Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13ba07bc586558fb64f1b66825209f18db56ce572477ab8155107c3ff3f0a88
+oid sha256:f44a8929830688bb4f6cf3bb4f71e56ae1288a232f4677e3d86095a957322a04
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030da15cbb81bbe486c293ede63079918942591b2c0aab7e2ba0cf09fe49d1a5
+oid sha256:a8f27453575437da6f87b9c37a6ab4b7dd09e5107bfc2aaa57336c7611e95b7c
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:646ade6023f73d01b10ebe8ac45df7f64238b06f8264b4a748bbde983b0bdd8f
+oid sha256:7168b0d6c665cd748268e687051b0b7d92835f5a5784945e8c1488a08a50658e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc75fc1c14b28d29d31fa9d4252536c919fc25a390fac3a1e8c09d6575b4029
+oid sha256:8d9707e13ab424365dde92daf30c033711d2caa0fada77309f65d41532581807
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.039122195733235526,
+  "epoch": 0.041567332966562745,
   "eval_steps": 34,
-  "global_step": 80,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -591,6 +591,41 @@
       "learning_rate": 0.00016026346363792567,
       "loss": 9.2195,
       "step": 80
+    },
+    {
+      "epoch": 0.03961122317990097,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 9.7124,
+      "step": 81
+    },
+    {
+      "epoch": 0.040100250626566414,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015727351400805052,
+      "loss": 9.2742,
+      "step": 82
+    },
+    {
+      "epoch": 0.04058927807323186,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015574894393428855,
+      "loss": 11.2145,
+      "step": 83
+    },
+    {
+      "epoch": 0.0410783055198973,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015420533564724495,
+      "loss": 8.6546,
+      "step": 84
+    },
+    {
+      "epoch": 0.041567332966562745,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001526432162877356,
+      "loss": 8.4331,
+      "step": 85
     }
   ],
   "logging_steps": 1,
@@ -610,7 +645,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7635837407657984e+17,
+  "total_flos": 1.8738077245636608e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null