Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915134b52dc7fae6a948f0418ab82ab4835a8bd1a2110b2e24c4a92784e60f8c
+oid sha256:984a7527231fdcf924c550cc4a8e0ad6fc5902a246abec109bf86ee6e40f3e96
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fca6a8eb3e8ec666c1da28150b075d9b18ba79c6681d0c0f28b21dc0e45690
+oid sha256:69da363107c07a785017addea26230ce3041c8a5b658259b6c960c80f4cd4391
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12322248943cf37dfd9e28e1543d080ca2a19c9cb57888370a2a229ccf14dde5
+oid sha256:8226228c393b137baf64ed3f82c6ed8807e456d3f8e179f09160bf26e5dcc037
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f759335f011566b97a7f413c78ad5fca435292d806b98b7a008cefd7be27717
+oid sha256:d72920266addd1520c8e9d88dcca5854048e355bd6edd8cc80e32e4e48b95586
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10999676480103526,
+  "epoch": 0.11646716273050793,
   "eval_steps": 386,
-  "global_step": 85,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -610,6 +610,41 @@
       "learning_rate": 9.99791792797946e-05,
       "loss": 1.0467,
       "step": 85
+    },
+    {
+      "epoch": 0.1112908443869298,
+      "grad_norm": 1.1422507762908936,
+      "learning_rate": 9.997797261646089e-05,
+      "loss": 0.9535,
+      "step": 86
+    },
+    {
+      "epoch": 0.11258492397282432,
+      "grad_norm": 0.8561545014381409,
+      "learning_rate": 9.997673197273365e-05,
+      "loss": 1.007,
+      "step": 87
+    },
+    {
+      "epoch": 0.11387900355871886,
+      "grad_norm": 1.0027543306350708,
+      "learning_rate": 9.997545734945639e-05,
+      "loss": 0.9861,
+      "step": 88
+    },
+    {
+      "epoch": 0.1151730831446134,
+      "grad_norm": 0.8489773273468018,
+      "learning_rate": 9.997414874749575e-05,
+      "loss": 0.9672,
+      "step": 89
+    },
+    {
+      "epoch": 0.11646716273050793,
+      "grad_norm": 1.0517115592956543,
+      "learning_rate": 9.997280616774147e-05,
+      "loss": 1.1672,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -629,7 +664,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.502465959395328e+16,
+  "total_flos": 1.0061434545242112e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null