Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d8b734641afcfe9a7cd1d6da80ce228471ca86cb97a58be3140fb19c7c422b
+oid sha256:6a27d48d34b8ccad96e402eb4f94ec667bf372ecd65cd4746cd18d89a3ee31ae
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af57cfd714c0b7ab3f23e52af9a802dba247a088b573f019e99a8faa44990fd
+oid sha256:96bc579cba2ba220a43642dd36ae216045b6c492a0b978a80ccd6cf9f5f30491
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a624c44263afb14378edac47214ec2c9da213c34fbe04289aef21a2b801784d7
+oid sha256:1d0ff9a7184dfef904a073aa76234f185ca283c0a479c1a8c903692aec73c4aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9517535082d3856241bb82290abcfc6ba4e812ae46ea90b0ce2e739b6902210d
+oid sha256:68bbf668b8239771e72cdecbaae5a40e09f6e926879b6dffd5fd09ed3de5395e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.156275976724855,
+  "epoch": 4.364089775561097,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -179,6 +179,13 @@
       "learning_rate": 3.381546134663342e-06,
       "loss": 0.3036,
       "step": 10000
+    },
+    {
+      "epoch": 4.364089775561097,
+      "grad_norm": 0.7941420078277588,
+      "learning_rate": 2.550290939318371e-06,
+      "loss": 0.3129,
+      "step": 10500
     }
   ],
   "logging_steps": 500,
@@ -198,7 +205,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.435587979083776e+16,
+  "total_flos": 2.557379557195776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null