sha256:55f47b3eea82387e1558781ef41b16160137853deab53c717ef6cd47dfbfddb9 +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..e3263507a5eec9a43b330a3b5001bedd310d1ca0 --- /dev/null +++ b/checkpoint-3426/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39fdabeef7466290e9470312293aadb5b1aafae0225a32b7df79e89fa94d0826 +size 1465 diff --git a/checkpoint-3426/trainer_state.json b/checkpoint-3426/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..7a84f674600af3f4d2ab334c75a2e31f08bdf5f5 --- /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": 0.8244, + "eval_samples_per_second": 24.261, + "eval_steps_per_second": 2.426, + "step": 0 + }, + { + "epoch": 0.0008750820389411508, + "grad_norm": 6.372805118560791, + "learning_rate": 2.915451895043732e-08, + "loss": 1.6434, + "step": 1 + }, + { + "epoch": 0.008750820389411508, + "grad_norm": 6.278440475463867, + "learning_rate": 2.915451895043732e-07, + "loss": 1.7188, + "step": 10 + }, + { + "epoch": 0.017501640778823015, + "grad_norm": 6.023682594299316, + "learning_rate": 5.830903790087464e-07, + "loss": 1.7154, + "step": 20 + }, + { + "epoch": 0.02625246116823452, + "grad_norm": 3.7778327465057373, + "learning_rate": 8.746355685131196e-07, + "loss": 1.6563, + "step": 30 + }, + { + "epoch": 0.03500328155764603, + "grad_norm": 3.8672306537628174, + "learning_rate": 1.1661807580174927e-06, + "loss": 1.5743, + "step": 40 + }, + { + "epoch": 0.04375410194705753, + "grad_norm": 2.53611159324646, + "learning_rate": 1.4577259475218661e-06, + "loss": 1.479, + "step": 50 + }, + { + "epoch": 0.05250492233646904, + "grad_norm": 2.019819974899292, + "learning_rate": 1.7492711370262391e-06, + "loss": 1.4242, + "step": 60 + }, + { + "epoch": 0.06125574272588055, + "grad_norm": 1.7553459405899048, + "learning_rate": 2.0408163265306125e-06, + "loss": 1.3795, + "step": 70 + }, + { + "epoch": 0.07000656311529206, + "grad_norm": 1.4397658109664917, + "learning_rate": 2.3323615160349855e-06, + "loss": 1.3745, + "step": 80 + }, + { + "epoch": 0.07875738350470357, + "grad_norm": 1.5793251991271973, + "learning_rate": 2.6239067055393585e-06, + "loss": 1.3529, + "step": 90 + }, + { + "epoch": 0.08750820389411507, + "grad_norm": 1.5069832801818848, + "learning_rate": 2.9154518950437323e-06, + "loss": 1.3459, + "step": 100 + }, + { + "epoch": 0.09625902428352658, + "grad_norm": 1.4921239614486694, + "learning_rate": 3.2069970845481052e-06, + "loss": 1.2743, + "step": 110 + }, + { + "epoch": 0.10500984467293809, + "grad_norm": 1.4761064052581787, + "learning_rate": 3.4985422740524782e-06, + "loss": 1.2959, + "step": 120 + }, + { + "epoch": 0.1137606650623496, + "grad_norm": 1.4724879264831543, + "learning_rate": 3.790087463556852e-06, + "loss": 1.2773, + "step": 130 + }, + { + "epoch": 0.1225114854517611, + "grad_norm": 1.4954681396484375, + "learning_rate": 4.081632653061225e-06, + "loss": 1.2695, + "step": 140 + }, + { + "epoch": 0.1312623058411726, + "grad_norm": 1.4220881462097168, + "learning_rate": 4.3731778425655976e-06, + "loss": 1.2668, + "step": 150 + }, + { + "epoch": 0.14001312623058412, + "grad_norm": 1.4039027690887451, + "learning_rate": 4.664723032069971e-06, + "loss": 1.2231, + "step": 160 + }, + { + "epoch": 0.14876394661999562, + "grad_norm": 1.468996524810791, + "learning_rate": 4.956268221574344e-06, + "loss": 1.221, + "step": 170 + }, + { + "epoch": 0.15751476700940714, + "grad_norm": 1.5780359506607056, + "learning_rate": 5.247813411078717e-06, + "loss": 1.2403, + "step": 180 + }, + { + "epoch": 0.16626558739881864, + "grad_norm": 1.4090375900268555, + "learning_rate": 5.539358600583091e-06, + "loss": 1.2021, + "step": 190 + }, + { + "epoch": 0.17501640778823013, + "grad_norm": 1.489652395248413, + "learning_rate": 5.8309037900874645e-06, + "loss": 1.1731, + "step": 200 + }, + { + "epoch": 0.18376722817764166, + "grad_norm": 1.3121322393417358, + "learning_rate": 6.122448979591837e-06, + "loss": 1.1924, + "step": 210 + }, + { + "epoch": 0.19251804856705315, + "grad_norm": 1.3954280614852905, + "learning_rate": 6.4139941690962105e-06, + "loss": 1.2121, + "step": 220 + }, + { + "epoch": 0.20126886895646467, + "grad_norm": 1.4191243648529053, + "learning_rate": 6.705539358600584e-06, + "loss": 1.1973, + "step": 230 + }, + { + "epoch": 0.21001968934587617, + "grad_norm": 1.4373400211334229, + "learning_rate": 6.9970845481049564e-06, + "loss": 1.1701, + "step": 240 + }, + { + "epoch": 0.2187705097352877, + "grad_norm": 1.4669713973999023, + "learning_rate": 7.28862973760933e-06, + "loss": 1.1923, + "step": 250 + }, + { + "epoch": 0.2275213301246992, + "grad_norm": 1.4269640445709229, + "learning_rate": 7.580174927113704e-06, + "loss": 1.1713, + "step": 260 + }, + { + "epoch": 0.23627215051411068, + "grad_norm": 1.7535545825958252, + "learning_rate": 7.871720116618077e-06, + "loss": 1.1891, + "step": 270 + }, + { + "epoch": 0.2450229709035222, + "grad_norm": 1.599094271659851, + "learning_rate": 8.16326530612245e-06, + "loss": 1.1827, + "step": 280 + }, + { + "epoch": 0.2537737912929337, + "grad_norm": 1.8278971910476685, + "learning_rate": 8.454810495626823e-06, + "loss": 1.1402, + "step": 290 + }, + { + "epoch": 0.2625246116823452, + "grad_norm": 1.5127216577529907, + "learning_rate": 8.746355685131195e-06, + "loss": 1.1597, + "step": 300 + }, + { + "epoch": 0.27127543207175675, + "grad_norm": 1.6015137434005737, + "learning_rate": 9.03790087463557e-06, + "loss": 1.1398, + "step": 310 + }, + { + "epoch": 0.28002625246116825, + "grad_norm": 1.3944435119628906, + "learning_rate": 9.329446064139942e-06, + "loss": 1.1174, + "step": 320 + }, + { + "epoch": 0.28877707285057974, + "grad_norm": 1.2441927194595337, + "learning_rate": 9.620991253644316e-06, + "loss": 1.1416, + "step": 330 + }, + { + "epoch": 0.29752789323999124, + "grad_norm": 1.4111624956130981, + "learning_rate": 9.912536443148689e-06, + "loss": 1.1352, + "step": 340 + }, + { + "epoch": 0.30627871362940273, + "grad_norm": 1.3007830381393433, + "learning_rate": 9.999872800049233e-06, + "loss": 1.1208, + "step": 350 + }, + { + "epoch": 0.3150295340188143, + "grad_norm": 1.3299254179000854, + "learning_rate": 9.999249795462235e-06, + "loss": 1.142, + "step": 360 + }, + { + "epoch": 0.3237803544082258, + "grad_norm": 1.2524114847183228, + "learning_rate": 9.998107687592326e-06, + "loss": 1.1147, + "step": 370 + }, + { + "epoch": 0.3325311747976373, + "grad_norm": 1.4711254835128784, + "learning_rate": 9.996446595031691e-06, + "loss": 1.1182, + "step": 380 + }, + { + "epoch": 0.34128199518704877, + "grad_norm": 1.3600913286209106, + "learning_rate": 