Training in progress, step 575, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4584dc7b0cb76f460c8d711cb91e7a00115c4b8b6e4c5f64c026bab2b1ffec56
+oid sha256:8dc3759cb3eadde8f65f5a3d7697045cdf5905ba99f1c6eaf2ca3a7844ad2aca
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e34737a84c54468cc2ddb658609e3abb120334092064eaaf03c2dd0f9ccf8bfa
+oid sha256:8685b80d11ca02ce5247ab56c8fdc4d82bb07cfe0c06ad76dd35d09f90963d57
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31720c6202686d6b213f1d4f529251465f67b801085538ab4bd286d72ff5e4d
+oid sha256:530917c5e79645a47e31080d2f68465b75947e6f663e644f4e8388bf2a65638b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac34b28e1ee591b304cbd862bb43f437e9105f534e9b2ad7a541d74d74af47f
+oid sha256:95e7e7df729679e04b7adacc504f1466aebac28d86d657be5afa757859f96a7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7376253639598835,
+  "epoch": 0.7440957618893562,
   "eval_steps": 386,
-  "global_step": 570,
+  "global_step": 575,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4013,6 +4013,41 @@
       "learning_rate": 9.54738116487959e-05,
       "loss": 0.8114,
       "step": 570
+    },
+    {
+      "epoch": 0.7389194435457781,
+      "grad_norm": 0.9224253296852112,
+      "learning_rate": 9.545665530288612e-05,
+      "loss": 0.8829,
+      "step": 571
+    },
+    {
+      "epoch": 0.7402135231316725,
+      "grad_norm": 0.8720259666442871,
+      "learning_rate": 9.543946805065992e-05,
+      "loss": 0.9658,
+      "step": 572
+    },
+    {
+      "epoch": 0.7415076027175671,
+      "grad_norm": 0.5992270708084106,
+      "learning_rate": 9.542224990380304e-05,
+      "loss": 0.8167,
+      "step": 573
+    },
+    {
+      "epoch": 0.7428016823034617,
+      "grad_norm": 0.7595481276512146,
+      "learning_rate": 9.540500087402222e-05,
+      "loss": 0.9002,
+      "step": 574
+    },
+    {
+      "epoch": 0.7440957618893562,
+      "grad_norm": 0.8269613981246948,
+      "learning_rate": 9.538772097304521e-05,
+      "loss": 0.8442,
+      "step": 575
     }
   ],
   "logging_steps": 1,
@@ -4032,7 +4067,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.372241878653338e+17,
+  "total_flos": 6.428138737238016e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null