Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e38cac279788f9ba48a6c252096f5316038cc48fe5b51aecebe97fd7e0b300
+oid sha256:3ea0c62440d4958bb35985e501f62fa55eb003dc3a1350bf1c5345ee15152212
 size 1037269336

last-checkpoint/global_step6050/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e21c52cb5d6020fa7d0c6fcc8acb8b4a522e62a7624aaa9d53cfd540b8273b
+size 781993445

last-checkpoint/global_step6050/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85caed726123824f3f1260cfe6d89f6f06dc5f03afdb291be53e4bdc73666298
+size 781993509

last-checkpoint/global_step6050/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:eb334fff088ade44f69b13a2ece19e8dba9c81956647313b6a6fe9a7567c7fa3
+size 781993509

last-checkpoint/global_step6050/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aae84590fe190b7b7fd8f5301ad294360c4990ab4926c56736445e79eac4cbe
+size 781993509

last-checkpoint/global_step6050/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0216656aa146e2f3a1c20ddd86caf831aa624281d16d6ab45ee3ddc16dc716e
+size 2610290277

last-checkpoint/latest

@@ -1 +1 @@
-global_step5950
+global_step6050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0590a67baf4c1926f23f7e23aa5dacc5865d56c4011a19a76ef7d9605e2b80cb
+oid sha256:84ca052bf113ca6aa364f4045598302f593db67e6acfb7d59d3634c066cab80a
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b2ff2dc738c62e79eb57d73e98bf3d93857213c3ae83881f4d39dde87d854d
+oid sha256:6801bd8ecfc9dc7bb5869a7e989aff32f373fd4c90cdf32a4fb5cc799f028212
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3107650669538fc83ee4233872ab550b4ceee7b7ea0a12a83f0b019318c5e53
+oid sha256:f2a6957df24b3fb7952b567d60a71a2ff6d82f37c52b0479941f7b0e9e2ae89f
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b96eed057177434cca431902963d067905c97002c5aa1580bb7f37ccf8d5a7
+oid sha256:42595b2ca965b2f44bfbc256b7ce186f80199e9132df51df786eee1f053b8ce7
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d67081d54a8742d659188f7c13f1d7ba7d806ea43a013dcf3b81362a9e0de6
+oid sha256:76b65b8068a2fa89a73c3f08865a6e5e6a870915916826840fa8d3d74d812d20
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 1.7622941732406616,
+  "best_metric": 1.7598167657852173,
   "best_model_checkpoint": null,
-  "epoch": 0.8649513010612008,
+  "epoch": 0.8794882977176915,
   "eval_steps": 50,
-  "global_step": 5950,
+  "global_step": 6050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9290,6 +9290,162 @@
       "eval_samples_per_second": 171.698,
       "eval_steps_per_second": 10.767,
       "step": 5950
+    },
+    {
+      "epoch": 0.8656781508940253,
+      "grad_norm": 2.325075626373291,
+      "learning_rate": 3.59230223035765e-05,
+      "loss": 1.8612,
+      "step": 5955
+    },
+    {
+      "epoch": 0.8664050007268498,
+      "grad_norm": 2.125944137573242,
+      "learning_rate": 3.584679931454372e-05,
+      "loss": 2.0552,
+      "step": 5960
+    },
+    {
+      "epoch": 0.8671318505596743,
+      "grad_norm": 2.3498165607452393,
+      "learning_rate": 3.577061220381711e-05,
+      "loss": 1.9108,
+      "step": 5965
+    },
+    {
+      "epoch": 0.8678587003924989,
+      "grad_norm": 2.3271546363830566,
+      "learning_rate": 3.5694461163197637e-05,
+      "loss": 2.0418,
+      "step": 5970
+    },
+    {
+      "epoch": 0.8685855502253235,
+      "grad_norm": 2.6309621334075928,
+      "learning_rate": 3.561834638439542e-05,