9.994266690261928e-06, + "loss": 1.1565, + "step": 390 + }, + { + "epoch": 0.35003281557646027, + "grad_norm": 1.3752756118774414, + "learning_rate": 9.991568199636149e-06, + "loss": 1.0803, + "step": 400 + }, + { + "epoch": 0.3587836359658718, + "grad_norm": 1.2283236980438232, + "learning_rate": 9.988351403355455e-06, + "loss": 1.1371, + "step": 410 + }, + { + "epoch": 0.3675344563552833, + "grad_norm": 1.266762614250183, + "learning_rate": 9.98461663543987e-06, + "loss": 1.1027, + "step": 420 + }, + { + "epoch": 0.3762852767446948, + "grad_norm": 1.2771412134170532, + "learning_rate": 9.980364283693638e-06, + "loss": 1.0891, + "step": 430 + }, + { + "epoch": 0.3850360971341063, + "grad_norm": 1.2226617336273193, + "learning_rate": 9.97559478966496e-06, + "loss": 1.1105, + "step": 440 + }, + { + "epoch": 0.39378691752351785, + "grad_norm": 1.2738267183303833, + "learning_rate": 9.970308648600142e-06, + "loss": 1.114, + "step": 450 + }, + { + "epoch": 0.40253773791292935, + "grad_norm": 1.3344817161560059, + "learning_rate": 9.964506409392178e-06, + "loss": 1.1178, + "step": 460 + }, + { + "epoch": 0.41128855830234085, + "grad_norm": 1.3076369762420654, + "learning_rate": 9.958188674523748e-06, + "loss": 1.1205, + "step": 470 + }, + { + "epoch": 0.42003937869175234, + "grad_norm": 1.251315712928772, + "learning_rate": 9.951356100004666e-06, + "loss": 1.0795, + "step": 480 + }, + { + "epoch": 0.42879019908116384, + "grad_norm": 1.1784945726394653, + "learning_rate": 9.94400939530375e-06, + "loss": 1.1175, + "step": 490 + }, + { + "epoch": 0.4375410194705754, + "grad_norm": 1.219256043434143, + "learning_rate": 9.93614932327517e-06, + "loss": 1.0933, + "step": 500 + }, + { + "epoch": 0.4462918398599869, + "grad_norm": 1.398763656616211, + "learning_rate": 9.927776700079217e-06, + "loss": 1.1267, + "step": 510 + }, + { + "epoch": 0.4550426602493984, + "grad_norm": 1.25184166431427, + "learning_rate": 9.918892395097572e-06, + "loss": 1.1191, + "step": 520 + }, + { + "epoch": 0.4637934806388099, + "grad_norm": 1.3422456979751587, + "learning_rate": 9.90949733084303e-06, + "loss": 1.1003, + "step": 530 + }, + { + "epoch": 0.47254430102822137, + "grad_norm": 1.3312543630599976, + "learning_rate": 9.8995924828637e-06, + "loss": 1.1004, + "step": 540 + }, + { + "epoch": 0.4812951214176329, + "grad_norm": 1.2708804607391357, + "learning_rate": 9.889178879641717e-06, + "loss": 1.1094, + "step": 550 + }, + { + "epoch": 0.4900459418070444, + "grad_norm": 1.3565181493759155, + "learning_rate": 9.878257602486445e-06, + "loss": 1.1252, + "step": 560 + }, + { + "epoch": 0.4987967621964559, + "grad_norm": 1.232021450996399, + "learning_rate": 9.866829785422201e-06, + "loss": 1.0976, + "step": 570 + }, + { + "epoch": 0.5075475825858674, + "grad_norm": 1.371229887008667, + "learning_rate": 9.854896615070495e-06, + "loss": 1.0941, + "step": 580 + }, + { + "epoch": 0.516298402975279, + "grad_norm": 1.35117769241333, + "learning_rate": 9.842459330526826e-06, + "loss": 1.1127, + "step": 590 + }, + { + "epoch": 0.5250492233646904, + "grad_norm": 1.234413504600525, + "learning_rate": 9.829519223232006e-06, + "loss": 1.09, + "step": 600 + }, + { + "epoch": 0.533800043754102, + "grad_norm": 1.2576864957809448, + "learning_rate": 9.816077636838079e-06, + "loss": 1.1094, + "step": 610 + }, + { + "epoch": 0.5425508641435135, + "grad_norm": 1.340950608253479, + "learning_rate": 9.802135967068783e-06, + "loss": 1.0889, + "step": 620 + }, + { + "epoch": 0.5513016845329249, + "grad_norm": 1.350095272064209, + "learning_rate": 9.787695661574632e-06, + "loss": 1.0661, + "step": 630 + }, + { + "epoch": 0.5600525049223365, + "grad_norm": 1.2629624605178833, + "learning_rate": 9.772758219782601e-06, + "loss": 1.0823, + "step": 640 + }, + { + "epoch": 0.5688033253117479, + "grad_norm": 1.234574556350708, + "learning_rate": 9.757325192740425e-06, + "loss": 1.0937, + "step": 650 + }, + { + "epoch": 0.5775541457011595, + "grad_norm": 1.1775031089782715, + "learning_rate": 9.741398182955548e-06, + "loss": 1.1066, + "step": 660 + }, + { + "epoch": 0.586304966090571, + "grad_norm": 1.2653073072433472, + "learning_rate": 9.724978844228717e-06, + "loss": 1.0964, + "step": 670 + }, + { + "epoch": 0.5950557864799825, + "grad_norm": 1.2665278911590576, + "learning_rate": 9.70806888148227e-06, + "loss": 1.1007, + "step": 680 + }, + { + "epoch": 0.603806606869394, + "grad_norm": 1.2909613847732544, + "learning_rate": 9.690670050583095e-06, + "loss": 1.0973, + "step": 690 + }, + { + "epoch": 0.6125574272588055, + "grad_norm": 1.2396572828292847, + "learning_rate": 9.672784158160307e-06, + "loss": 1.0423, + "step": 700 + }, + { + "epoch": 0.621308247648217, + "grad_norm": 1.2569255828857422, + "learning_rate": 9.654413061417655e-06, + "loss": 1.0764, + "step": 710 + }, + { + "epoch": 0.6300590680376286, + "grad_norm": 1.3747756481170654, + "learning_rate": 9.635558667940683e-06, + "loss": 1.0563, + "step": 720 + }, + { + "epoch": 0.63880988842704, + "grad_norm": 1.2752923965454102, + "learning_rate": 9.616222935498647e-06, + "loss": 1.1084, + "step": 730 + }, + { + "epoch": 0.6475607088164516, + "grad_norm": 1.218320369720459, + "learning_rate": 9.596407871841229e-06, + "loss": 1.0674, + "step": 740 + }, + { + "epoch": 0.656311529205863, + "grad_norm": 1.2466013431549072, + "learning_rate": 9.57611553449006e-06, + "loss": 1.1048, + "step": 750 + }, + { + "epoch": 0.6650623495952745, + "grad_norm": 1.2956342697143555, + "learning_rate": 9.555348030525076e-06, + "loss": 1.0723, + "step": 760 + }, + { + "epoch": 0.6738131699846861, + "grad_norm": 1.29911208152771, + "learning_rate": 9.534107516365725e-06, + "loss": 1.0743, + "step": 770 + }, + { + "epoch": 0.6825639903740975, + "grad_norm": 1.2063359022140503, + "learning_rate": 9.512396197547053e-06, + "loss": 1.0717, + "step": 780 + }, + { + "epoch": 0.6913148107635091, + "grad_norm": 1.184462547302246, + "learning_rate": 9.490216328490693e-06, + "loss": 1.0895, + "step": 790 + }, + { + "epoch": 0.7000656311529205, + "grad_norm": 1.186874270439148, + "learning_rate": 9.467570212270767e-06, + "loss": 1.1476, + "step": 800 + }, + { + "epoch": 0.7088164515423321, + "grad_norm": 1.2901315689086914, + "learning_rate": 9.444460200374747e-06, + "loss": 1.0538, + "step": 810 + }, + { + "epoch": 0.7175672719317436, + "grad_norm": 1.2175313234329224, + "learning_rate": 9.42088869245929e-06, + "loss": 1.079, + "step": 820 + }, + { + "epoch": 0.7263180923211551, + "grad_norm": 1.1771786212921143, + "learning_rate": 9.396858136101066e-06, + "loss": 