Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6889ce869137e3d279293e3ffff9f22039ae191700c8265421901a0e6021c3f
+oid sha256:026a8181b8fa63af3c342319007cfd5ca60318bc824e266b0a9d4743b34255b1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd548064b42e9bc13e75e6e88004e41384e0a954cdd111e6655e7c700709f114
+oid sha256:0d56121245376a058eacc2a33be5ad0373905095531af4bc92dccea2183d72cf
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2beb5f3eae46760fe93c244c16d7260ed6d437cc6536ace16b095ba9f37e6d
+oid sha256:f2f8cb1d04d85cb700bc0a165ddfffe857827b34a325813bd7675c23cb4f568a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9fdfaf4edd9a546b1d0f37b5f883b42cacfc782c11efcb3c34d2675d15c08f7
+oid sha256:6ac8c1d8a81c24b85fd218732e29aedf5ad8d51951edcda5923c223ea804a4dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0781379883624274,
+  "epoch": 2.1820448877805485,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,13 @@
       "learning_rate": 6.151288445552786e-06,
       "loss": 0.3294,
       "step": 10000
+    },
+    {
+      "epoch": 2.1820448877805485,
+      "grad_norm": 1.1987346410751343,
+      "learning_rate": 5.459961208090885e-06,
+      "loss": 0.3377,
+      "step": 10500
     }
   ],
   "logging_steps": 500,
@@ -182,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.217793989541888e+16,
+  "total_flos": 1.278689778597888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null