Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc941af358c41fdacb4643bbfec2e2f6cedd8ccebc8d32a056a9fe1f0067a572
+oid sha256:9c0b9b66eb18cf0b855508e06ba01803083db1d16dbf2b0fffd8f4d3ca32afc1
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171a625f2f946875f946841d317f73ae901bc37acb6617c511d58b5b274af3c6
+oid sha256:b1ee4c082d32f2e525bbdd97fd0fb1392f16516055373773711cc8ff57d3b7d8
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a97cd7f079d7f12ed4724344a7cbd6b5515d4008435f2e5a63f0ce71a90c202c
+oid sha256:92cb433dd7b6353454fd7a1a5cd6ae3809d9ab1ab0b7913e6509216203ba9cb2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2139917695473251,
+  "epoch": 0.2222222222222222,
   "eval_steps": 500,
-  "global_step": 78,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,27 @@
       "learning_rate": 0.00015600000000000002,
       "loss": 1.2942,
       "step": 78
+    },
+    {
+      "epoch": 0.2167352537722908,
+      "grad_norm": 0.09426167607307434,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.333,
+      "step": 79
+    },
+    {
+      "epoch": 0.2194787379972565,
+      "grad_norm": 0.09674811363220215,
+      "learning_rate": 0.00016,
+      "loss": 1.3242,
+      "step": 80
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.09802138805389404,
+      "learning_rate": 0.000162,
+      "loss": 1.3322,
+      "step": 81
     }
   ],
   "logging_steps": 1,
@@ -572,7 +593,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.669833466976666e+16,
+  "total_flos": 1.0050886434935194e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null