Training in progress, step 3192, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9cd3ef2efeae29b51e25136882cfab90d7a71ca3c7ca103f17568a4ec621271
+oid sha256:e963705c16b053b94ecc7fb1e65350d738a1a1ccc4d852b3b13c8e1132ed1152
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea37f6d5ce2ec5e6702eeb02f71ddad7d49fa6746f7960a3cfbfbbb00ea91183
+oid sha256:41b804648b78f6aba4b3c759b83d3b63afbcc2e9b23d01cff14205168d48d6da
 size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f80ae50f55e38592bafea5bf235aff66d6b17a8507210f6e651d75ef82cc25
+oid sha256:1e837c3df27ba5c150fca3ab0ea53bed8b6518dd15754087371a66bda5b1bffd
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd58a77fb7b7665f33ee01f886911abb1b6ea7a224aa5480aef1ff01347137c
+oid sha256:6637ca6b270447484bcdcef0a0495294e6184477f8a9ca4b540be4b8a24d109b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2727551960683936,
+  "epoch": 1.307156752329272,
   "eval_steps": 500,
-  "global_step": 3108,
+  "global_step": 3192,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2178,6 +2178,69 @@
       "learning_rate": 6.226075067602142e-05,
       "loss": 0.4101614475250244,
       "step": 3100
+    },
+    {
+      "epoch": 1.2735742807412715,
+      "grad_norm": 0.19505725800991058,
+      "learning_rate": 6.16474237297412e-05,
+      "loss": 0.4245493412017822,
+      "step": 3110
+    },
+    {
+      "epoch": 1.277669704105662,
+      "grad_norm": 0.2136741727590561,
+      "learning_rate": 6.103578367020859e-05,
+      "loss": 0.3775672435760498,
+      "step": 3120
+    },
+    {
+      "epoch": 1.2817651274700523,
+      "grad_norm": 0.15684273838996887,
+      "learning_rate": 6.042585739959319e-05,
+      "loss": 0.4015648365020752,
+      "step": 3130
+    },
+    {
+      "epoch": 1.2858605508344425,
+      "grad_norm": 0.19410577416419983,
+      "learning_rate": 5.981767174468584e-05,
+      "loss": 0.357032036781311,
+      "step": 3140
+    },
+    {
+      "epoch": 1.2899559741988327,
+      "grad_norm": 0.22308309376239777,
+      "learning_rate": 5.921125345571883e-05,
+      "loss": 0.37316844463348386,
+      "step": 3150
+    },
+    {
+      "epoch": 1.294051397563223,
+      "grad_norm": 0.19800947606563568,
+      "learning_rate": 5.860662920518909e-05,
+      "loss": 0.4194052219390869,
+      "step": 3160
+    },
+    {
+      "epoch": 1.2981468209276135,
+      "grad_norm": 0.21715150773525238,
+      "learning_rate": 5.8003825586685245e-05,
+      "loss": 0.4099376678466797,
+      "step": 3170
+    },
+    {
+      "epoch": 1.3022422442920036,
+      "grad_norm": 0.19309502840042114,
+      "learning_rate": 5.740286911371786e-05,
+      "loss": 0.4126273632049561,
+      "step": 3180
+    },
+    {
+      "epoch": 1.306337667656394,
+      "grad_norm": 0.21837358176708221,
+      "learning_rate": 5.6803786218553225e-05,
+      "loss": 0.39436218738555906,
+      "step": 3190
     }
   ],
   "logging_steps": 10,
@@ -2197,7 +2260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3931908410302874e+17,
+  "total_flos": 5.538904590800609e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null