Training in progress, step 234, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042b65e1dac882ac0093711ff9d1ed6dec458676188c7d4000affb0485375140
+oid sha256:1990c2d68f0e2e44d28f9a5ee2378d9cee7f403a3934fca2a1cb4385e8f66fc6
 size 550593856

last-checkpoint/global_step234/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3978781575f21b035f8ba8f5cdf0926bb0c9639ee8f3b475d8beff9f5ff762e8
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331c79fad78e2018dd5ab702370191c1ba9d76ceed7df33831618cc74f51f139
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a829b15f8ce7aaccd2aa9e7b413a1499fc9117e65bfbd4bb0e0c9b4e754dc6cf
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a8a270568d77ff77bb3b06638111e8dd5762cf5a7c0da42dfa357b3f339c0c
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae710fc3816397c00617977eda0f3a0869a72696f4ff8ca9f199140b6659fdd4
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54dfa0369915dc9f6c5e05306751bf6cb81a0a30b988dca22cc6afc97b88006
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e0d94fa68689faccd4069ec0129ff3aa6cea98e66d110d55969e8f100aae0e
+size 243590464

last-checkpoint/global_step234/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af78a0696566f11c7acc705d8bdbfb9401d1b103365d1f956043384ba4abe78c
+size 243590464

last-checkpoint/global_step234/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5286b6bf1b06e4faeea7783920020d7f9e730ae75c99d086ddef52daa56896
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb304e1edba2ada327ea07b04d195bedc51426cefec33d8fc89c986365cae1f7
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c931d02bb03ff9aaf2141b57d64494b21d048147ffc41c2849d75053183d16a6
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfccbfd9f4bc00b40475ea66d1c49501eef8d5d9d7b379fad1a3a892588c3f0
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedc996b57fd1e9b2c353c6fa9dc2a23aca3db52ec66f40e0ca7cda820a9955b
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fccd3cfabeb6bedcd9ba9e760f04df590e889b9c525639d449c227212f3d8661
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a2173d0821780144beac4cd92441e2d47bd4ff489e6bcb2522b3dcb5f2fd26
+size 211435686

last-checkpoint/global_step234/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6f252a007f965b4fe85d1dfef586386bb45f891dcb9d2af9f4785643c81e94
+size 211435686

last-checkpoint/latest

@@ -1 +1 @@
-global_step195
+global_step234

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d205b247ab17b5fb7452990cd269cf4ef10bda2683097ddce6af8c135abdc1
+oid sha256:134a1f059f52a9bdf9df082d6896f7d8b5760d4d52176fa82dfbe01a23fb87c9
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ca1bf98495958499a22cade70d63eaabfdcb012a2f66af4f5e7d4414626392
+oid sha256:92a620eacd8f4cd828cfb1aebe552d5e8dae8821e0f453da23766cd3cb0fc809
 size 15920

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4071ea30f675614d9bcaeb751a6df81010828e93a461dc017bb8c2d1790fd8b3
+oid sha256:a162c9df7047160908baee7101046d35e92bb1a1356ac6f65730b0b0abb6d169
 size 15920

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122476c594e95007c2b6aee18c853f5e96679ed35da34b2a71dda0a35dffb9b3
+oid sha256:2f9712a619d6aa46296d8a883ec08e9d1c3e69b8f47bb56e4a362c61af346d5c
 size 15920

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61b284b2b274f92f376a2e95925d0cbb78a5ed491b1f17dff855d4053e0449d
+oid sha256:4c3be75b246d7517b2ce93c5ea356d84fa1126631a1aa584e4174a6a45fb01f8
 size 15920

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee5173863e2cb2c91670d300a1232c7136aeb3cbb8e8c415e2b561ed21531c1
+oid sha256:b2cd295e7ee2a480367b2e688de7637a1d212d602ed9ac1e83ce463138ef7d19
 size 15920

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae86fdfe88f89628e7a5f8ad48bf1ed1417d375ea504c7851d524b56445ed89
+oid sha256:393dcff3659995d822f8e1744b724bc57b6986bec073c96de798eb021d6f55e4
 size 15920

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb21013bed59d364e3b186bc3199360efcdc8144f2dd2d2b123e56a645623fe2
+oid sha256:f042c259ed788084e3425e22e2364144fa3d72b73d1f475b32393e7b99cb156c
 size 15920

