Training in progress, step 655, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3668fa34724afb7451663beb5c2888ddcb2b7ecddb13ed07d944025c27d8d3b
+oid sha256:3c5083d6fe7fc6ad40025db9a82bb1249d80b2a676e2a697dce57e7e8f6ff900
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03eb30e093c78829d55e5b35712320efbf2416ee2737745a276186c084bbdecb
+oid sha256:8d2e8d1efd498662ea22edb0b65f53bc5fc876649c55d813f1c68179c92087b6
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f89037ac2abeb6171c1ce95a77a94c808e277b9f70abf8b11f093a79735219d
+oid sha256:eaffbd51d7716e49736bc2fc49a38c283c724ab2443bef57f7bac6587bb0f07f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40d91018758ada40c1cb9514ff9b9e8ed129fd32f51a6eaa9ac898e033c2d44
+oid sha256:ed8ec70c66524f977f482912ad14e6e50f55a63de0200f38bf63dd1a0f5fc3f3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8411517308314461,
+  "epoch": 0.8476221287609188,
   "eval_steps": 386,
-  "global_step": 650,
+  "global_step": 655,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4573,6 +4573,41 @@
       "learning_rate": 9.400463314275943e-05,
       "loss": 0.9865,
       "step": 650
+    },
+    {
+      "epoch": 0.8424458104173407,
+      "grad_norm": 0.7086622714996338,
+      "learning_rate": 9.398504293135507e-05,
+      "loss": 0.8451,
+      "step": 651
+    },
+    {
+      "epoch": 0.8437398900032352,
+      "grad_norm": 0.8999130725860596,
+      "learning_rate": 9.396542281419445e-05,
+      "loss": 0.919,
+      "step": 652
+    },
+    {
+      "epoch": 0.8450339695891297,
+      "grad_norm": 0.8439355492591858,
+      "learning_rate": 9.39457728046174e-05,
+      "loss": 0.808,
+      "step": 653
+    },
+    {
+      "epoch": 0.8463280491750242,
+      "grad_norm": 0.863634467124939,
+      "learning_rate": 9.392609291598413e-05,
+      "loss": 1.0594,
+      "step": 654
+    },
+    {
+      "epoch": 0.8476221287609188,
+      "grad_norm": 0.8126616477966309,
+      "learning_rate": 9.390638316167512e-05,
+      "loss": 1.0526,
+      "step": 655
     }
   ],
   "logging_steps": 1,
@@ -4592,7 +4627,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.266591616008192e+17,
+  "total_flos": 7.32248847459287e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null