Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a933413642590a6a5c7c4c1807b8f9fcb55aa9e9f5150f555c768312c783eef
+oid sha256:cf5b338899e4e3215f011ef26c41c7e9bc41b20f8f1fb586ea0f638c7912ac01
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a30b83a522cfa7cfbe6050aa6a6a197b948bb8dee5bbc3cfbfae5fc2c3f88b
+oid sha256:d3c0615ae142b1988b6a40f9267e4f8ed3030355a25a5aaad7bc3333f5c3521d
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f30fb79add30e9197a872210bb6fe13c041e77a650d28f4d45e4d519d6b3c14
+oid sha256:702cc6df180758d3d6dd377c11b570f3269e7e0e686b4163706b71308e16fd59
 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": 0.0003649035742305096,
+  "epoch": 0.0007298071484610192,
   "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": 1.9497,
       "step": 9
+    },
+    {
+      "epoch": 0.0004378842890766115,
+      "grad_norm": 1.895203709602356,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.7148,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005473553613457644,
+      "grad_norm": 1.1740204095840454,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.6693,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005838457187688153,
+      "eval_loss": 1.5610108375549316,
+      "eval_runtime": 861.494,
+      "eval_samples_per_second": 13.394,
+      "eval_steps_per_second": 6.698,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006568264336149173,
+      "grad_norm": 1.226759433746338,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.6198,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4237749607464960.0,
+  "total_flos": 8475499214929920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null