Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4b588f5c69c5aa5246f293d3d9777a57b325330869d1c53c8e5f892307608d
+oid sha256:86a467661dfbddb3df49408627a9998da21495b85677a249376b994906029bdd
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fbf1bf341edb75a4a190feef85eaabd26f5ae01354f5ae1e71c8be1d4ed1cf
+oid sha256:b3b0f703d5d306039df5babc0f8a847c4fce918ba096d5abf55cfcc37fca5698
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b6593e59a746c53f1d44f025276548c083a7b206701e1c3eedf35c30b683ea
+oid sha256:726de56569df8e1f59bb119c6dba51085afe680cfab701a55fb21769d5819a96
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc459a4e56616fd7a5479951e6d72545d3fcc978945a838cd5c66c02cdd231d
+oid sha256:186a27fe70052dfbc993bf5c2067adb8b29fdda85afb7475ca3a4f0d64c3a355
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.854028664338191,
+  "epoch": 4.094905455859328,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,13 @@
       "learning_rate": 0.0008715169035573758,
       "loss": 1.0959,
       "step": 16000
+    },
+    {
+      "epoch": 4.094905455859328,
+      "grad_norm": 0.4543096125125885,
+      "learning_rate": 0.0008634867100297117,
+      "loss": 1.0903,
+      "step": 17000
     }
   ],
   "logging_steps": 1000,
@@ -138,7 +145,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.600589764094853e+17,
+  "total_flos": 1.7006183713026867e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null