1.0756, + "step": 830 + }, + { + "epoch": 0.7350689127105666, + "grad_norm": 1.2814205884933472, + "learning_rate": 9.372371026542595e-06, + "loss": 1.0697, + "step": 840 + }, + { + "epoch": 0.7438197330999782, + "grad_norm": 1.2603764533996582, + "learning_rate": 9.347429906433175e-06, + "loss": 1.1079, + "step": 850 + }, + { + "epoch": 0.7525705534893896, + "grad_norm": 1.2228299379348755, + "learning_rate": 9.322037365564844e-06, + "loss": 1.0746, + "step": 860 + }, + { + "epoch": 0.7613213738788012, + "grad_norm": 1.1895763874053955, + "learning_rate": 9.296196040603476e-06, + "loss": 1.0831, + "step": 870 + }, + { + "epoch": 0.7700721942682126, + "grad_norm": 1.2288453578948975, + "learning_rate": 9.269908614814995e-06, + "loss": 1.0649, + "step": 880 + }, + { + "epoch": 0.7788230146576242, + "grad_norm": 1.1580345630645752, + "learning_rate": 9.243177817786757e-06, + "loss": 1.1053, + "step": 890 + }, + { + "epoch": 0.7875738350470357, + "grad_norm": 1.1613861322402954, + "learning_rate": 9.216006425144118e-06, + "loss": 1.0854, + "step": 900 + }, + { + "epoch": 0.7963246554364471, + "grad_norm": 1.0809310674667358, + "learning_rate": 9.188397258262221e-06, + "loss": 1.059, + "step": 910 + }, + { + "epoch": 0.8050754758258587, + "grad_norm": 1.2021125555038452, + "learning_rate": 9.160353183973045e-06, + "loss": 1.064, + "step": 920 + }, + { + "epoch": 0.8138262962152701, + "grad_norm": 1.286584496498108, + "learning_rate": 9.131877114267711e-06, + "loss": 1.0516, + "step": 930 + }, + { + "epoch": 0.8225771166046817, + "grad_norm": 1.177673578262329, + "learning_rate": 9.102972005994123e-06, + "loss": 1.0358, + "step": 940 + }, + { + "epoch": 0.8313279369940932, + "grad_norm": 1.2117091417312622, + "learning_rate": 9.073640860549931e-06, + "loss": 1.0701, + "step": 950 + }, + { + "epoch": 0.8400787573835047, + "grad_norm": 1.2018595933914185, + "learning_rate": 9.043886723570885e-06, + "loss": 1.0833, + "step": 960 + }, + { + "epoch": 0.8488295777729162, + "grad_norm": 1.1337984800338745, + "learning_rate": 9.013712684614582e-06, + "loss": 1.0785, + "step": 970 + }, + { + "epoch": 0.8575803981623277, + "grad_norm": 1.2217832803726196, + "learning_rate": 8.983121876839658e-06, + "loss": 1.0623, + "step": 980 + }, + { + "epoch": 0.8663312185517392, + "grad_norm": 1.2249287366867065, + "learning_rate": 8.95211747668046e-06, + "loss": 1.0285, + "step": 990 + }, + { + "epoch": 0.8750820389411508, + "grad_norm": 1.1673548221588135, + "learning_rate": 8.920702703517205e-06, + "loss": 1.0354, + "step": 1000 + }, + { + "epoch": 0.8838328593305622, + "grad_norm": 1.1298819780349731, + "learning_rate": 8.888880819341703e-06, + "loss": 1.0538, + "step": 1010 + }, + { + "epoch": 0.8925836797199738, + "grad_norm": 1.1600337028503418, + "learning_rate": 8.856655128418638e-06, + "loss": 1.0527, + "step": 1020 + }, + { + "epoch": 0.9013345001093852, + "grad_norm": 1.2292169332504272, + "learning_rate": 8.824028976942465e-06, + "loss": 1.0613, + "step": 1030 + }, + { + "epoch": 0.9100853204987968, + "grad_norm": 1.1878681182861328, + "learning_rate": 8.791005752689958e-06, + "loss": 1.0489, + "step": 1040 + }, + { + "epoch": 0.9188361408882083, + "grad_norm": 1.2165477275848389, + "learning_rate": 8.757588884668435e-06, + "loss": 1.0675, + "step": 1050 + }, + { + "epoch": 0.9275869612776197, + "grad_norm": 1.1682305335998535, + "learning_rate": 8.723781842759696e-06, + "loss": 1.084, + "step": 1060 + }, + { + "epoch": 0.9363377816670313, + "grad_norm": 1.3387882709503174, + "learning_rate": 8.689588137359731e-06, + "loss": 1.0564, + "step": 1070 + }, + { + "epoch": 0.9450886020564427, + "grad_norm": 1.2144585847854614, + "learning_rate": 8.655011319014217e-06, + "loss": 1.08, + "step": 1080 + }, + { + "epoch": 0.9538394224458543, + "grad_norm": 1.2637611627578735, + "learning_rate": 8.620054978049828e-06, + "loss": 1.0716, + "step": 1090 + }, + { + "epoch": 0.9625902428352658, + "grad_norm": 1.230635404586792, + "learning_rate": 8.584722744201448e-06, + "loss": 1.0429, + "step": 1100 + }, + { + "epoch": 0.9713410632246773, + "grad_norm": 1.2495629787445068, + "learning_rate": 8.549018286235255e-06, + "loss": 1.0464, + "step": 1110 + }, + { + "epoch": 0.9800918836140888, + "grad_norm": 1.1702367067337036, + "learning_rate": 8.512945311567786e-06, + "loss": 1.0476, + "step": 1120 + }, + { + "epoch": 0.9888427040035004, + "grad_norm": 1.1367738246917725, + "learning_rate": 8.476507565880959e-06, + "loss": 1.0392, + "step": 1130 + }, + { + "epoch": 0.9975935243929118, + "grad_norm": 1.1903005838394165, + "learning_rate": 8.439708832733142e-06, + "loss": 1.0414, + "step": 1140 + }, + { + "epoch": 1.006125574272588, + "grad_norm": 1.310563325881958, + "learning_rate": 8.402552933166288e-06, + "loss": 0.9966, + "step": 1150 + }, + { + "epoch": 1.0148763946619996, + "grad_norm": 1.2823761701583862, + "learning_rate": 8.36504372530916e-06, + "loss": 0.9961, + "step": 1160 + }, + { + "epoch": 1.023627215051411, + "grad_norm": 1.340758204460144, + "learning_rate": 8.327185103976731e-06, + "loss": 0.9904, + "step": 1170 + }, + { + "epoch": 1.0323780354408225, + "grad_norm": 1.2751260995864868, + "learning_rate": 8.288981000265748e-06, + "loss": 1.004, + "step": 1180 + }, + { + "epoch": 1.041128855830234, + "grad_norm": 1.1516119241714478, + "learning_rate": 8.25043538114655e-06, + "loss": 0.9757, + "step": 1190 + }, + { + "epoch": 1.0498796762196456, + "grad_norm": 1.206026315689087, + "learning_rate": 8.211552249051149e-06, + "loss": 0.9799, + "step": 1200 + }, + { + "epoch": 1.0586304966090572, + "grad_norm": 1.2714760303497314, + "learning_rate": 8.17233564145764e-06, + "loss": 0.9731, + "step": 1210 + }, + { + "epoch": 1.0673813169984685, + "grad_norm": 1.2047169208526611, + "learning_rate": 8.132789630470952e-06, + "loss": 0.971, + "step": 1220 + }, + { + "epoch": 1.07613213738788, + "grad_norm": 1.282832384109497, + "learning_rate": 8.092918322400028e-06, + "loss": 0.9695, + "step": 1230 + }, + { + "epoch": 1.0848829577772916, + "grad_norm": 1.2463730573654175, + "learning_rate": 8.05272585733143e-06, + "loss": 0.9727, + "step": 1240 + }, + { + "epoch": 1.0936337781667032, + "grad_norm": 1.230220079421997, + "learning_rate": 8.012216408699456e-06, + "loss": 0.9909, + "step": 1250 + }, + { + "epoch": 1.1023845985561147, + "grad_norm": 1.3110296726226807, + "learning_rate": 7.97139418285279e-06, + "loss": 0.9887, + "step": 1260 + }, + { + "epoch": 1.1111354189455263, + "grad_norm": 1.234381914138794, + "learning_rate": 7.930263418617714e-06, + "loss": 1.0014, + "step": 