Training in progress, step 3444, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f49bd87a32773e2d42cb4615b685c1eb817d700138b2d5557b0704a73beed9
+oid sha256:e6a94cba7ea87fbf021935c11f8615cd03a048a31a588040545f87a93c2e3a95
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6892383a25460708a4fb2cced1a1cc86b3515767ba3d2638589b16c2ff90205
+oid sha256:06b5081540569441715547ff43f37b97bf715f723d6d2b5b311557c590442d39
 size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654245017c7e7b38c8d54c25faf5ec110aeb4d430b027453b43bf66aeaea920e
+oid sha256:cd742063009ee981d5848fe9bf7a543d4a8cbaadadaaa45de6889369e1d15c73
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3198eff19aee3f3613e93dee113ccfe4fd29cbc3d20274d9a676926712ec98e
+oid sha256:1cf281356dd7e1d35a833a56918425e18fa9ac5fc5fd3a71e84ab0822f7136df
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.375959864851029,
+  "epoch": 1.4103614211119075,
   "eval_steps": 500,
-  "global_step": 3360,
+  "global_step": 3444,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2360,6 +2360,62 @@
       "learning_rate": 4.693123018745226e-05,
       "loss": 0.33828010559082033,
       "step": 3360
+    },
+    {
+      "epoch": 1.3800552882154193,
+      "grad_norm": 0.221778005361557,
+      "learning_rate": 4.637029211027704e-05,
+      "loss": 0.40473618507385256,
+      "step": 3370
+    },
+    {
+      "epoch": 1.3841507115798095,
+      "grad_norm": 0.21674896776676178,
+      "learning_rate": 4.581171286404134e-05,
+      "loss": 0.3835453987121582,
+      "step": 3380
+    },
+    {
+      "epoch": 1.3882461349442,
+      "grad_norm": 0.21298988163471222,
+      "learning_rate": 4.525551701710592e-05,
+      "loss": 0.4054240703582764,
+      "step": 3390
+    },
+    {
+      "epoch": 1.39234155830859,
+      "grad_norm": 0.2046922743320465,
+      "learning_rate": 4.470172903300088e-05,
+      "loss": 0.3975031852722168,
+      "step": 3400
+    },
+    {
+      "epoch": 1.3964369816729805,
+      "grad_norm": 0.19061703979969025,
+      "learning_rate": 4.415037326934962e-05,
+      "loss": 0.38409886360168455,
+      "step": 3410
+    },
+    {
+      "epoch": 1.4005324050373709,
+      "grad_norm": 0.16538187861442566,
+      "learning_rate": 4.36014739767977e-05,
+      "loss": 0.38607375621795653,
+      "step": 3420
+    },
+    {
+      "epoch": 1.404627828401761,
+      "grad_norm": 0.17867620289325714,
+      "learning_rate": 4.305505529794599e-05,
+      "loss": 0.39211108684539797,
+      "step": 3430
+    },
+    {
+      "epoch": 1.4087232517661512,
+      "grad_norm": 0.22965748608112335,
+      "learning_rate": 4.251114126628882e-05,
+      "loss": 0.47037758827209475,
+      "step": 3440
     }
   ],
   "logging_steps": 10,
@@ -2379,7 +2435,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.830463432210227e+17,
+  "total_flos": 5.97610359630803e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null