Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c4e341fea77f4eb866b258e42597c53a7549b9bb0f89e2f5fac421899e13f3
+oid sha256:9d4b588f5c69c5aa5246f293d3d9777a57b325330869d1c53c8e5f892307608d
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18386c57662a786d5a583e23b6d7f2562bd2214a160c708fcca3a5d47d2d6a5e
+oid sha256:87fbf1bf341edb75a4a190feef85eaabd26f5ae01354f5ae1e71c8be1d4ed1cf
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ac2d3dc8bf456762ba0b5fc4335d4ddbfc02b255c8b0104d3523ee9fd194cb
+oid sha256:b3b6593e59a746c53f1d44f025276548c083a7b206701e1c3eedf35c30b683ea
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173718d11a1787bf6666e53d794b4477dfea7dd9e0c678e2e15dd29149b85460
+oid sha256:5bc459a4e56616fd7a5479951e6d72545d3fcc978945a838cd5c66c02cdd231d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.613151872817054,
+  "epoch": 3.854028664338191,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,13 @@
       "learning_rate": 0.0008795470970850398,
       "loss": 1.11,
       "step": 15000
+    },
+    {
+      "epoch": 3.854028664338191,
+      "grad_norm": 0.43153703212738037,
+      "learning_rate": 0.0008715169035573758,
+      "loss": 1.0959,
+      "step": 16000
     }
   ],
   "logging_steps": 1000,
@@ -131,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5005509992893645e+17,
+  "total_flos": 1.600589764094853e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null