1270 + }, + { + "epoch": 1.1198862393349376, + "grad_norm": 1.2342872619628906, + "learning_rate": 7.888828386857985e-06, + "loss": 0.9795, + "step": 1280 + }, + { + "epoch": 1.1286370597243491, + "grad_norm": 1.279505729675293, + "learning_rate": 7.847093390031351e-06, + "loss": 0.9647, + "step": 1290 + }, + { + "epoch": 1.1373878801137607, + "grad_norm": 1.3248056173324585, + "learning_rate": 7.8050627617428e-06, + "loss": 0.9881, + "step": 1300 + }, + { + "epoch": 1.1461387005031722, + "grad_norm": 1.234870433807373, + "learning_rate": 7.76274086629458e-06, + "loss": 0.9728, + "step": 1310 + }, + { + "epoch": 1.1548895208925836, + "grad_norm": 1.2661969661712646, + "learning_rate": 7.72013209823303e-06, + "loss": 0.9716, + "step": 1320 + }, + { + "epoch": 1.1636403412819951, + "grad_norm": 1.180408239364624, + "learning_rate": 7.677240881892259e-06, + "loss": 0.9641, + "step": 1330 + }, + { + "epoch": 1.1723911616714067, + "grad_norm": 1.2939667701721191, + "learning_rate": 7.634071670934734e-06, + "loss": 0.9832, + "step": 1340 + }, + { + "epoch": 1.1811419820608182, + "grad_norm": 1.1289607286453247, + "learning_rate": 7.5906289478888475e-06, + "loss": 0.9733, + "step": 1350 + }, + { + "epoch": 1.1898928024502298, + "grad_norm": 1.2281969785690308, + "learning_rate": 7.546917223683453e-06, + "loss": 0.9645, + "step": 1360 + }, + { + "epoch": 1.1986436228396413, + "grad_norm": 1.226364254951477, + "learning_rate": 7.502941037179474e-06, + "loss": 0.9668, + "step": 1370 + }, + { + "epoch": 1.2073944432290526, + "grad_norm": 1.2580183744430542, + "learning_rate": 7.4587049546986e-06, + "loss": 1.0167, + "step": 1380 + }, + { + "epoch": 1.2161452636184642, + "grad_norm": 1.261915683746338, + "learning_rate": 7.414213569549145e-06, + "loss": 0.9896, + "step": 1390 + }, + { + "epoch": 1.2248960840078758, + "grad_norm": 1.2158194780349731, + "learning_rate": 7.369471501549087e-06, + "loss": 0.9893, + "step": 1400 + }, + { + "epoch": 1.2336469043972873, + "grad_norm": 1.2699130773544312, + "learning_rate": 7.324483396546371e-06, + "loss": 1.0171, + "step": 1410 + }, + { + "epoch": 1.2423977247866986, + "grad_norm": 1.1923282146453857, + "learning_rate": 7.279253925936498e-06, + "loss": 0.9802, + "step": 1420 + }, + { + "epoch": 1.2511485451761102, + "grad_norm": 1.1498876810073853, + "learning_rate": 7.233787786177464e-06, + "loss": 0.9683, + "step": 1430 + }, + { + "epoch": 1.2598993655655217, + "grad_norm": 1.2153609991073608, + "learning_rate": 7.188089698302097e-06, + "loss": 0.9916, + "step": 1440 + }, + { + "epoch": 1.2686501859549333, + "grad_norm": 1.1934350728988647, + "learning_rate": 7.142164407427849e-06, + "loss": 0.9788, + "step": 1450 + }, + { + "epoch": 1.2774010063443448, + "grad_norm": 1.2987148761749268, + "learning_rate": 7.096016682264074e-06, + "loss": 0.9865, + "step": 1460 + }, + { + "epoch": 1.2861518267337564, + "grad_norm": 1.2581541538238525, + "learning_rate": 7.049651314616862e-06, + "loss": 0.9494, + "step": 1470 + }, + { + "epoch": 1.2949026471231677, + "grad_norm": 1.257711410522461, + "learning_rate": 7.003073118891487e-06, + "loss": 0.9534, + "step": 1480 + }, + { + "epoch": 1.3036534675125793, + "grad_norm": 1.3140227794647217, + "learning_rate": 6.956286931592481e-06, + "loss": 0.9888, + "step": 1490 + }, + { + "epoch": 1.3124042879019908, + "grad_norm": 1.2232003211975098, + "learning_rate": 6.909297610821444e-06, + "loss": 0.9632, + "step": 1500 + }, + { + "epoch": 1.3211551082914024, + "grad_norm": 1.190757393836975, + "learning_rate": 6.86211003577259e-06, + "loss": 0.9598, + "step": 1510 + }, + { + "epoch": 1.3299059286808137, + "grad_norm": 1.180031657218933, + "learning_rate": 6.81472910622611e-06, + "loss": 0.9804, + "step": 1520 + }, + { + "epoch": 1.3386567490702252, + "grad_norm": 1.2404285669326782, + "learning_rate": 6.7671597420394e-06, + "loss": 0.9915, + "step": 1530 + }, + { + "epoch": 1.3474075694596368, + "grad_norm": 1.2322285175323486, + "learning_rate": 6.719406882636196e-06, + "loss": 0.9908, + "step": 1540 + }, + { + "epoch": 1.3561583898490484, + "grad_norm": 1.1908921003341675, + "learning_rate": 6.671475486493691e-06, + "loss": 0.9716, + "step": 1550 + }, + { + "epoch": 1.36490921023846, + "grad_norm": 1.2217786312103271, + "learning_rate": 6.623370530627661e-06, + "loss": 0.9602, + "step": 1560 + }, + { + "epoch": 1.3736600306278715, + "grad_norm": 1.2622575759887695, + "learning_rate": 6.575097010075665e-06, + "loss": 0.9509, + "step": 1570 + }, + { + "epoch": 1.382410851017283, + "grad_norm": 1.2419332265853882, + "learning_rate": 6.526659937378392e-06, + "loss": 0.9821, + "step": 1580 + }, + { + "epoch": 1.3911616714066943, + "grad_norm": 1.3119240999221802, + "learning_rate": 6.478064342059165e-06, + "loss": 0.9823, + "step": 1590 + }, + { + "epoch": 1.3999124917961059, + "grad_norm": 1.3174080848693848, + "learning_rate": 6.429315270101702e-06, + "loss": 0.9844, + "step": 1600 + }, + { + "epoch": 1.4086633121855174, + "grad_norm": 1.2387707233428955, + "learning_rate": 6.380417783426154e-06, + "loss": 0.9545, + "step": 1610 + }, + { + "epoch": 1.4174141325749288, + "grad_norm": 1.1914652585983276, + "learning_rate": 6.331376959363501e-06, + "loss": 0.9792, + "step": 1620 + }, + { + "epoch": 1.4261649529643403, + "grad_norm": 1.2240160703659058, + "learning_rate": 6.2821978901283386e-06, + "loss": 0.9573, + "step": 1630 + }, + { + "epoch": 1.4349157733537519, + "grad_norm": 1.2401772737503052, + "learning_rate": 6.232885682290119e-06, + "loss": 0.9669, + "step": 1640 + }, + { + "epoch": 1.4436665937431634, + "grad_norm": 1.2027502059936523, + "learning_rate": 6.183445456242905e-06, + "loss": 0.9815, + "step": 1650 + }, + { + "epoch": 1.452417414132575, + "grad_norm": 1.2344744205474854, + "learning_rate": 6.13388234567369e-06, + "loss": 0.9361, + "step": 1660 + }, + { + "epoch": 1.4611682345219865, + "grad_norm": 1.2103825807571411, + "learning_rate": 6.084201497029333e-06, + "loss": 0.9744, + "step": 1670 + }, + { + "epoch": 1.469919054911398, + "grad_norm": 1.3063782453536987, + "learning_rate": 6.034408068982171e-06, + "loss": 0.9681, + "step": 1680 + }, + { + "epoch": 1.4786698753008094, + "grad_norm": 1.2130053043365479, + "learning_rate": 5.984507231894364e-06, + "loss": 0.9586, + "step": 1690 + }, + { + "epoch": 1.487420695690221, + "grad_norm": 1.2866191864013672, + "learning_rate": 5.934504167281022e-06, + "loss": 0.9681, + "step": 1700 + }, + { + "epoch": 1.4961715160796325, + "grad_norm": 1.3027279376983643, + "learning_rate": 5.884404067272175e-06, + "loss": 