Training in progress, step 580, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc3759cb3eadde8f65f5a3d7697045cdf5905ba99f1c6eaf2ca3a7844ad2aca
+oid sha256:ddd8d5d17a70fc79518195b5b2e2d18e0edf35451d2de3c1d4af60412a1a30e8
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8685b80d11ca02ce5247ab56c8fdc4d82bb07cfe0c06ad76dd35d09f90963d57
+oid sha256:1105fd8323adc5ab31859ebf0c1f559487e30aa157c674ed5d23d9852296ed98
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530917c5e79645a47e31080d2f68465b75947e6f663e644f4e8388bf2a65638b
+oid sha256:48e8d93d81cb229c0956f2142d68e1f8aa0357ca11d56ce040bb137cf176e02f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e7e7df729679e04b7adacc504f1466aebac28d86d657be5afa757859f96a7b
+oid sha256:49970088ac3a5ad000c30d8106322041a0265ebced6d734c6afdb98d800f2095
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7440957618893562,
+  "epoch": 0.7505661598188289,
   "eval_steps": 386,
-  "global_step": 575,
+  "global_step": 580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4048,6 +4048,41 @@
       "learning_rate": 9.538772097304521e-05,
       "loss": 0.8442,
       "step": 575
+    },
+    {
+      "epoch": 0.7453898414752508,
+      "grad_norm": 0.7087002992630005,
+      "learning_rate": 9.537041021262072e-05,
+      "loss": 0.8004,
+      "step": 576
+    },
+    {
+      "epoch": 0.7466839210611452,
+      "grad_norm": 0.8022588491439819,
+      "learning_rate": 9.535306860451849e-05,
+      "loss": 0.9188,
+      "step": 577
+    },
+    {
+      "epoch": 0.7479780006470398,
+      "grad_norm": 0.8022916316986084,
+      "learning_rate": 9.533569616052921e-05,
+      "loss": 0.9815,
+      "step": 578
+    },
+    {
+      "epoch": 0.7492720802329343,
+      "grad_norm": 0.6670771837234497,
+      "learning_rate": 9.531829289246452e-05,
+      "loss": 0.812,
+      "step": 579
+    },
+    {
+      "epoch": 0.7505661598188289,
+      "grad_norm": 0.7644294500350952,
+      "learning_rate": 9.530085881215705e-05,
+      "loss": 0.8092,
+      "step": 580
     }
   ],
   "logging_steps": 1,
@@ -4067,7 +4102,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.428138737238016e+17,
+  "total_flos": 6.484035595822694e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null