Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4a36b2dc567f709001b2e2d3eb0df64c45a7519278333da631724b7c483a06
+oid sha256:54a2c237308577c12f2bd60b99b56367cf64a37f14cfa7fa7ef21f746bed9ae5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf3fcff38bbc765eba6abc1f450e9afcc0e5a585cc684906f1e657c6603da5f
+oid sha256:64d60163084377634719f48ce1c687bea1a36d675b36393419b3c36bded9c9ab
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:2df7a7c548661260df026af22e850190c6e0e825fcd4f3951c3661d2bae55f7a
 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": 0.006845798391237378,
+  "epoch": 0.013691596782474755,
   "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": 0.7291,
       "step": 9
+    },
+    {
+      "epoch": 0.008214958069484853,
+      "grad_norm": 0.9412434697151184,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.7513,
+      "step": 12
+    },
+    {
+      "epoch": 0.010268697586856067,
+      "grad_norm": 0.942672610282898,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.7163,
+      "step": 15
+    },
+    {
+      "epoch": 0.010953277425979804,
+      "eval_loss": 0.7357094287872314,
+      "eval_runtime": 53.5798,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 5.748,
+      "step": 16
+    },
+    {
+      "epoch": 0.01232243710422728,
+      "grad_norm": 3.3070077896118164,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6944,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7697080566939648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null