Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2141320f9b8a2cd3772fb223d1131baebd71974e2bf87b6a1c24de6bf13c8fae
+oid sha256:91b9bbdd755c53c0e737d7e661686c38f23d60d1782fcbf1d45edeeba9d87b95
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee2854b2510e7dccd90f9604ed994b1eb7a8d1050daf4f2c17001c85658d2b8
+oid sha256:bfee0acd7960658f9aa003a100cb4c569de6a3bb0e0e233660c579db5df84976
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce122efa58437e9eb4167be3235ff668c46393aa7e777fe0c234b56b42a65288
+oid sha256:4ef6f9afaee6b3c66bd6603d6f0a1ae70b2f238fe9e271cbda545439817d0f6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4b192ffac4efaba4f3cd35aa1226766929983bc37c1c74305bd3d40b48b106
+oid sha256:d3fb3881e58ff0c357457e26af721d36ad38644f638c6a34d44b118fd264af5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10390689941812137,
+  "epoch": 0.20781379883624274,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 1.9311443613189252e-05,
       "loss": 0.8436,
       "step": 500
+    },
+    {
+      "epoch": 0.20781379883624274,
+      "grad_norm": 0.8393851518630981,
+      "learning_rate": 1.8618730950401776e-05,
+      "loss": 0.5316,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 608957890560000.0,
+  "total_flos": 1217915781120000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null