0.975, + "step": 1710 + }, + { + "epoch": 1.5049223364690438, + "grad_norm": 1.2601852416992188, + "learning_rate": 5.834212134073645e-06, + "loss": 0.9388, + "step": 1720 + }, + { + "epoch": 1.5136731568584554, + "grad_norm": 1.2413978576660156, + "learning_rate": 5.783933579426867e-06, + "loss": 0.9723, + "step": 1730 + }, + { + "epoch": 1.522423977247867, + "grad_norm": 1.2116490602493286, + "learning_rate": 5.733573624067717e-06, + "loss": 0.973, + "step": 1740 + }, + { + "epoch": 1.5311747976372785, + "grad_norm": 1.2060950994491577, + "learning_rate": 5.683137497184424e-06, + "loss": 0.9375, + "step": 1750 + }, + { + "epoch": 1.53992561802669, + "grad_norm": 1.2472314834594727, + "learning_rate": 5.63263043587457e-06, + "loss": 1.0112, + "step": 1760 + }, + { + "epoch": 1.5486764384161016, + "grad_norm": 1.2653073072433472, + "learning_rate": 5.582057684601308e-06, + "loss": 0.9778, + "step": 1770 + }, + { + "epoch": 1.5574272588055131, + "grad_norm": 1.2270764112472534, + "learning_rate": 5.531424494648789e-06, + "loss": 0.9807, + "step": 1780 + }, + { + "epoch": 1.5661780791949247, + "grad_norm": 1.2816975116729736, + "learning_rate": 5.480736123576886e-06, + "loss": 0.9847, + "step": 1790 + }, + { + "epoch": 1.574928899584336, + "grad_norm": 1.2429735660552979, + "learning_rate": 5.429997834675276e-06, + "loss": 0.9886, + "step": 1800 + }, + { + "epoch": 1.5836797199737476, + "grad_norm": 1.3056929111480713, + "learning_rate": 5.379214896416908e-06, + "loss": 0.9514, + "step": 1810 + }, + { + "epoch": 1.592430540363159, + "grad_norm": 1.155527949333191, + "learning_rate": 5.328392581910962e-06, + "loss": 0.9593, + "step": 1820 + }, + { + "epoch": 1.6011813607525704, + "grad_norm": 1.2867212295532227, + "learning_rate": 5.277536168355293e-06, + "loss": 0.9722, + "step": 1830 + }, + { + "epoch": 1.609932181141982, + "grad_norm": 1.3213430643081665, + "learning_rate": 5.226650936488474e-06, + "loss": 0.9588, + "step": 1840 + }, + { + "epoch": 1.6186830015313936, + "grad_norm": 1.2772150039672852, + "learning_rate": 5.1757421700414645e-06, + "loss": 0.9729, + "step": 1850 + }, + { + "epoch": 1.627433821920805, + "grad_norm": 1.2589421272277832, + "learning_rate": 5.124815155188966e-06, + "loss": 1.0171, + "step": 1860 + }, + { + "epoch": 1.6361846423102167, + "grad_norm": 1.2326509952545166, + "learning_rate": 5.073875180000523e-06, + "loss": 0.9622, + "step": 1870 + }, + { + "epoch": 1.6449354626996282, + "grad_norm": 1.1593009233474731, + "learning_rate": 5.022927533891434e-06, + "loss": 0.9584, + "step": 1880 + }, + { + "epoch": 1.6536862830890398, + "grad_norm": 1.303597331047058, + "learning_rate": 4.97197750707352e-06, + "loss": 0.9994, + "step": 1890 + }, + { + "epoch": 1.662437103478451, + "grad_norm": 1.2183244228363037, + "learning_rate": 4.9210303900058025e-06, + "loss": 0.9582, + "step": 1900 + }, + { + "epoch": 1.6711879238678626, + "grad_norm": 1.2271572351455688, + "learning_rate": 4.870091472845166e-06, + "loss": 0.9775, + "step": 1910 + }, + { + "epoch": 1.679938744257274, + "grad_norm": 1.222212791442871, + "learning_rate": 4.819166044897047e-06, + "loss": 0.9578, + "step": 1920 + }, + { + "epoch": 1.6886895646466855, + "grad_norm": 1.2827479839324951, + "learning_rate": 4.7682593940662156e-06, + "loss": 0.982, + "step": 1930 + }, + { + "epoch": 1.697440385036097, + "grad_norm": 1.2533340454101562, + "learning_rate": 4.717376806307696e-06, + "loss": 0.9735, + "step": 1940 + }, + { + "epoch": 1.7061912054255086, + "grad_norm": 1.267432451248169, + "learning_rate": 4.666523565077889e-06, + "loss": 0.9598, + "step": 1950 + }, + { + "epoch": 1.7149420258149202, + "grad_norm": 1.2450517416000366, + "learning_rate": 4.615704950785965e-06, + "loss": 0.9751, + "step": 1960 + }, + { + "epoch": 1.7236928462043317, + "grad_norm": 1.2049565315246582, + "learning_rate": 4.5649262402455705e-06, + "loss": 0.9737, + "step": 1970 + }, + { + "epoch": 1.7324436665937433, + "grad_norm": 1.2524805068969727, + "learning_rate": 4.514192706126885e-06, + "loss": 0.9662, + "step": 1980 + }, + { + "epoch": 1.7411944869831548, + "grad_norm": 1.2566184997558594, + "learning_rate": 4.463509616409144e-06, + "loss": 0.9618, + "step": 1990 + }, + { + "epoch": 1.7499453073725662, + "grad_norm": 1.176069736480713, + "learning_rate": 4.4128822338336295e-06, + "loss": 0.9521, + "step": 2000 + }, + { + "epoch": 1.7586961277619777, + "grad_norm": 1.1588139533996582, + "learning_rate": 4.362315815357197e-06, + "loss": 0.9488, + "step": 2010 + }, + { + "epoch": 1.767446948151389, + "grad_norm": 1.1984119415283203, + "learning_rate": 4.311815611606423e-06, + "loss": 0.9702, + "step": 2020 + }, + { + "epoch": 1.7761977685408006, + "grad_norm": 1.1387180089950562, + "learning_rate": 4.261386866332397e-06, + "loss": 0.9528, + "step": 2030 + }, + { + "epoch": 1.7849485889302121, + "grad_norm": 1.1617263555526733, + "learning_rate": 4.211034815866228e-06, + "loss": 0.951, + "step": 2040 + }, + { + "epoch": 1.7936994093196237, + "grad_norm": 1.1776400804519653, + "learning_rate": 4.160764688575321e-06, + "loss": 0.9634, + "step": 2050 + }, + { + "epoch": 1.8024502297090352, + "grad_norm": 1.25057852268219, + "learning_rate": 4.110581704320495e-06, + "loss": 0.9633, + "step": 2060 + }, + { + "epoch": 1.8112010500984468, + "grad_norm": 1.2121225595474243, + "learning_rate": 4.0604910739139575e-06, + "loss": 0.9749, + "step": 2070 + }, + { + "epoch": 1.8199518704878583, + "grad_norm": 1.3024873733520508, + "learning_rate": 4.0104979985782394e-06, + "loss": 0.9744, + "step": 2080 + }, + { + "epoch": 1.8287026908772699, + "grad_norm": 1.1998348236083984, + "learning_rate": 3.960607669406129e-06, + "loss": 0.9622, + "step": 2090 + }, + { + "epoch": 1.8374535112666812, + "grad_norm": 1.2691677808761597, + "learning_rate": 3.9108252668216294e-06, + "loss": 0.9702, + "step": 2100 + }, + { + "epoch": 1.8462043316560928, + "grad_norm": 1.2797294855117798, + "learning_rate": 3.861155960042057e-06, + "loss": 0.9294, + "step": 2110 + }, + { + "epoch": 1.8549551520455043, + "grad_norm": 1.2609057426452637, + "learning_rate": 3.811604906541287e-06, + "loss": 0.9624, + "step": 2120 + }, + { + "epoch": 1.8637059724349156, + "grad_norm": 1.2273874282836914, + "learning_rate": 3.762177251514218e-06, + "loss": 0.9563, + "step": 2130 + }, + { + "epoch": 1.8724567928243272, + "grad_norm": 1.225128173828125, + "learning_rate": 3.7128781273425156e-06, + "loss": 0.9587, + "step": 2140 + }, + { + "epoch": 1.8812076132137387, + "grad_norm": 1.2284705638885498, + "learning_rate": 