Training in progress, step 31000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b4d2a21ab34ea5aae19f2c79c17d535d0eceb21e9bd3fbe132c0c6743fbd74
+oid sha256:35881b4a958bf056508d114860b14084addd8682c5b35498eb4cbf8f6a42ffcc
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60601e0df9ec0d20e49569fddd22a460360511cad0bf70986d2e0dfe2c6fc5ac
+oid sha256:9a03972f1e2c45bae275800dd72230f94d0382cbf9d6d293e189b2e288ac62bf
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfe40bf67dcc41ade516e25138c73f55e1a79032c0542ad6be33784e59a5c69
+oid sha256:5d5a75fa06d8e0567428171895f2f5be669b2393bf43f572fee60b1f39d5db02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6148692faa22908e20b6fbcdb986515b0d89f409366c21a08301b9100cfff4f
+oid sha256:4cadac78638c6cb012c738c824827d4d4609dcfa94ea2fed086f7884c5c610aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.033333333333333,
+  "epoch": 2.066666666666667,
   "eval_steps": 500,
-  "global_step": 30500,
+  "global_step": 31000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2158,6 +2158,41 @@
       "learning_rate": 6.4493333333333345e-06,
       "loss": 0.0544,
       "step": 30500
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.12454479187726974,
+      "learning_rate": 6.40488888888889e-06,
+      "loss": 0.0566,
+      "step": 30600
+    },
+    {
+      "epoch": 2.046666666666667,
+      "grad_norm": 0.18834765255451202,
+      "learning_rate": 6.360444444444445e-06,
+      "loss": 0.0523,
+      "step": 30700
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 0.14881722629070282,
+      "learning_rate": 6.316000000000001e-06,
+      "loss": 0.0505,
+      "step": 30800
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.12314546853303909,
+      "learning_rate": 6.271555555555556e-06,
+      "loss": 0.0505,
+      "step": 30900
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.18147911131381989,
+      "learning_rate": 6.2271111111111115e-06,
+      "loss": 0.046,
+      "step": 31000
     }
   ],
   "logging_steps": 100,
@@ -2177,7 +2212,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.429286264832e+16,
+  "total_flos": 7.551077842944e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null