Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c03a015a580a3bd179f291fdab75eff7e31ece839cfcc4f63a32dd988c19119
+oid sha256:12346378a437430746ea222bc30f45cb5a7e6e3496c59adcbf36eba58b092b4c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115dfa6ebf66d93a158589f495daf2056b3849994cbf7767365100319397ab22
+oid sha256:4cfeb972b2138cc8dd35ff34c1ca97dc04dea2015b3270dc3a86460cf3ad0f7d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c242e7269432a4962e7acfd56ff459323e841ff92246b22f7b2a9e1ada61c17b
+oid sha256:059978edfb431ab0cc0b8804f18a5762ea8e46e8902de7ab856b3c461008a7a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006326111023248458,
+  "epoch": 0.012652222046496917,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 4.3806,
       "step": 9
+    },
+    {
+      "epoch": 0.00759133322789815,
+      "grad_norm": 1.8158526420593262,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.0533,
+      "step": 12
+    },
+    {
+      "epoch": 0.009489166534872686,
+      "grad_norm": 1.1403063535690308,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.7933,
+      "step": 15
+    },
+    {
+      "epoch": 0.010121777637197533,
+      "eval_loss": 0.8931291103363037,
+      "eval_runtime": 93.3125,
+      "eval_samples_per_second": 7.137,
+      "eval_steps_per_second": 3.569,
+      "step": 16
+    },
+    {
+      "epoch": 0.011386999841847224,
+      "grad_norm": 1.1006195545196533,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.5634,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6534582019031040.0,
+  "total_flos": 1.306916403806208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null