Training in progress, step 18500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c271689f6760d4359c2a43653eb4d2901456cbdb4b87714c22ec9cdaa2c8b8e
+oid sha256:bfa8b32014bbb1116102bb096f351b477c375f02a76f56941cd43b6b2b8c9ae0
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b2573858366c51da080dc52026b5cf706984e6769263fae62f35276ad423d25
+oid sha256:24c06d2ce08030ea9353adcf0c618c2748ba4afafcd7e2ef1fa5088554e20156
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265f7ddb321b2fa01d3a22602c4d8e894508ea8d4458f230512f39344ac67fcf
+oid sha256:40162c830f5df6b739cc1f24fd1ff7e4f55f1a27766e6deeff7911f41b300f3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944535d8118858ad045305f7f05f43c95ec4aaef08aedf918a1fec60acb21f30
+oid sha256:b23d12d924a2c5ac71a2463338c282c759dd6e8f289f7165dd510cc1f6cd61fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2,
+  "epoch": 1.2333333333333334,
   "eval_steps": 500,
-  "global_step": 18000,
+  "global_step": 18500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1275,6 +1275,41 @@
       "learning_rate": 1.2002222222222225e-05,
       "loss": 0.0591,
       "step": 18000
+    },
+    {
+      "epoch": 1.2066666666666666,
+      "grad_norm": 0.1682252287864685,
+      "learning_rate": 1.195777777777778e-05,
+      "loss": 0.0613,
+      "step": 18100
+    },
+    {
+      "epoch": 1.2133333333333334,
+      "grad_norm": 0.11706658452749252,
+      "learning_rate": 1.1913333333333335e-05,
+      "loss": 0.0676,
+      "step": 18200
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.22997494041919708,
+      "learning_rate": 1.186888888888889e-05,
+      "loss": 0.0576,
+      "step": 18300
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.2240549921989441,
+      "learning_rate": 1.1824444444444445e-05,
+      "loss": 0.0532,
+      "step": 18400
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.10644257068634033,
+      "learning_rate": 1.178e-05,
+      "loss": 0.0657,
+      "step": 18500
     }
   ],
   "logging_steps": 100,
@@ -1294,7 +1329,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.384496812032e+16,
+  "total_flos": 4.506288390144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null