Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35faa10e2e1025e6e80dd90784a3e69cbb7d70864601429699e8945875e8a5ac
+oid sha256:1b5b970d09d4cbd24a80743cc054aeff9963ded3de71eb0c85c035ffa82c4ddd
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d17a84885bcb28207d7bc0e0c30e20a7d9daa100360895f2fb3062bcb0f1fd6
+oid sha256:9ef54933cabdae91fc35f701aa5d1e254f0f2935284153355ec8f76df7f389d4
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f066a20e5da7fa04a9a4d285ab2b059c8b0e76ab21f5e65de0aafabb42a20b2
+oid sha256:ee53bcfdd5f1a8c97c44b57116be4b9598eeed231f258e11af07fe6b34c0936f
 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": 0.0013633729847643068,
+  "epoch": 0.0027267459695286137,
   "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": 2.1532,
       "step": 9
+    },
+    {
+      "epoch": 0.0016360475817171682,
+      "grad_norm": 0.876745343208313,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.1755,
+      "step": 12
+    },
+    {
+      "epoch": 0.0020450594771464605,
+      "grad_norm": 0.892664909362793,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.9987,
+      "step": 15
+    },
+    {
+      "epoch": 0.002181396775622891,
+      "eval_loss": 2.047835111618042,
+      "eval_runtime": 157.4554,
+      "eval_samples_per_second": 19.618,
+      "eval_steps_per_second": 9.812,
+      "step": 16
+    },
+    {
+      "epoch": 0.0024540713725757523,
+      "grad_norm": 0.9952620267868042,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2332,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1475663018065920.0,
+  "total_flos": 2631599048884224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null