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b13e35de6391f1bb48cdfbaa998c2879cd015ccd85e1b48a62d504eed8a347
+oid sha256:366054962264279f0b5e5302d033c378e5387597c8a92a96d8dbf2d43d872448
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5078125,
+  "epoch": 0.609375,
   "eval_steps": 39,
-  "global_step": 195,
+  "global_step": 234,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1420,6 +1420,287 @@
       "eval_samples_per_second": 1.225,
       "eval_steps_per_second": 0.153,
       "step": 195
+    },
+    {
+      "epoch": 0.5104166666666666,
+      "grad_norm": 0.15606553454493674,
+      "learning_rate": 5.7329260879789437e-05,
+      "loss": 2.3709,
+      "step": 196
+    },
+    {
+      "epoch": 0.5130208333333334,
+      "grad_norm": 0.1448236972696976,
+      "learning_rate": 5.6941315870408066e-05,
+      "loss": 2.4256,
+      "step": 197
+    },
+    {
+      "epoch": 0.515625,
+      "grad_norm": 0.15924118657730604,
+      "learning_rate": 5.655322625363687e-05,
+      "loss": 2.5228,
+      "step": 198
+    },
+    {
+      "epoch": 0.5182291666666666,
+      "grad_norm": 0.17454487852950232,
+      "learning_rate": 5.616502093802565e-05,
+      "loss": 2.2945,
+      "step": 199
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "grad_norm": 0.14248471717781994,
+      "learning_rate": 5.577672884074249e-05,
+      "loss": 2.3514,
+      "step": 200
+    },
+    {
+      "epoch": 0.5234375,
+      "grad_norm": 0.14873123082787126,
+      "learning_rate": 5.538837888541986e-05,
+      "loss": 2.4918,
+      "step": 201
+    },
+    {
+      "epoch": 0.5260416666666666,
+      "grad_norm": 0.1600074911775423,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3231,
+      "step": 202
+    },
+    {
+      "epoch": 0.5286458333333334,
+      "grad_norm": 0.15123679319262007,
+      "learning_rate": 5.461162111458016e-05,
+      "loss": 2.3613,
+      "step": 203
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 0.13067031369476279,
+      "learning_rate": 5.422327115925753e-05,
+      "loss": 2.3407,
+      "step": 204
+    },
+    {
+      "epoch": 0.5338541666666666,
+      "grad_norm": 0.1419685152456832,
+      "learning_rate": 5.3834979061974376e-05,
+      "loss": 2.4375,
+      "step": 205
+    },
+    {
+      "epoch": 0.5364583333333334,
+      "grad_norm": 0.13456464948427768,
+      "learning_rate": 5.3446773746363153e-05,
+      "loss": 2.3542,
+      "step": 206
+    },
+    {
+      "epoch": 0.5390625,
+      "grad_norm": 0.1394757337185396,
+      "learning_rate": 5.305868412959195e-05,
+      "loss": 2.6189,
+      "step": 207
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.14661264347416875,
+      "learning_rate": 5.2670739120210574e-05,
+      "loss": 2.4666,
+      "step": 208
+    },
+    {
+      "epoch": 0.5442708333333334,
+      "grad_norm": 0.15772002651226175,
+      "learning_rate": 5.2282967615997125e-05,
+      "loss": 2.2665,
+      "step": 209
+    },
+    {
+      "epoch": 0.546875,
+      "grad_norm": 0.1436207432226202,
+      "learning_rate": 5.1895398501805383e-05,
+      "loss": 2.4412,
+      "step": 210
+    },
+    {
+      "epoch": 0.5494791666666666,
+      "grad_norm": 0.1627045485383769,
+      "learning_rate": 5.150806064741323e-05,
+      "loss": 2.4241,
+      "step": 211
+    },
+    {
+      "epoch": 0.5520833333333334,
+      "grad_norm": 0.1608053633868765,
+      "learning_rate": 5.112098290537213e-05,
+      "loss": 2.2647,
+      "step": 212
+    },
+    {
+      "epoch": 0.5546875,
+      "grad_norm": 0.15608204954248603,
+      "learning_rate": 5.0734194108858e-05,
+      "loss": 2.4768,
+      "step": 213
+    },
+    {
+      "epoch": 0.5572916666666666,
+      "grad_norm": 0.1576523104437354,
+      "learning_rate": 5.0347723069523355e-05,
+      "loss": 2.2488,
+      "step": 214
+    },
+    {
+      "epoch": 0.5598958333333334,
