Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebe659d2f76c3b6d0004991e20f559679d6cf72d52e6cf39d03f3a1993703e4
+oid sha256:6b5849099de6d64da9163882e434d47ddd3f52875f754b124b878b5d8d76b11b
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae61259f2e63dcfe7725038bb24c483967928f6ef0d982a8f8cd2b593a116162
+oid sha256:f1fedb2f50db670c47275e3ef8f58cd862a8dd1891a81406d1d6e8dbb0ca662b
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba118175917d0b3967d192cc434ab0812fa81db5e2563d542f010b46a09a3fbb
+oid sha256:6e510d47805713e04f667951f9cdc1d488606c58294839c2a021b9c3bb3b8555
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bf5e612f4fd4a32693b4794e80a1434e64b43319b927beb253a75b7d3b07a4
+oid sha256:bc533cf1bb7177235d15f56f9dac5f23ac9d59fa4a64c89a32769793623a6b44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5111614364283403,
+  "epoch": 0.517631834357813,
   "eval_steps": 386,
-  "global_step": 395,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2788,6 +2788,41 @@
       "learning_rate": 9.799045745084847e-05,
       "loss": 1.1194,
       "step": 395
+    },
+    {
+      "epoch": 0.5124555160142349,
+      "grad_norm": 0.7900609374046326,
+      "learning_rate": 9.797887028418746e-05,
+      "loss": 0.9747,
+      "step": 396
+    },
+    {
+      "epoch": 0.5137495956001294,
+      "grad_norm": 0.8245125412940979,
+      "learning_rate": 9.796725049633741e-05,
+      "loss": 0.8594,
+      "step": 397
+    },
+    {
+      "epoch": 0.5150436751860239,
+      "grad_norm": 0.7617928385734558,
+      "learning_rate": 9.795559809519866e-05,
+      "loss": 0.8176,
+      "step": 398
+    },
+    {
+      "epoch": 0.5163377547719185,
+      "grad_norm": 0.9844444990158081,
+      "learning_rate": 9.79439130886938e-05,
+      "loss": 1.0116,
+      "step": 399
+    },
+    {
+      "epoch": 0.517631834357813,
+      "grad_norm": 0.8849684000015259,
+      "learning_rate": 9.793219548476753e-05,
+      "loss": 0.8706,
+      "step": 400
     }
   ],
   "logging_steps": 1,
@@ -2807,7 +2842,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4158518281895936e+17,
+  "total_flos": 4.471748686774272e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null