Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0e1101a7928c3bdee8510a8c27f892c295133ceff3f596bea16c69b8889147
+oid sha256:f10dd57fcd736d65d260ba835b7c77d356de5997eccf0f1f5adde9a6c1fb79ca
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767267c33ba45a25fe2e81d5c46be66aa26ea56509e863c6bf768b57469df4e0
+oid sha256:6343b146a693516c9b46c66a077b7f935cb841637dd5341caeb48b69ad74ca7e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccb60052eef72298bae34a53cf15b570d1ea8c23c2be486da135e9020a2e721
+oid sha256:3e0d20d58bd89e713c08b07c8c7060ac9cf564e52b782f77021cead0bd733f4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301b38b5450010c3333e2f3ff82e4d11c803056aaea7e9900505a4d6beb8ec24
+oid sha256:acf23b21acd31c1d3464aaff618f82d2724f1b36ad9868a85d99877306c53404
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2468827930174564,
+  "epoch": 1.4546965918536992,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -57,6 +57,13 @@
       "learning_rate": 1.5015793848711555e-05,
       "loss": 0.3857,
       "step": 3000
+    },
+    {
+      "epoch": 1.4546965918536992,
+      "grad_norm": 0.4072982668876648,
+      "learning_rate": 1.4184538653366584e-05,
+      "loss": 0.3754,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
@@ -76,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7306885728829440.0,
+  "total_flos": 8524801509949440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null