Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a21f5248ee534df9381e1721ae456913da6eb9dafce38124a627e25c449736
+oid sha256:dc0c06095577ccb805ce1e91c5b8230e75cd3747f6b4f2bb5094848f4421e46c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfddddd1140e1bff643517d99fe94e407c1a9378ef1258dec46f830847b9321b
+oid sha256:de456381fa10bc523dbf33f9a94236ce02d2812872265dbfd1210ce2bc6ef92b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649972b74bc158ab4c264ec3365bee656d459119091a36a2f24b3f8290a1c762
+oid sha256:0b65f1a0fab783030b9678af169570889794fb3146a39ba3945282029a965db4
 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": 0.0016332530317259401,
+  "epoch": 0.0032665060634518802,
   "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": 1.5788,
       "step": 9
+    },
+    {
+      "epoch": 0.0019599036380711283,
+      "grad_norm": 1.013359546661377,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.2081,
+      "step": 12
+    },
+    {
+      "epoch": 0.0024498795475889103,
+      "grad_norm": 0.826115071773529,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.2438,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026132048507615043,
+      "eval_loss": 1.3581643104553223,
+      "eval_runtime": 222.1395,
+      "eval_samples_per_second": 11.605,
+      "eval_steps_per_second": 5.803,
+      "step": 16
+    },
+    {
+      "epoch": 0.0029398554571066922,
+      "grad_norm": 0.6555772423744202,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3149,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3894908238692352.0,
+  "total_flos": 7604344656494592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null