3.6637126530616816e-06, + "loss": 0.9401, + "step": 2150 + }, + { + "epoch": 1.8899584336031503, + "grad_norm": 1.2802456617355347, + "learning_rate": 3.6146859338295248e-06, + "loss": 0.9386, + "step": 2160 + }, + { + "epoch": 1.8987092539925619, + "grad_norm": 1.22531259059906, + "learning_rate": 3.5658030603960437e-06, + "loss": 0.9652, + "step": 2170 + }, + { + "epoch": 1.9074600743819734, + "grad_norm": 1.2205225229263306, + "learning_rate": 3.5170691085748325e-06, + "loss": 0.9418, + "step": 2180 + }, + { + "epoch": 1.916210894771385, + "grad_norm": 1.1588237285614014, + "learning_rate": 3.4684891387160292e-06, + "loss": 0.9624, + "step": 2190 + }, + { + "epoch": 1.9249617151607963, + "grad_norm": 1.2422109842300415, + "learning_rate": 3.42006819518086e-06, + "loss": 0.9714, + "step": 2200 + }, + { + "epoch": 1.9337125355502078, + "grad_norm": 1.2960257530212402, + "learning_rate": 3.371811305817858e-06, + "loss": 0.9521, + "step": 2210 + }, + { + "epoch": 1.9424633559396194, + "grad_norm": 1.1022367477416992, + "learning_rate": 3.3237234814407904e-06, + "loss": 0.9775, + "step": 2220 + }, + { + "epoch": 1.9512141763290307, + "grad_norm": 1.160735011100769, + "learning_rate": 3.275809715308349e-06, + "loss": 0.9497, + "step": 2230 + }, + { + "epoch": 1.9599649967184423, + "grad_norm": 1.2306522130966187, + "learning_rate": 3.2280749826056736e-06, + "loss": 0.9544, + "step": 2240 + }, + { + "epoch": 1.9687158171078538, + "grad_norm": 1.1739164590835571, + "learning_rate": 3.180524239927749e-06, + "loss": 0.9526, + "step": 2250 + }, + { + "epoch": 1.9774666374972654, + "grad_norm": 1.2096645832061768, + "learning_rate": 3.1331624247647276e-06, + "loss": 0.9503, + "step": 2260 + }, + { + "epoch": 1.986217457886677, + "grad_norm": 1.2347972393035889, + "learning_rate": 3.085994454989232e-06, + "loss": 0.9473, + "step": 2270 + }, + { + "epoch": 1.9949682782760885, + "grad_norm": 1.28371000289917, + "learning_rate": 3.039025228345725e-06, + "loss": 0.9787, + "step": 2280 + }, + { + "epoch": 2.0035003281557646, + "grad_norm": 1.1137796640396118, + "learning_rate": 2.992259621941916e-06, + "loss": 0.9234, + "step": 2290 + }, + { + "epoch": 2.012251148545176, + "grad_norm": 1.3428007364273071, + "learning_rate": 2.9457024917423594e-06, + "loss": 0.8978, + "step": 2300 + }, + { + "epoch": 2.0210019689345877, + "grad_norm": 1.2651664018630981, + "learning_rate": 2.8993586720642307e-06, + "loss": 0.8992, + "step": 2310 + }, + { + "epoch": 2.0297527893239993, + "grad_norm": 1.1616652011871338, + "learning_rate": 2.85323297507534e-06, + "loss": 0.8695, + "step": 2320 + }, + { + "epoch": 2.038503609713411, + "grad_norm": 1.2452731132507324, + "learning_rate": 2.8073301902944518e-06, + "loss": 0.901, + "step": 2330 + }, + { + "epoch": 2.047254430102822, + "grad_norm": 1.2381782531738281, + "learning_rate": 2.761655084093976e-06, + "loss": 0.9096, + "step": 2340 + }, + { + "epoch": 2.0560052504922335, + "grad_norm": 1.265434980392456, + "learning_rate": 2.7162123992050316e-06, + "loss": 0.8984, + "step": 2350 + }, + { + "epoch": 2.064756070881645, + "grad_norm": 1.2683861255645752, + "learning_rate": 2.671006854224982e-06, + "loss": 0.8864, + "step": 2360 + }, + { + "epoch": 2.0735068912710566, + "grad_norm": 1.2859617471694946, + "learning_rate": 2.626043143127477e-06, + "loss": 0.8728, + "step": 2370 + }, + { + "epoch": 2.082257711660468, + "grad_norm": 1.3000761270523071, + "learning_rate": 2.5813259347750445e-06, + "loss": 0.932, + "step": 2380 + }, + { + "epoch": 2.0910085320498797, + "grad_norm": 1.23272705078125, + "learning_rate": 2.5368598724342974e-06, + "loss": 0.9114, + "step": 2390 + }, + { + "epoch": 2.0997593524392912, + "grad_norm": 1.243643879890442, + "learning_rate": 2.4926495732937877e-06, + "loss": 0.8987, + "step": 2400 + }, + { + "epoch": 2.108510172828703, + "grad_norm": 1.2681580781936646, + "learning_rate": 2.4486996279845864e-06, + "loss": 0.9277, + "step": 2410 + }, + { + "epoch": 2.1172609932181143, + "grad_norm": 1.2045451402664185, + "learning_rate": 2.4050146001035983e-06, + "loss": 0.8988, + "step": 2420 + }, + { + "epoch": 2.126011813607526, + "grad_norm": 1.2446624040603638, + "learning_rate": 2.361599025739695e-06, + "loss": 0.889, + "step": 2430 + }, + { + "epoch": 2.134762633996937, + "grad_norm": 1.298621654510498, + "learning_rate": 2.318457413002718e-06, + "loss": 0.898, + "step": 2440 + }, + { + "epoch": 2.1435134543863485, + "grad_norm": 1.2545632123947144, + "learning_rate": 2.2755942415553593e-06, + "loss": 0.8675, + "step": 2450 + }, + { + "epoch": 2.15226427477576, + "grad_norm": 1.1765785217285156, + "learning_rate": 2.233013962148016e-06, + "loss": 0.853, + "step": 2460 + }, + { + "epoch": 2.1610150951651717, + "grad_norm": 1.3674156665802002, + "learning_rate": 2.1907209961566418e-06, + "loss": 0.9134, + "step": 2470 + }, + { + "epoch": 2.169765915554583, + "grad_norm": 1.337667465209961, + "learning_rate": 2.1487197351236443e-06, + "loss": 0.8766, + "step": 2480 + }, + { + "epoch": 2.1785167359439948, + "grad_norm": 1.240268349647522, + "learning_rate": 2.107014540301886e-06, + "loss": 0.8921, + "step": 2490 + }, + { + "epoch": 2.1872675563334063, + "grad_norm": 1.2723026275634766, + "learning_rate": 2.0656097422018346e-06, + "loss": 0.8948, + "step": 2500 + }, + { + "epoch": 2.196018376722818, + "grad_norm": 1.244240164756775, + "learning_rate": 2.0245096401418853e-06, + "loss": 0.902, + "step": 2510 + }, + { + "epoch": 2.2047691971122294, + "grad_norm": 1.2332072257995605, + "learning_rate": 1.9837185018019465e-06, + "loss": 0.9042, + "step": 2520 + }, + { + "epoch": 2.213520017501641, + "grad_norm": 1.3075368404388428, + "learning_rate": 1.9432405627802963e-06, + "loss": 0.8743, + "step": 2530 + }, + { + "epoch": 2.2222708378910525, + "grad_norm": 1.2511454820632935, + "learning_rate": 1.9030800261537742e-06, + "loss": 0.8919, + "step": 2540 + }, + { + "epoch": 2.2310216582804636, + "grad_norm": 1.2848820686340332, + "learning_rate": 1.8632410620413505e-06, + "loss": 0.8948, + "step": 2550 + }, + { + "epoch": 2.239772478669875, + "grad_norm": 1.1853325366973877, + "learning_rate": 1.823727807171115e-06, + "loss": 0.9262, + "step": 2560 + }, + { + "epoch": 2.2485232990592867, + "grad_norm": 1.2825355529785156, + "learning_rate": 1.7845443644507355e-06, + "loss": 0.8744, + "step": 2570 + }, + { + "epoch": 2.2572741194486983, + "grad_norm": 1.2997822761535645, + "learning_rate": 1.7456948025414288e-06, + "loss": 0.9153, + "step": 2580 + }, + { + "epoch": 2.26602493983811, + "grad_norm": 1.2967973947525024, + "learning_rate": 