Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bafcc9a9ebde4190041472b1d7c6bad6b878c12c3b4f582f266fea1c3eacac0
+oid sha256:a779a7ba575e5edcac70afeba630682ce2a44fc592dd079094d736140a456c32
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623d33b495d388f6c37e729ef9c4af9bca1d14e864851ef196003f2a71a97eaf
+oid sha256:3687402629152e97084f4e720d6e43d8122f1f5d639076cd18fd099521a48809
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1ff603da069d5ec1d3507af633b75dcd549e3cc82effcd3f4a0b5d5cd0d6e4
+oid sha256:51ee1bf5b27eb04de43eae4d043594a4fa2dd767fc1040a6564857f7a8c2a2e5
 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": 0.0005853258801837923,
+  "epoch": 0.0011706517603675846,
   "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": 8.9528,
       "step": 9
+    },
+    {
+      "epoch": 0.0007023910562205508,
+      "grad_norm": 0.7445560693740845,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.3718,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008779888202756885,
+      "grad_norm": 1.0188826322555542,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 8.0393,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009365214082940678,
+      "eval_loss": 2.02815842628479,
+      "eval_runtime": 998.7777,
+      "eval_samples_per_second": 7.203,
+      "eval_steps_per_second": 3.601,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010535865843308261,
+      "grad_norm": 1.1103371381759644,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.9674,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6982612958576640.0,
+  "total_flos": 1.444131316432896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null