Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2295db7c3787f041a0d921ea38ba92a0c96ad0c119ea49905329ab11b00ee672
+oid sha256:6297606052a4277aa0a1e4619bd299b3833e32268284b14aa730349c00e330a7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20ad2af010c8f7b9e90d434aec4381b6abebb4e0ef496dc53a2987bcfd3c4fa
+oid sha256:2366e26bc61fe9363daef1823fa6a4707c5d0477f89a365a7728b80458335ff1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b70a97ff18a63ef26fe23f248a99f7e6c8585ce19a9713e037357e85de43714
+oid sha256:2d95327014bf0e992837899fdc63d1e3049ea8baca978228506724df9c716834
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be04ea4bc9f159499b4a7b296b15e0c0e5c54743663ee8550a26340683f89e32
+oid sha256:5a946cb282348d3fba8c242cd51f3b90b3dccbd24720ee6b6397a7e493e7b92c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0709089797664894,
+  "epoch": 0.07335411699981662,
   "eval_steps": 34,
-  "global_step": 145,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1062,6 +1062,41 @@
       "learning_rate": 4.735678371226441e-05,
       "loss": 0.8951,
       "step": 145
+    },
+    {
+      "epoch": 0.07139800721315484,
+      "grad_norm": 0.4603347182273865,
+      "learning_rate": 4.5794664352755055e-05,
+      "loss": 1.0377,
+      "step": 146
+    },
+    {
+      "epoch": 0.07188703465982028,
+      "grad_norm": 0.28372839093208313,
+      "learning_rate": 4.425105606571145e-05,
+      "loss": 1.008,
+      "step": 147
+    },
+    {
+      "epoch": 0.07237606210648573,
+      "grad_norm": 0.29044821858406067,
+      "learning_rate": 4.272648599194948e-05,
+      "loss": 1.0118,
+      "step": 148
+    },
+    {
+      "epoch": 0.07286508955315117,
+      "grad_norm": 0.3254542350769043,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0088,
+      "step": 149
+    },
+    {
+      "epoch": 0.07335411699981662,
+      "grad_norm": 0.3154352605342865,
+      "learning_rate": 3.973653636207437e-05,
+      "loss": 1.0273,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -1081,7 +1116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.436483583547802e+17,
+  "total_flos": 6.658431293325312e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null