1.7071831554354822e-06, + "loss": 0.8702, + "step": 2590 + }, + { + "epoch": 2.2747757602275214, + "grad_norm": 1.2506667375564575, + "learning_rate": 1.6690134220373866e-06, + "loss": 0.9055, + "step": 2600 + }, + { + "epoch": 2.283526580616933, + "grad_norm": 1.2581911087036133, + "learning_rate": 1.631189565748596e-06, + "loss": 0.8953, + "step": 2610 + }, + { + "epoch": 2.2922774010063445, + "grad_norm": 1.2846101522445679, + "learning_rate": 1.5937155140559885e-06, + "loss": 0.8857, + "step": 2620 + }, + { + "epoch": 2.301028221395756, + "grad_norm": 1.317673683166504, + "learning_rate": 1.556595158124049e-06, + "loss": 0.8936, + "step": 2630 + }, + { + "epoch": 2.309779041785167, + "grad_norm": 1.3196806907653809, + "learning_rate": 1.5198323523908266e-06, + "loss": 0.8889, + "step": 2640 + }, + { + "epoch": 2.3185298621745787, + "grad_norm": 1.2810077667236328, + "learning_rate": 1.483430914167701e-06, + "loss": 0.9023, + "step": 2650 + }, + { + "epoch": 2.3272806825639902, + "grad_norm": 1.3437639474868774, + "learning_rate": 1.447394623243018e-06, + "loss": 0.9372, + "step": 2660 + }, + { + "epoch": 2.336031502953402, + "grad_norm": 1.2470753192901611, + "learning_rate": 1.41172722148959e-06, + "loss": 0.8692, + "step": 2670 + }, + { + "epoch": 2.3447823233428133, + "grad_norm": 1.226980209350586, + "learning_rate": 1.3764324124761735e-06, + "loss": 0.9238, + "step": 2680 + }, + { + "epoch": 2.353533143732225, + "grad_norm": 1.2623775005340576, + "learning_rate": 1.3415138610828987e-06, + "loss": 0.8965, + "step": 2690 + }, + { + "epoch": 2.3622839641216364, + "grad_norm": 1.1816771030426025, + "learning_rate": 1.3069751931207164e-06, + "loss": 0.863, + "step": 2700 + }, + { + "epoch": 2.371034784511048, + "grad_norm": 1.0856176614761353, + "learning_rate": 1.2728199949549143e-06, + "loss": 0.8694, + "step": 2710 + }, + { + "epoch": 2.3797856049004595, + "grad_norm": 1.1386377811431885, + "learning_rate": 1.2390518131327173e-06, + "loss": 0.8742, + "step": 2720 + }, + { + "epoch": 2.388536425289871, + "grad_norm": 1.1820670366287231, + "learning_rate": 1.205674154015033e-06, + "loss": 0.8797, + "step": 2730 + }, + { + "epoch": 2.3972872456792826, + "grad_norm": 1.3150583505630493, + "learning_rate": 1.1726904834123582e-06, + "loss": 0.9003, + "step": 2740 + }, + { + "epoch": 2.4060380660686937, + "grad_norm": 1.30619478225708, + "learning_rate": 1.1401042262249056e-06, + "loss": 0.9086, + "step": 2750 + }, + { + "epoch": 2.4147888864581053, + "grad_norm": 1.3051726818084717, + "learning_rate": 1.10791876608698e-06, + "loss": 0.8602, + "step": 2760 + }, + { + "epoch": 2.423539706847517, + "grad_norm": 1.225061297416687, + "learning_rate": 1.0761374450156203e-06, + "loss": 0.8669, + "step": 2770 + }, + { + "epoch": 2.4322905272369284, + "grad_norm": 1.1500948667526245, + "learning_rate": 1.04476356306359e-06, + "loss": 0.8733, + "step": 2780 + }, + { + "epoch": 2.44104134762634, + "grad_norm": 1.2501094341278076, + "learning_rate": 1.0138003779767102e-06, + "loss": 0.9025, + "step": 2790 + }, + { + "epoch": 2.4497921680157515, + "grad_norm": 1.1673866510391235, + "learning_rate": 9.832511048555825e-07, + "loss": 0.918, + "step": 2800 + }, + { + "epoch": 2.458542988405163, + "grad_norm": 1.2898247241973877, + "learning_rate": 9.53118915821748e-07, + "loss": 0.8854, + "step": 2810 + }, + { + "epoch": 2.4672938087945746, + "grad_norm": 1.201026201248169, + "learning_rate": 9.234069396883066e-07, + "loss": 0.9144, + "step": 2820 + }, + { + "epoch": 2.476044629183986, + "grad_norm": 1.1994189023971558, + "learning_rate": 8.941182616350319e-07, + "loss": 0.889, + "step": 2830 + }, + { + "epoch": 2.4847954495733973, + "grad_norm": 1.2872554063796997, + "learning_rate": 8.652559228880169e-07, + "loss": 0.8989, + "step": 2840 + }, + { + "epoch": 2.493546269962809, + "grad_norm": 1.286000370979309, + "learning_rate": 8.368229204038897e-07, + "loss": 0.9244, + "step": 2850 + }, + { + "epoch": 2.5022970903522204, + "grad_norm": 1.227409839630127, + "learning_rate": 8.088222065586132e-07, + "loss": 0.9, + "step": 2860 + }, + { + "epoch": 2.511047910741632, + "grad_norm": 1.2374303340911865, + "learning_rate": 7.812566888409228e-07, + "loss": 0.9094, + "step": 2870 + }, + { + "epoch": 2.5197987311310435, + "grad_norm": 1.3504208326339722, + "learning_rate": 7.541292295504327e-07, + "loss": 0.8945, + "step": 2880 + }, + { + "epoch": 2.528549551520455, + "grad_norm": 1.203357219696045, + "learning_rate": 7.27442645500413e-07, + "loss": 0.8938, + "step": 2890 + }, + { + "epoch": 2.5373003719098666, + "grad_norm": 1.2361124753952026, + "learning_rate": 7.011997077253113e-07, + "loss": 0.8804, + "step": 2900 + }, + { + "epoch": 2.546051192299278, + "grad_norm": 1.2695845365524292, + "learning_rate": 6.75403141193014e-07, + "loss": 0.901, + "step": 2910 + }, + { + "epoch": 2.5548020126886897, + "grad_norm": 1.3083370923995972, + "learning_rate": 6.500556245218986e-07, + "loss": 0.903, + "step": 2920 + }, + { + "epoch": 2.5635528330781012, + "grad_norm": 1.253382921218872, + "learning_rate": 6.25159789702695e-07, + "loss": 0.8944, + "step": 2930 + }, + { + "epoch": 2.5723036534675128, + "grad_norm": 1.2046483755111694, + "learning_rate": 6.007182218251883e-07, + "loss": 0.8654, + "step": 2940 + }, + { + "epoch": 2.5810544738569243, + "grad_norm": 1.286098837852478, + "learning_rate": 5.767334588097979e-07, + "loss": 0.8889, + "step": 2950 + }, + { + "epoch": 2.5898052942463354, + "grad_norm": 1.212591290473938, + "learning_rate": 5.532079911440419e-07, + "loss": 0.8724, + "step": 2960 + }, + { + "epoch": 2.598556114635747, + "grad_norm": 1.2204617261886597, + "learning_rate": 5.301442616239371e-07, + "loss": 0.8696, + "step": 2970 + }, + { + "epoch": 2.6073069350251585, + "grad_norm": 1.1826462745666504, + "learning_rate": 5.075446651003535e-07, + "loss": 0.8542, + "step": 2980 + }, + { + "epoch": 2.61605775541457, + "grad_norm": 1.270414113998413, + "learning_rate": 4.854115482303345e-07, + "loss": 0.8681, + "step": 2990 + }, + { + "epoch": 2.6248085758039816, + "grad_norm": 1.2174789905548096, + "learning_rate": 4.6374720923343275e-07, + "loss": 0.9086, + "step": 3000 + }, + { + "epoch": 2.633559396193393, + "grad_norm": 1.2752397060394287, + "learning_rate": 4.4255389765307077e-07, + "loss": 0.8978, + "step": 3010 + }, + { + "epoch": 2.6423102165828047, + "grad_norm": 1.2312636375427246, + "learning_rate": 4.2183381412295666e-07, + "loss": 0.8834, + "step": 3020 + }, + { + "epoch": 2.6510610369722163, + "grad_norm": 1.1354252099990845, + "learning_rate": 