Training in progress, step 4740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99faddfad100fa77c0039f881c84ac5f3a3a476e17a63ba466ba08fe8ab8e4c
+oid sha256:8d77bee8e521431d0d810269afca006ef1827174939871728823f4302637331d
 size 678616072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50c75c95f9950fcf39e3323c3040ae8a2ba627959291a9b84e2e2ebccac1cc3
+oid sha256:cd8a49ff38db4a28ca2cd50fd6b91f6e6123e2285bb7a1642faf86e84ac899d7
 size 35918620

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc5e30f0122c3006101bb791664dadef26bc6297649ce424c7f6635c0291cc9e
+oid sha256:dda5d5e3fb4873072a3f6c6dbcb5ae3abb4df64a040f016331e928413ed9ae3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf353364c20b461a84ee85e28a511189bdf113495f91172acf4273106ef6546
+oid sha256:0087a623fb1ae91ceff851544989b0b5e0ae3009ea2753b5d119d172a1937c7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9493670886075949,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 4740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,20 @@
       "learning_rate": 2.830188679245283e-06,
       "loss": 2.609,
       "step": 4500
+    },
+    {
+      "epoch": 0.9704641350210971,
+      "grad_norm": 4.100802898406982,
+      "learning_rate": 1.650943396226415e-06,
+      "loss": 2.6422,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9915611814345991,
+      "grad_norm": 3.709977149963379,
+      "learning_rate": 4.7169811320754717e-07,
+      "loss": 2.6155,
+      "step": 4700
     }
   ],
   "logging_steps": 100,
@@ -336,12 +350,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.335847845888e+17,
+  "total_flos": 1.406870423027712e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null