+      "loss": 2.2077,
+      "step": 5975
+    },
+    {
+      "epoch": 0.869312400058148,
+      "grad_norm": 2.5525426864624023,
+      "learning_rate": 3.554226805902938e-05,
+      "loss": 2.014,
+      "step": 5980
+    },
+    {
+      "epoch": 0.8700392498909725,
+      "grad_norm": 2.4370927810668945,
+      "learning_rate": 3.546622637862657e-05,
+      "loss": 1.9503,
+      "step": 5985
+    },
+    {
+      "epoch": 0.870766099723797,
+      "grad_norm": 2.439393997192383,
+      "learning_rate": 3.539022153462185e-05,
+      "loss": 1.87,
+      "step": 5990
+    },
+    {
+      "epoch": 0.8714929495566216,
+      "grad_norm": 2.106350898742676,
+      "learning_rate": 3.531425371835732e-05,
+      "loss": 1.8859,
+      "step": 5995
+    },
+    {
+      "epoch": 0.8722197993894462,
+      "grad_norm": 2.5693132877349854,
+      "learning_rate": 3.523832312108185e-05,
+      "loss": 1.9528,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8722197993894462,
+      "eval_loss": 1.7619251012802124,
+      "eval_runtime": 21.1122,
+      "eval_samples_per_second": 156.355,
+      "eval_steps_per_second": 9.805,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8729466492222707,
+      "grad_norm": 2.170193910598755,
+      "learning_rate": 3.516242993395065e-05,
+      "loss": 1.9875,
+      "step": 6005
+    },
+    {
+      "epoch": 0.8736734990550952,
+      "grad_norm": 1.888143539428711,
+      "learning_rate": 3.50865743480247e-05,
+      "loss": 1.8329,
+      "step": 6010
+    },
+    {
+      "epoch": 0.8744003488879197,
+      "grad_norm": 2.452836513519287,
+      "learning_rate": 3.5010756554270395e-05,
+      "loss": 1.9746,
+      "step": 6015
+    },
+    {
+      "epoch": 0.8751271987207443,
+      "grad_norm": 2.2386631965637207,
+      "learning_rate": 3.493497674355889e-05,
+      "loss": 2.0318,
+      "step": 6020
+    },
+    {
+      "epoch": 0.8758540485535689,
+      "grad_norm": 2.0503358840942383,
+      "learning_rate": 3.4859235106665804e-05,
+      "loss": 1.9775,
+      "step": 6025
+    },
+    {
+      "epoch": 0.8765808983863934,
+      "grad_norm": 2.4012866020202637,
+      "learning_rate": 3.47835318342706e-05,
+      "loss": 1.9532,
+      "step": 6030
+    },
+    {
+      "epoch": 0.8773077482192179,
+      "grad_norm": 2.37467622756958,
+      "learning_rate": 3.470786711695619e-05,
+      "loss": 1.876,
+      "step": 6035
+    },
+    {
+      "epoch": 0.8780345980520424,
+      "grad_norm": 2.233384370803833,
+      "learning_rate": 3.463224114520838e-05,
+      "loss": 2.0133,
+      "step": 6040
+    },
+    {
+      "epoch": 0.878761447884867,
+      "grad_norm": 2.4239954948425293,
+      "learning_rate": 3.4556654109415496e-05,
+      "loss": 1.8969,
+      "step": 6045
+    },
+    {
+      "epoch": 0.8794882977176915,
+      "grad_norm": 2.236656904220581,
+      "learning_rate": 3.44811061998678e-05,
+      "loss": 2.0484,
+      "step": 6050
+    },
+    {
+      "epoch": 0.8794882977176915,
+      "eval_loss": 1.7598167657852173,
+      "eval_runtime": 18.9654,
+      "eval_samples_per_second": 174.054,
+      "eval_steps_per_second": 10.915,
+      "step": 6050
     }
   ],
   "logging_steps": 5,
@@ -9318,7 +9474,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5511774280076493e+18,
+  "total_flos": 1.5770032329226977e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null