4.015891101385794e-07, + "loss": 0.8863, + "step": 3030 + }, + { + "epoch": 2.6598118573616274, + "grad_norm": 1.2844924926757812, + "learning_rate": 3.8182188783380534e-07, + "loss": 0.8984, + "step": 3040 + }, + { + "epoch": 2.668562677751039, + "grad_norm": 1.2184648513793945, + "learning_rate": 3.6253419976260027e-07, + "loss": 0.904, + "step": 3050 + }, + { + "epoch": 2.6773134981404505, + "grad_norm": 1.2693063020706177, + "learning_rate": 3.437280486858996e-07, + "loss": 0.8813, + "step": 3060 + }, + { + "epoch": 2.686064318529862, + "grad_norm": 1.3009639978408813, + "learning_rate": 3.2540538736364977e-07, + "loss": 0.8851, + "step": 3070 + }, + { + "epoch": 2.6948151389192736, + "grad_norm": 1.2336896657943726, + "learning_rate": 3.075681183520407e-07, + "loss": 0.8994, + "step": 3080 + }, + { + "epoch": 2.703565959308685, + "grad_norm": 1.2099403142929077, + "learning_rate": 2.9021809380595066e-07, + "loss": 0.899, + "step": 3090 + }, + { + "epoch": 2.7123167796980967, + "grad_norm": 1.1838281154632568, + "learning_rate": 2.7335711528663047e-07, + "loss": 0.8951, + "step": 3100 + }, + { + "epoch": 2.7210676000875083, + "grad_norm": 1.2549548149108887, + "learning_rate": 2.569869335746267e-07, + "loss": 0.8795, + "step": 3110 + }, + { + "epoch": 2.72981842047692, + "grad_norm": 1.189772605895996, + "learning_rate": 2.411092484879957e-07, + "loss": 0.8632, + "step": 3120 + }, + { + "epoch": 2.7385692408663314, + "grad_norm": 1.4026386737823486, + "learning_rate": 2.2572570870579845e-07, + "loss": 0.905, + "step": 3130 + }, + { + "epoch": 2.747320061255743, + "grad_norm": 1.2943899631500244, + "learning_rate": 2.1083791159690615e-07, + "loss": 0.8858, + "step": 3140 + }, + { + "epoch": 2.7560708816451545, + "grad_norm": 1.3465709686279297, + "learning_rate": 1.9644740305413636e-07, + "loss": 0.8963, + "step": 3150 + }, + { + "epoch": 2.764821702034566, + "grad_norm": 1.2346800565719604, + "learning_rate": 1.8255567733373392e-07, + "loss": 0.8928, + "step": 3160 + }, + { + "epoch": 2.773572522423977, + "grad_norm": 1.255714774131775, + "learning_rate": 1.691641769002139e-07, + "loss": 0.8977, + "step": 3170 + }, + { + "epoch": 2.7823233428133887, + "grad_norm": 1.3175842761993408, + "learning_rate": 1.5627429227657864e-07, + "loss": 0.9226, + "step": 3180 + }, + { + "epoch": 2.7910741632028, + "grad_norm": 1.333662748336792, + "learning_rate": 1.4388736189993257e-07, + "loss": 0.8932, + "step": 3190 + }, + { + "epoch": 2.7998249835922118, + "grad_norm": 1.2100019454956055, + "learning_rate": 1.320046719825069e-07, + "loss": 0.8886, + "step": 3200 + }, + { + "epoch": 2.8085758039816233, + "grad_norm": 1.2037444114685059, + "learning_rate": 1.2062745637809737e-07, + "loss": 0.8912, + "step": 3210 + }, + { + "epoch": 2.817326624371035, + "grad_norm": 1.2076711654663086, + "learning_rate": 1.0975689645395193e-07, + "loss": 0.8627, + "step": 3220 + }, + { + "epoch": 2.8260774447604464, + "grad_norm": 1.2997610569000244, + "learning_rate": 9.939412096809986e-08, + "loss": 0.899, + "step": 3230 + }, + { + "epoch": 2.8348282651498575, + "grad_norm": 1.171425461769104, + "learning_rate": 8.954020595214441e-08, + "loss": 0.9032, + "step": 3240 + }, + { + "epoch": 2.843579085539269, + "grad_norm": 1.2966265678405762, + "learning_rate": 8.019617459953333e-08, + "loss": 0.8888, + "step": 3250 + }, + { + "epoch": 2.8523299059286806, + "grad_norm": 1.27556574344635, + "learning_rate": 7.136299715931438e-08, + "loss": 0.8775, + "step": 3260 + }, + { + "epoch": 2.861080726318092, + "grad_norm": 1.2437477111816406, + "learning_rate": 6.304159083538652e-08, + "loss": 0.8696, + "step": 3270 + }, + { + "epoch": 2.8698315467075037, + "grad_norm": 1.2502518892288208, + "learning_rate": 5.523281969126271e-08, + "loss": 0.8915, + "step": 3280 + }, + { + "epoch": 2.8785823670969153, + "grad_norm": 1.250112771987915, + "learning_rate": 4.7937494560349464e-08, + "loss": 0.8792, + "step": 3290 + }, + { + "epoch": 2.887333187486327, + "grad_norm": 1.2390645742416382, + "learning_rate": 4.115637296174979e-08, + "loss": 0.8995, + "step": 3300 + }, + { + "epoch": 2.8960840078757384, + "grad_norm": 1.2656710147857666, + "learning_rate": 3.4890159021608305e-08, + "loss": 0.8741, + "step": 3310 + }, + { + "epoch": 2.90483482826515, + "grad_norm": 1.149044156074524, + "learning_rate": 2.9139503399996382e-08, + "loss": 0.8869, + "step": 3320 + }, + { + "epoch": 2.9135856486545615, + "grad_norm": 1.2886285781860352, + "learning_rate": 2.3905003223349544e-08, + "loss": 0.8875, + "step": 3330 + }, + { + "epoch": 2.922336469043973, + "grad_norm": 1.2327951192855835, + "learning_rate": 1.9187202022464822e-08, + "loss": 0.8899, + "step": 3340 + }, + { + "epoch": 2.9310872894333846, + "grad_norm": 1.3543472290039062, + "learning_rate": 1.4986589676063147e-08, + "loss": 0.8787, + "step": 3350 + }, + { + "epoch": 2.939838109822796, + "grad_norm": 1.3077126741409302, + "learning_rate": 1.1303602359919452e-08, + "loss": 0.9173, + "step": 3360 + }, + { + "epoch": 2.9485889302122072, + "grad_norm": 1.254578948020935, + "learning_rate": 8.1386225015756e-09, + "loss": 0.8375, + "step": 3370 + }, + { + "epoch": 2.957339750601619, + "grad_norm": 1.3026719093322754, + "learning_rate": 5.491978740627679e-09, + "loss": 0.8827, + "step": 3380 + }, + { + "epoch": 2.9660905709910304, + "grad_norm": 1.2489607334136963, + "learning_rate": 3.3639458946027603e-09, + "loss": 0.8835, + "step": 3390 + }, + { + "epoch": 2.974841391380442, + "grad_norm": 1.264045000076294, + "learning_rate": 1.7547449304222696e-09, + "loss": 0.8905, + "step": 3400 + }, + { + "epoch": 2.9835922117698535, + "grad_norm": 1.2398723363876343, + "learning_rate": 6.645429414570137e-10, + "loss": 0.8854, + "step": 3410 + }, + { + "epoch": 2.992343032159265, + "grad_norm": 1.2165299654006958, + "learning_rate": 9.345313017938839e-11, + "loss": 0.8911, + "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..c8ef91d5e9ee2fb2a2493df3c1be634ab282994a --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820107c450f9970840ac4a0e16496303518791415599627ba058a86e48a877dc +size 4943274328 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9443bcf70a6371d56dfdc13c5b413b7c2d2090eb --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a014650eacad2d305c266635ee4b02e6be5673ca799708ce4f68bb78b754d591 +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..4e44b1c822a527ca6f13ecb13cb34752d34c3146 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624091669511519817f039dffda036537c092491ac9942969536d5000055fdb6 +size 6353