Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05692a4437c6b755e45bfb087fd33b111bf4718965bb2e9854cffdb277171fb2
+oid sha256:241e36aa4e2b4e65686d74de6cb59e577a2314b034679fb2dd07aa0082ca4494
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0a5e86b68658f9375454cd75c06ebfc4d6d66b541ac42b8109641c1b13954c
+oid sha256:bbdba28c2035ed9ecdaa1ee131176f190f907bfa69509de83346bdc186b21df9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce222c2390094b071bddb3c451bd7b53527591253692707adf546412178fd3cd
+oid sha256:c32871ed367fbfce842fc140e0a7e8cd760b068dd07514dcbc3cbab9304e7efd
 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": 0.00019502586530538614,
+  "epoch": 0.0003900517306107723,
   "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": 11.6503,
       "step": 9
+    },
+    {
+      "epoch": 0.00023403103836646335,
+      "grad_norm": 17.868330001831055,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.7207,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "grad_norm": 13.60641098022461,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.5884,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003120413844886178,
+      "eval_loss": 2.744744300842285,
+      "eval_runtime": 1468.1313,
+      "eval_samples_per_second": 14.706,
+      "eval_steps_per_second": 7.353,
+      "step": 16
+    },
+    {
+      "epoch": 0.00035104655754969504,
+      "grad_norm": 13.693025588989258,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.7769,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515647493406720.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null