Training in progress, step 220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9766f34d5fd8118f8b13baef08d58f9b128b6e836dfa00f87f22281d2037639d
+oid sha256:205d6e49f052c68e31e4b4d48cfda1756d56bdd8b8f793f6885d29be396c52c7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381aca70bbccce8e9502373e40bfbd03e15395ec8e91ff949ac503e7ef5d6a5a
+oid sha256:ce6b050b1c5edf6aec30582163726e1425f3b8a84ebc8293985d0a47f0b28b43
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5502029eee065fc820abe1436c0ce76c27cd136332c2b1740a3333c5e65413a3
+oid sha256:bc86b00df74af7c3ae7c1114b70673a81bf15a56d4e6f0edaf89c595f91d6339
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1929499981cc6333ee109a44552912f6f3059a331b019ddd14fcca42c15184
+oid sha256:67b93879c4e6775563c05d16d872585eaef843648c94363ef6e0e8ca9fabb503
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2782271109673245,
+  "epoch": 0.2846975088967972,
   "eval_steps": 386,
-  "global_step": 215,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1520,6 +1520,41 @@
       "learning_rate": 9.953795138672291e-05,
       "loss": 0.9093,
       "step": 215
+    },
+    {
+      "epoch": 0.279521190553219,
+      "grad_norm": 1.162850022315979,
+      "learning_rate": 9.95323425992942e-05,
+      "loss": 1.0372,
+      "step": 216
+    },
+    {
+      "epoch": 0.28081527013911356,
+      "grad_norm": 0.9785279631614685,
+      "learning_rate": 9.952670013445913e-05,
+      "loss": 0.8818,
+      "step": 217
+    },
+    {
+      "epoch": 0.28210934972500806,
+      "grad_norm": 0.9386499524116516,
+      "learning_rate": 9.9521023996054e-05,
+      "loss": 0.8711,
+      "step": 218
+    },
+    {
+      "epoch": 0.2834034293109026,
+      "grad_norm": 0.8620506525039673,
+      "learning_rate": 9.951531418793812e-05,
+      "loss": 1.011,
+      "step": 219
+    },
+    {
+      "epoch": 0.2846975088967972,
+      "grad_norm": 0.9523435831069946,
+      "learning_rate": 9.950957071399357e-05,
+      "loss": 0.8541,
+      "step": 220
     }
   ],
   "logging_steps": 1,
@@ -1539,7 +1574,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4035649191411712e+17,
+  "total_flos": 2.4594617777258496e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null