+      "grad_norm": 0.16267311756196431,
+      "learning_rate": 4.9961598575351155e-05,
+      "loss": 2.2745,
+      "step": 215
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.14597656332784,
+      "learning_rate": 4.9575849388510473e-05,
+      "loss": 2.2226,
+      "step": 216
+    },
+    {
+      "epoch": 0.5651041666666666,
+      "grad_norm": 0.12952717920836662,
+      "learning_rate": 4.919050424321395e-05,
+      "loss": 2.2863,
+      "step": 217
+    },
+    {
+      "epoch": 0.5677083333333334,
+      "grad_norm": 0.14126095486957518,
+      "learning_rate": 4.880559184357745e-05,
+      "loss": 2.2773,
+      "step": 218
+    },
+    {
+      "epoch": 0.5703125,
+      "grad_norm": 0.15894975244045567,
+      "learning_rate": 4.842114086148185e-05,
+      "loss": 2.4144,
+      "step": 219
+    },
+    {
+      "epoch": 0.5729166666666666,
+      "grad_norm": 0.15187930552412898,
+      "learning_rate": 4.803717993443734e-05,
+      "loss": 2.2729,
+      "step": 220
+    },
+    {
+      "epoch": 0.5755208333333334,
+      "grad_norm": 0.15567668429445186,
+      "learning_rate": 4.765373766345028e-05,
+      "loss": 2.4327,
+      "step": 221
+    },
+    {
+      "epoch": 0.578125,
+      "grad_norm": 0.1577838508745425,
+      "learning_rate": 4.727084261089257e-05,
+      "loss": 2.5534,
+      "step": 222
+    },
+    {
+      "epoch": 0.5807291666666666,
+      "grad_norm": 0.1447851641278385,
+      "learning_rate": 4.688852329837424e-05,
+      "loss": 2.2928,
+      "step": 223
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.13963925711509403,
+      "learning_rate": 4.6506808204618754e-05,
+      "loss": 2.3612,
+      "step": 224
+    },
+    {
+      "epoch": 0.5859375,
+      "grad_norm": 0.17944687510007068,
+      "learning_rate": 4.612572576334171e-05,
+      "loss": 2.4195,
+      "step": 225
+    },
+    {
+      "epoch": 0.5885416666666666,
+      "grad_norm": 0.15388075071309162,
+      "learning_rate": 4.574530436113286e-05,
+      "loss": 2.5277,
+      "step": 226
+    },
+    {
+      "epoch": 0.5911458333333334,
+      "grad_norm": 0.12718481374460847,
+      "learning_rate": 4.536557233534153e-05,
+      "loss": 2.2991,
+      "step": 227
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 0.14948263293785125,
+      "learning_rate": 4.498655797196586e-05,
+      "loss": 2.4404,
+      "step": 228
+    },
+    {
+      "epoch": 0.5963541666666666,
+      "grad_norm": 0.13608773847019048,
+      "learning_rate": 4.460828950354577e-05,
+      "loss": 2.2945,
+      "step": 229
+    },
+    {
+      "epoch": 0.5989583333333334,
+      "grad_norm": 0.14126010771163286,
+      "learning_rate": 4.423079510705992e-05,
+      "loss": 2.2835,
+      "step": 230
+    },
+    {
+      "epoch": 0.6015625,
+      "grad_norm": 0.15458611014177978,
+      "learning_rate": 4.3854102901826834e-05,
+      "loss": 2.4491,
+      "step": 231
+    },
+    {
+      "epoch": 0.6041666666666666,
+      "grad_norm": 0.17078246755698387,
+      "learning_rate": 4.3478240947410386e-05,
+      "loss": 2.5331,
+      "step": 232
+    },
+    {
+      "epoch": 0.6067708333333334,
+      "grad_norm": 0.14807435693469648,
+      "learning_rate": 4.3103237241529506e-05,
+      "loss": 2.4154,
+      "step": 233
+    },
+    {
+      "epoch": 0.609375,
+      "grad_norm": 0.15605308853260608,
+      "learning_rate": 4.272911971797279e-05,
+      "loss": 2.3354,
+      "step": 234
+    },
+    {
+      "epoch": 0.609375,
+      "eval_loss": 2.401761531829834,
+      "eval_runtime": 65.3141,
+      "eval_samples_per_second": 1.225,
+      "eval_steps_per_second": 0.153,
+      "step": 234
     }
   ],
   "logging_steps": 1,
@@ -1439,7 +1720,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 64462761492480.0,
+  "total_flos": 77355313790976.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null