Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b685b1486c967cf23886d3449a6f31454d7e30c03d932bf7801636fa5872302
+oid sha256:1c20a70b6d0972c58d836c89ee17cf543a4eb978130e2a4732538878eba93ea0
 size 15035600

last-checkpoint/global_step30/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9412df69a01036961e3472a5d6438d4333253c6f5332b191be198405258091
+size 5661904

last-checkpoint/global_step30/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648810212fda641bb6f0ea8c52f9f58264e4fe7cf515ec7c0f16ed8401163568
+size 5661904

last-checkpoint/global_step30/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:efdf02fae6eda3b9c5dd95355e6f7807ee656c6dc98ea2a9ded4784a0ca30279
+size 5661904

last-checkpoint/global_step30/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:c79e4da80f34f52ab42ed0c1cc22b3cc7fc901beab1347a5a6dd51f8f035cd28
+size 5661968

last-checkpoint/global_step30/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6041137c22fe018e071744fe4736de9fa5b2673cb53dfc566386ce47378754e8
+size 5661968

last-checkpoint/global_step30/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a6ccd925b1c7e41491512bb9e14c83e17cc9e97c69110c071cf7ee5ae969b7
+size 5661968

last-checkpoint/global_step30/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:f5ca882017721e6164ab03e2974b400a856bb97f9dff14d1f4a92dc7318725f0
+size 5661968

last-checkpoint/global_step30/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76844d5a3981940d99ed301990efce274b02d7b6616277d8310a53a78220a9b8
+size 5661968

last-checkpoint/global_step30/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fb1113bb3af1bbd477e907506379319728eeb254284e2e7739a59e8107b821
+size 15248620

last-checkpoint/latest

@@ -1 +1 @@
-global_step24
+global_step30

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34bd4952aa5397fa46bb47d4d085b1886cc176fe885898ef08b3320f3a0e2fb1
+oid sha256:a29af2ff6d4c99e44b8eeb34cba572fe0f21655786ca5302486b8584af092cc5
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6f564937e940389f40673bb4053485cd729fd377eb36c0e61a150019a3522d
+oid sha256:894d72deac20be843c93535c26d6f1697cd73b32fa43d952806c703a5e990a8b
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a04d7fec5221ed547e1be9f14cb87e3ad14bd5439bbf49d163fd51ee1bfd2c1
+oid sha256:a02c0068d36daa3110db1e69464c23686bfe40f580fba01acc0313c4c0745f01
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96483e5a416f5fdbc55fbdc72a3a0945510cc3893340b585d92b0770038c4424
+oid sha256:9c34ccbdfdc447bf30985ec5f6c92287b16b72de8ba528a8942251e1ad2ab961
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9fead095e7ee26e05fd8bc946d326d32914154091bf32979a0f8490c8e8255
+oid sha256:ed2c819f4a38840600ae1da1521ae5c09612f5fd11a79453fa7f948bfb5905a6
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705cc1ff23962a0bed9212fa869462eaa7161ddf0a8975fc77299bfd8a2ef063
+oid sha256:f3f61c6551849a9922566a85cfd895313572e484ca8c6eab7bd499c608c894a4
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1b39843439a5a6448276408569b2391e19fec88f069b48915e897b2b9bbdba
+oid sha256:2a7c2124bbf63aa1393c5d1d506267e32e5f0058803838f9e8118c7b33ed54a0
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:effbec3f9e924087204ea2f1d2043f31fd2771e3ab48d0796e528596d0104ed9
+oid sha256:9f151081a538aaf5cb123553ec389579cfcf08ea63ae904e588e966a31161f3d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c2f528b0de4d670ece3c078c700755c89253d3fb5a8c5c55bc0ddc9ffb9dbe
+oid sha256:4a6f41f72b0f5831073b4bb7a65600110ae9e67c00118701d48bbec2a561f354
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23104693140794225,
+  "epoch": 0.2888086642599278,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -208,6 +208,48 @@
       "eval_samples_per_second": 119.508,
       "eval_steps_per_second": 7.512,
       "step": 24
+    },
+    {
+      "epoch": 0.24067388688327315,
+      "grad_norm": 0.2106037437915802,
+      "learning_rate": 4.06547058867883e-06,
+      "loss": 1.6749,
+      "step": 25
+    },
+    {
+      "epoch": 0.2503008423586041,
+      "grad_norm": 0.19816969335079193,
+      "learning_rate": 2.86474508437579e-06,
+      "loss": 1.6535,
+      "step": 26
+    },
+    {
+      "epoch": 0.259927797833935,
+      "grad_norm": 0.2047451287508011,
+      "learning_rate": 1.8553997993420495e-06,
+      "loss": 1.6481,
+      "step": 27
+    },
+    {
+      "epoch": 0.2695547533092659,
+      "grad_norm": 0.20088627934455872,
+      "learning_rate": 1.0533527116762298e-06,
+      "loss": 1.6513,
+      "step": 28
+    },
+    {
+      "epoch": 0.27918170878459686,
+      "grad_norm": 0.21228325366973877,
+      "learning_rate": 4.7125258307053385e-07,
+      "loss": 1.6851,
+      "step": 29
+    },
+    {
+      "epoch": 0.2888086642599278,
+      "grad_norm": 0.20036223530769348,
+      "learning_rate": 1.1827948028283353e-07,
+      "loss": 1.6196,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -222,12 +264,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.719416501567488e+16,
+  "total_flos": 1.214927062695936e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null