Training in progress, step 306000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9059c7ff5ec357e1082fff881998d4d8a30eede22bba05493a66ace8dba8d5
+oid sha256:e67cb24b5c7f8f8f4375b0db04500bcc197056ffee0d9ae806c274773498fc47
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2effa5352c89b206e44ccadb69f034b726f36fc284163a218fd75ef56180b8aa
+oid sha256:a35c508ec9ef02da634fb99ba732a8522e613b658a75aaa26a9b7b7f2493e0ac
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5b6640ad93342f752a41c1124d9c323f04de5c98620a27f9e7cb09a277063e
+oid sha256:72a128c971ea8f9adfc8199f5d8881c46f465a1de9bd830d2e82fbc2fd4820cf
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb100654eb1b6490066538bef0e21e522294dc4d5c8d344077f61ada4f8578b5
+oid sha256:4e6c66490c6ad4b2efcb520faa311a87fdb2457e0dbd926b08a9eb8cc11d8971
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9327999999999999,
+  "epoch": 1.9584000000000001,
   "eval_steps": 500,
-  "global_step": 302000,
+  "global_step": 306000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4235,6 +4235,62 @@
       "learning_rate": 1.69776e-06,
       "loss": 0.2399,
       "step": 302000
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.5442044734954834,
+      "learning_rate": 1.6177600000000002e-06,
+      "loss": 0.2461,
+      "step": 302500
+    },
+    {
+      "epoch": 1.9392,
+      "grad_norm": 0.6031491756439209,
+      "learning_rate": 1.53776e-06,
+      "loss": 0.2463,
+      "step": 303000
+    },
+    {
+      "epoch": 1.9424000000000001,
+      "grad_norm": 0.6695773005485535,
+      "learning_rate": 1.4579200000000002e-06,
+      "loss": 0.2475,
+      "step": 303500
+    },
+    {
+      "epoch": 1.9456,
+      "grad_norm": 0.5614984631538391,
+      "learning_rate": 1.37792e-06,
+      "loss": 0.2442,
+      "step": 304000
+    },
+    {
+      "epoch": 1.9487999999999999,
+      "grad_norm": 0.5449358224868774,
+      "learning_rate": 1.2980800000000002e-06,
+      "loss": 0.2482,
+      "step": 304500
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.4947919249534607,
+      "learning_rate": 1.2180800000000001e-06,
+      "loss": 0.2434,
+      "step": 305000
+    },
+    {
+      "epoch": 1.9552,
+      "grad_norm": 0.5914204716682434,
+      "learning_rate": 1.13808e-06,
+      "loss": 0.2449,
+      "step": 305500
+    },
+    {
+      "epoch": 1.9584000000000001,
+      "grad_norm": 0.5385975241661072,
+      "learning_rate": 1.05808e-06,
+      "loss": 0.2484,
+      "step": 306000
     }
   ],
   "logging_steps": 500,
@@ -4254,7 +4310,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.47124226359296e+18,
+  "total_flos": 1.49072891609088e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null