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:a923dd453d29792040ab42e646f5bf12e221e27204668dd47f40611384e48e82
+oid sha256:0cae663f0d6985e504665a69f47b670e758ab34b71f5fb723f6922fba538f147
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d1598f0bbf4db4c5e5d48adeb7551d8e83f430c8aa0f7d3bddfe3a5253b8ab
+oid sha256:7c6b844b8bd5e13c47e2f63494c3d43e22d8e3840031357049c20c56e880046f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e300bddb0d7e7d6e026d32cddc3203212379cd7e7d4945e7775d35a028e0ce1f
+oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
 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": 0.007797270955165692,
+  "epoch": 0.015594541910331383,
   "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": 6.6057,
       "step": 9
+    },
+    {
+      "epoch": 0.00935672514619883,
+      "grad_norm": 1.0121257305145264,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.6128,
+      "step": 12
+    },
+    {
+      "epoch": 0.011695906432748537,
+      "grad_norm": 0.9788318872451782,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.1365,
+      "step": 15
+    },
+    {
+      "epoch": 0.012475633528265107,
+      "eval_loss": 1.501676082611084,
+      "eval_runtime": 57.0453,
+      "eval_samples_per_second": 9.466,
+      "eval_steps_per_second": 4.733,
+      "step": 16
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 1.0046123266220093,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.0462,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1842091508367360.0,
+  "total_flos": 3684183016734720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null