Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43947f7dff9276008c5ac3a3bb1a1f78045f6daf3ab26be1df501497ecb5a13c
+oid sha256:893983e61e005312c4a5a5937ac7d9e97a84f157f2d2506651c26610d9fc5649
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659ad3bb4e988117552420945713bf112a7f8dc606586d8b6b10aff068671da7
+oid sha256:f8c6f9fb1ab37c26c8e9cd8f06ff85c9304df7bb97167c11edaec7366d9b2dd7
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f8cb1d04d85cb700bc0a165ddfffe857827b34a325813bd7675c23cb4f568a
+oid sha256:81366beb45812d30c24b5a5034071dc5850a14e0029b0be5806b5186ffb17322
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac8c1d8a81c24b85fd218732e29aedf5ad8d51951edcda5923c223ea804a4dd
+oid sha256:976d1f52844e987390213cc75aaff01e7bbae8d7552dcf3147571e784e111d4d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1820448877805485,
+  "epoch": 2.28595178719867,
   "eval_steps": 500,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,13 @@
       "learning_rate": 5.459961208090885e-06,
       "loss": 0.3369,
       "step": 10500
+    },
+    {
+      "epoch": 2.28595178719867,
+      "grad_norm": 0.7700533270835876,
+      "learning_rate": 4.767248545303408e-06,
+      "loss": 0.3387,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -189,7 +196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.278689778597888e+16,
+  "total_flos": 1.339585567653888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null