Training in progress, step 1528, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6fb4957fada6ecab50fa08c8a31d022817b69beb5fe802008a63553b4e3af87
+oid sha256:d6b9d2acbd0f168009f26b7ef13d571b89b41526bebf47dfd26aa64eccffacf7
 size 557912620

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bf0a653f421c33e3ba0755c2101d46686890bbdb05dfa9238d9bd8d0bdd825
+oid sha256:a4b934f68933cf5a165e3dc8c0b8ed15087c86623719bd958ef589336c02b179
 size 1115579834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e25a375aea0986e1ff49c229feb71c134d7d2c78e3f6bc24f04319b58e4105c
+oid sha256:edf4cbadc64285734eaa93ad7c58796388c4125fa5554ad0cc36602591473bf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7c4028863b38382c81b1e563b248dc15055fba98c7622e800df339f6218bc1
+oid sha256:7f523988ba2de8054dc46a890358ab72870b8513bf3f43057aee303c531f01bf
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6544502617801047,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1528,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,20 @@
       "learning_rate": 1.731020942408377e-05,
       "loss": 0.0004,
       "step": 1000
+    },
+    {
+      "epoch": 0.8180628272251309,
+      "grad_norm": 0.03750693053007126,
+      "learning_rate": 9.129581151832461e-06,
+      "loss": 0.0003,
+      "step": 1250
+    },
+    {
+      "epoch": 0.981675392670157,
+      "grad_norm": 0.022292787209153175,
+      "learning_rate": 9.489528795811518e-07,
+      "loss": 0.0004,
+      "step": 1500
     }
   ],
   "logging_steps": 250,
@@ -50,12 +64,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4877891665920000.0,
+  "total_flos": 7452961163182080.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null