Training in progress, step 145, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2e0910ee8ff17a681acdd56f9074e96fa82a916a8f3239bf3f1f3cd80ce465
+oid sha256:c6232ed48b9c18e085faf4119484b73bc66018b47f3bd50b5a6e541e5ccc1e03
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e25365edc54422e82cbac4c671e2435e8bbd2900af3e9044725a0b51ab79a1
+oid sha256:b26583c118f37f0f901f941c1caddee16c708cd7a19dc546b58c02f36d2f5862
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3620fd05065514f79fda6c0faf379ce93ec4350e71e2f2104721a44e9230ff6
+oid sha256:b362eff1a75d9bf020525cb57285e4b861253ed25664be12ca93f1935aca2a48
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671828e69cd8fd42106344a5797cbc78f701a434a6386d9dfacd16451ba179aa
+oid sha256:be04ea4bc9f159499b4a7b296b15e0c0e5c54743663ee8550a26340683f89e32
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06846384253316218,
+  "epoch": 0.0709089797664894,
   "eval_steps": 34,
-  "global_step": 140,
+  "global_step": 145,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1027,6 +1027,41 @@
       "learning_rate": 5.542616442234618e-05,
       "loss": 10.4222,
       "step": 140
+    },
+    {
+      "epoch": 0.06895286997982762,
+      "grad_norm": Infinity,
+      "learning_rate": 5.37796116459687e-05,
+      "loss": 9.8649,
+      "step": 141
+    },
+    {
+      "epoch": 0.06944189742649307,
+      "grad_norm": Infinity,
+      "learning_rate": 5.214884308987136e-05,
+      "loss": 10.3785,
+      "step": 142
+    },
+    {
+      "epoch": 0.06993092487315851,
+      "grad_norm": Infinity,
+      "learning_rate": 5.0534415660022136e-05,
+      "loss": 9.2483,
+      "step": 143
+    },
+    {
+      "epoch": 0.07041995231982395,
+      "grad_norm": Infinity,
+      "learning_rate": 4.893688068190932e-05,
+      "loss": 10.5841,
+      "step": 144
+    },
+    {
+      "epoch": 0.0709089797664894,
+      "grad_norm": Infinity,
+      "learning_rate": 4.735678371226441e-05,
+      "loss": 8.9077,
+      "step": 145
     }
   ],
   "logging_steps": 1,
@@ -1046,7 +1081,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.086271546340147e+17,
+  "total_flos": 3.1964955301380096e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null