Training in progress, step 185, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d07a125acf118b1129c100c6b14f4c3ec600c5d9bb5bd7f070b8a63141f90b3
+oid sha256:eb723e62fb82cd4b78aa0cca1ace2861019e61e678760115be31dba5ad1696fb
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ecfeeafecbec2a3a15990a51ba72578f9c86b9c0d8af9cca4c5141999cd257
+oid sha256:69404c049d0fc9a8dcd6c745ff05d502bd435ce6e5e88f9d263276b6c3e98a21
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6362b09e58588bf4bb998fe89b4e73cad56d76d2d176c7abc6cfafe3bad8a094
+oid sha256:15f3f424f914fd255fa1ff6a73e197c5d3690a5830ea92f8fc6fedd09ca07699
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c990948ce2aaf07d64c7544604482e458e5281aa73955448bb3e7dee4b1367
+oid sha256:31cc4c125027b06153274d1c1fcc2291ff49e04af7d8c2cae65dd480bfd90a0c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08802494039977994,
+  "epoch": 0.09047007763310716,
   "eval_steps": 34,
-  "global_step": 180,
+  "global_step": 185,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1315,6 +1315,41 @@
       "learning_rate": 6.75277705956443e-06,
       "loss": 8.2317,
       "step": 180
+    },
+    {
+      "epoch": 0.08851396784644538,
+      "grad_norm": Infinity,
+      "learning_rate": 6.1011639384943585e-06,
+      "loss": 8.8381,
+      "step": 181
+    },
+    {
+      "epoch": 0.08900299529311083,
+      "grad_norm": Infinity,
+      "learning_rate": 5.481617183918053e-06,
+      "loss": 9.8422,
+      "step": 182
+    },
+    {
+      "epoch": 0.08949202273977627,
+      "grad_norm": Infinity,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 8.9866,
+      "step": 183
+    },
+    {
+      "epoch": 0.08998105018644172,
+      "grad_norm": Infinity,
+      "learning_rate": 4.339558049955927e-06,
+      "loss": 8.7644,
+      "step": 184
+    },
+    {
+      "epoch": 0.09047007763310716,
+      "grad_norm": Infinity,
+      "learning_rate": 3.817435682718096e-06,
+      "loss": 9.5396,
+      "step": 185
     }
   ],
   "logging_steps": 1,
@@ -1334,7 +1369,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.9680634167230464e+17,
+  "total_flos": 4.078287400520909e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null