Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e3105355c2df4b040acd4c2944a96c6e4176ce252181e7699f9ea948f127e2
+oid sha256:bc6487ab00d7819edaaf1f49a88363d57abccd183ee61af4353c764f4f6f23f5
 size 42002584

last-checkpoint/global_step3500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a260abc6e640dd8e3daa5a349ce4b73fe05ceb36c58ed9ea47b4c296d54fc85
+size 251710672

last-checkpoint/global_step3500/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1f4f50743d9108416e8549518fd567fec0053de9a0d77241fa590e4176271a
+size 47955328

last-checkpoint/latest

@@ -1 +1 @@
-global_step3000
+global_step3500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b552361bcc18d8148b831b255d9e181d4beeb2d1ba3aee8779f232860eb665c7
+oid sha256:68c17378dafa1374ee684c365b3aeb8454074c8a8957207088418a6e24a4f102
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.094017094017094,
+  "epoch": 19.943019943019944,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -434,6 +434,76 @@
       "learning_rate": 5.015015015015015e-05,
       "loss": 0.0534,
       "step": 3000
+    },
+    {
+      "epoch": 17.37891737891738,
+      "grad_norm": 0.06696134060621262,
+      "learning_rate": 4.764764764764765e-05,
+      "loss": 0.0534,
+      "step": 3050
+    },
+    {
+      "epoch": 17.663817663817664,
+      "grad_norm": 0.07864591479301453,
+      "learning_rate": 4.5145145145145146e-05,
+      "loss": 0.0543,
+      "step": 3100
+    },
+    {
+      "epoch": 17.94871794871795,
+      "grad_norm": 0.04788205400109291,
+      "learning_rate": 4.264264264264264e-05,
+      "loss": 0.055,
+      "step": 3150
+    },
+    {
+      "epoch": 18.233618233618234,
+      "grad_norm": 0.08312636613845825,
+      "learning_rate": 4.014014014014014e-05,
+      "loss": 0.0556,
+      "step": 3200
+    },
+    {
+      "epoch": 18.51851851851852,
+      "grad_norm": 0.050425197929143906,
+      "learning_rate": 3.763763763763764e-05,
+      "loss": 0.0531,
+      "step": 3250
+    },
+    {
+      "epoch": 18.803418803418804,
+      "grad_norm": 0.06965469568967819,
+      "learning_rate": 3.513513513513514e-05,
+      "loss": 0.0533,
+      "step": 3300
+    },
+    {
+      "epoch": 19.08831908831909,
+      "grad_norm": 0.05819595977663994,
+      "learning_rate": 3.263263263263263e-05,
+      "loss": 0.0554,
+      "step": 3350
+    },
+    {
+      "epoch": 19.373219373219374,
+      "grad_norm": 0.06934893876314163,
+      "learning_rate": 3.013013013013013e-05,
+      "loss": 0.0545,
+      "step": 3400
+    },
+    {
+      "epoch": 19.65811965811966,
+      "grad_norm": 0.0720212310552597,
+      "learning_rate": 2.762762762762763e-05,
+      "loss": 0.0524,
+      "step": 3450
+    },
+    {
+      "epoch": 19.943019943019944,
+      "grad_norm": 0.04772196337580681,
+      "learning_rate": 2.5125125125125126e-05,
+      "loss": 0.0553,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -453,7 +523,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.179327598749286e+16,
+  "total_flos": 9.530782880523878e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null