Training in progress, step 443, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84e019c8851cde8bbc3291912c02b0d372f753097e404cd9c63df3635876d58
+oid sha256:f1cb3584a29e18bec768b8e7b922394b14eb16d5a59df96581aa6e806cd203c0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb16128ba3713943c32c15e444ff5b9d0639d313830202e6e343341c474be781
+oid sha256:51a033999582f74f2801deebf3db478f4ad5fb573b14ddd95f433732cc79b0b9
 size 85723732

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bde99108f092870a3ddeadad368065f1715b17c0e73ecda20ac6b84eb7df46
+oid sha256:37da11d39eb35aed0c8ad8207c512f99ead2ccb4dca8a51d03b958e80a004672
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62fb05d1751019ac24743a26e17e60ff4857e4af1f72362a4b410a6c8410a65b
+oid sha256:f0a6fa1f8ea24e79ddc54d54c9b1eebadb52949e41e7f120fa0737819f774d79
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54547a23ea029fe03b5f58871d4527a748e7ac8f837926dd1a6e08b721fbdc33
+oid sha256:e724795976531e687125fbb945603a96f2112de8f393fc6fa4a9b74f9ac8e79e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef39a40db1a483262af7570836839950da73fbe882edbfe93922ade4768db34
+oid sha256:1edd3582e68db638a33154dba95f3473466b2e81ca61ce580cb51b83a6e90aee
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8323834fccc4192732a390e4554f47c9681faaee6040082de0c2920fe02fd450
+oid sha256:9f430f59a9990175ce86df7bc8287717036151aba66a7f1f929e5118bcddc0e6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9937888198757764,
+  "epoch": 1.0005646527385659,
   "eval_steps": 222,
-  "global_step": 440,
+  "global_step": 443,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3103,6 +3103,27 @@
       "learning_rate": 1.3018570910466877e-08,
       "loss": 1.1954,
       "step": 440
+    },
+    {
+      "epoch": 0.9960474308300395,
+      "grad_norm": 0.574373185634613,
+      "learning_rate": 5.786171016708419e-09,
+      "loss": 1.598,
+      "step": 441
+    },
+    {
+      "epoch": 0.9983060417843026,
+      "grad_norm": 0.6945062875747681,
+      "learning_rate": 1.446563679641244e-09,
+      "loss": 1.4279,
+      "step": 442
+    },
+    {
+      "epoch": 1.0005646527385659,
+      "grad_norm": 0.6715332865715027,
+      "learning_rate": 0.0,
+      "loss": 1.5682,
+      "step": 443
     }
   ],
   "logging_steps": 1,
@@ -3117,12 +3138,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.6129270118945915e+18,
+  "total_flos": 2.630732306700042e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null