Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9ae7e86bbc77dbce22ca2c90f22880719186ccf1df5b938440f4fba479e8f8
+oid sha256:e22260d65676f915e4958d20419e6e1670fca3c9554454b41e00a01f59036dc8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f073df4c55287ce71ca924a294e38b1ab7cc164a34073772713039d245568f
+oid sha256:10f0faeafff597195ee7f26d52a60f75e5adf20ceaeaf10787f20bf70ee638b4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343cbf433a49823c26aa4dd9334fa3e204370732996c7bb60db1a7158c5badde
+oid sha256:f2b67c05f37b4606592392a2a2e3555caf2c285ee68c702566e4cb3524218561
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b8133c0078c9773a22c7a49b5547dc88d96e16d710eff8078381e482ecc029
+oid sha256:fcc9e973441a5ba67c47763b37bce78dd415347becadca5e0c593823cb37a70d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8703241895261846,
+  "epoch": 1.9742310889443058,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -141,6 +141,13 @@
       "learning_rate": 7.536713771127737e-06,
       "loss": 0.3492,
       "step": 9000
+    },
+    {
+      "epoch": 1.9742310889443058,
+      "grad_norm": 1.3331661224365234,
+      "learning_rate": 6.844001108340261e-06,
+      "loss": 0.3386,
+      "step": 9500
     }
   ],
   "logging_steps": 500,
@@ -160,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.096063307218944e+16,
+  "total_flos": 1.156959096274944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null