Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eefe47546c7525148b4e341f999d24f1264598101e98622c370a043c48a263c
+oid sha256:4404b24076cc63d331e67d7ba3a7fe9520f7a0e8f6d4b52270bfbfafc9664489
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5017babea20a99d5d0b5c8fa8ae20dd386cd70986105b12e6903abf458b3592
+oid sha256:d619ba6794210f6129f2e991bb4cca6fb744cc687fb23c48cd2119fe42dacaae
 size 281829907

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c3a2b79a9e1779a4ea69c8a2af53377d65090012e5bf6f98d07565c161f2d7
+oid sha256:417227e46f0a581722968d781d8ea2ba8688c7892e0d69749745f185230daf6a
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675187a06f2fd35edecfb05a0a513255f7787fa03b6116545ac0d5fb4843e9a2
+oid sha256:d2f9c1a66b0f67830f363d7aa55a784bfca1310ea07876b83a0f2f54a5722f96
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5333333333333333,
+  "epoch": 1.0666666666666667,
   "eval_steps": 100,
-  "global_step": 40,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,62 @@
       "learning_rate": 0.0004922997497999166,
       "loss": 0.5324,
       "step": 40
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1061202809214592,
+      "learning_rate": 0.00048678455732775007,
+      "loss": 0.554,
+      "step": 45
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.10958874970674515,
+      "learning_rate": 0.00047983825974555906,
+      "loss": 0.6044,
+      "step": 50
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.09531711041927338,
+      "learning_rate": 0.0004715028398670787,
+      "loss": 0.5653,
+      "step": 55
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.11301957815885544,
+      "learning_rate": 0.00046182867623944434,
+      "loss": 0.5539,
+      "step": 60
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.1083487942814827,
+      "learning_rate": 0.00045087423865966894,
+      "loss": 0.5267,
+      "step": 65
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.10189539939165115,
+      "learning_rate": 0.0004387057347883143,
+      "loss": 0.5533,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.09216652810573578,
+      "learning_rate": 0.0004253967099961942,
+      "loss": 0.5016,
+      "step": 75
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.10134831815958023,
+      "learning_rate": 0.0004110276028625994,
+      "loss": 0.4856,
+      "step": 80
     }
   ],
   "logging_steps": 5,
@@ -83,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1322295041064960.0,
+  "total_flos": 2644590082129920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null