Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a7a6acc2e229d6ac777f7db99e140da4a6b4b0fb8dc42de984f2ba5668aba0
+oid sha256:d6ffcfc40d589ce0b6dd6df844dd95e8b8880932c10c713a0c73aced339869f3
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb0e1c14b1fedfdcb541e274a0187a6a76f40f54ef4d70553f11af8d58bed1f
+oid sha256:b2af64e77994e236659aca185b0ef802526cfbacb78bc7d64d83fc6e96716a59
 size 40131268

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e8c5e597281b87cdb4d76ec6e31877af66233abff999994a7c03255786430
+oid sha256:31a9827b5b55d3198d221c0ef9991e57cf0b8cb8526bf545d88ea8fccef7a892
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33daadc0c8784b734b94f204caebbcb9d5ab500af28517017de7ebeedc1baac9
+oid sha256:2ffbbb63f9cebda9480278aecd34a01e4c2839f21778c5bbd0fd7ee355c0640e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07044081955184286,
+  "epoch": 0.09030874301518316,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 24.008,
       "eval_steps_per_second": 6.005,
       "step": 39
+    },
+    {
+      "epoch": 0.07224699441214652,
+      "grad_norm": 0.23702038824558258,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4505,
+      "step": 40
+    },
+    {
+      "epoch": 0.07405316927245019,
+      "grad_norm": 0.21211156249046326,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4021,
+      "step": 41
+    },
+    {
+      "epoch": 0.07585934413275386,
+      "grad_norm": 0.2211143970489502,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4463,
+      "step": 42
+    },
+    {
+      "epoch": 0.07766551899305751,
+      "grad_norm": 0.20987620949745178,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4313,
+      "step": 43
+    },
+    {
+      "epoch": 0.07947169385336118,
+      "grad_norm": 0.2077188938856125,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4092,
+      "step": 44
+    },
+    {
+      "epoch": 0.08127786871366484,
+      "grad_norm": 0.1921454817056656,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4024,
+      "step": 45
+    },
+    {
+      "epoch": 0.08308404357396851,
+      "grad_norm": 0.22376859188079834,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4143,
+      "step": 46
+    },
+    {
+      "epoch": 0.08489021843427216,
+      "grad_norm": 0.2070239931344986,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3753,
+      "step": 47
+    },
+    {
+      "epoch": 0.08669639329457583,
+      "grad_norm": 0.22126780450344086,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4333,
+      "step": 48
+    },
+    {
+      "epoch": 0.08850256815487949,
+      "grad_norm": 0.21691939234733582,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4049,
+      "step": 49
+    },
+    {
+      "epoch": 0.09030874301518316,
+      "grad_norm": 0.20602606236934662,
+      "learning_rate": 0.0,
+      "loss": 0.3844,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.455503262061691e+17,
+  "total_flos": 3.148081105207296e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null