Training in progress, step 485, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7021ae9619a321c4fe6163d1c096061cc13b61a48ce860e6b0f7790a0de1a45
+oid sha256:47a6b59d01849a163702b8e50607c498745112dc6ced09ce72986bc17ec447c5
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b4fc0e2d4071b340f24f1590dacac63838b744b2dd6aa10c6c78993a30b8bf5
+oid sha256:4c943a007ca820031ad467134581d9a1d6d566dbef8d77e1cbb5e854f9dbe6f0
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032f2d26c59f5362e1f97b89368915c6408089f13037766115fb561ba9953a00
+oid sha256:a2c2f577326b2b04f054023f26d112b121ac8ff4bf7c93ae38255948cc3a2c22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0aea3ba173d77bf5e35d75c17e1d368377724dd79bc59ed76d246cf3682b43
+oid sha256:04f4b94f1a44c59895f464174a55ad4567f9ad6cb9a5184c25fed320934f9e0d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6211582012293756,
+  "epoch": 0.6276285991588483,
   "eval_steps": 386,
-  "global_step": 480,
+  "global_step": 485,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3383,6 +3383,41 @@
       "learning_rate": 9.688991567458933e-05,
       "loss": 0.7721,
       "step": 480
+    },
+    {
+      "epoch": 0.6224522808152702,
+      "grad_norm": 0.7499825954437256,
+      "learning_rate": 9.687558608994232e-05,
+      "loss": 0.8728,
+      "step": 481
+    },
+    {
+      "epoch": 0.6237463604011647,
+      "grad_norm": 0.871703028678894,
+      "learning_rate": 9.686122463423732e-05,
+      "loss": 0.88,
+      "step": 482
+    },
+    {
+      "epoch": 0.6250404399870592,
+      "grad_norm": 0.8204110860824585,
+      "learning_rate": 9.684683131723884e-05,
+      "loss": 0.8569,
+      "step": 483
+    },
+    {
+      "epoch": 0.6263345195729537,
+      "grad_norm": 0.8779101371765137,
+      "learning_rate": 9.683240614873294e-05,
+      "loss": 0.901,
+      "step": 484
+    },
+    {
+      "epoch": 0.6276285991588483,
+      "grad_norm": 0.8231368064880371,
+      "learning_rate": 9.681794913852746e-05,
+      "loss": 0.989,
+      "step": 485
     }
   ],
   "logging_steps": 1,
@@ -3402,7 +3437,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3660984241291264e+17,
+  "total_flos": 5.421995282713805e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null