Training in progress, step 274, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad73acc7a44c1fcd562883c85272c2e33e24df2154f4b3d1668ef117da46401
+oid sha256:5e419c6b9165e42320f1a7472a3846377e8c91119c563d4005aff51a69aa4685
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064b2a9e45b619870f65440ad9ebda6135d621bd81ea4fa5c9d2073e6847a8a5
+oid sha256:28cdb21230b7824d55a4297c2ab3edbca84bc6dbaeedc644b7618d78672df3e0
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d3048c859719401ed6523107918b9f1d6ac0f3668115efc907a5a4c443c081
+oid sha256:70901b94b4e1e6b99201989f00c77c6a02ae46cc48fbef26b5bd41545d57275c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7352537722908093,
+  "epoch": 0.7517146776406035,
   "eval_steps": 500,
-  "global_step": 268,
+  "global_step": 274,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1883,6 +1883,48 @@
       "learning_rate": 7.272727272727273e-05,
       "loss": 1.2259,
       "step": 268
+    },
+    {
+      "epoch": 0.7379972565157751,
+      "grad_norm": 0.15109026432037354,
+      "learning_rate": 7.196969696969698e-05,
+      "loss": 1.2103,
+      "step": 269
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.15917524695396423,
+      "learning_rate": 7.121212121212121e-05,
+      "loss": 1.1641,
+      "step": 270
+    },
+    {
+      "epoch": 0.7434842249657064,
+      "grad_norm": 0.16973435878753662,
+      "learning_rate": 7.045454545454546e-05,
+      "loss": 1.1128,
+      "step": 271
+    },
+    {
+      "epoch": 0.7462277091906722,
+      "grad_norm": 0.16686728596687317,
+      "learning_rate": 6.96969696969697e-05,
+      "loss": 1.1665,
+      "step": 272
+    },
+    {
+      "epoch": 0.7489711934156379,
+      "grad_norm": 0.16650721430778503,
+      "learning_rate": 6.893939393939395e-05,
+      "loss": 1.1626,
+      "step": 273
+    },
+    {
+      "epoch": 0.7517146776406035,
+      "grad_norm": 0.1571473777294159,
+      "learning_rate": 6.818181818181818e-05,
+      "loss": 1.1167,
+      "step": 274
     }
   ],
   "logging_steps": 1,
@@ -1902,7 +1944,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3135793961210266e+17,
+  "total_flos": 3.387494336322847e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null