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:d7ba0baa523f6d25122ae71100f596ae71fdaa12de5a26138210fafb3f305257
+oid sha256:1c1a7f1340eec4c553b12accb55a73dd24dd157dd52efb073cb17595142e9f55
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc233b8f308488f25317fed2d8377e9f77c79592127f755303687902477c6bd9
+oid sha256:6930b2abafd0bfaaef0e7868be3cfc60487c53ebd86a410caf0547d89b4447f4
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1599935195b131f027fefd904b1041b9f3c0cdd237e663cf0fb4a514fb2923
+oid sha256:7617ba3cf9e8ddb856448f9dbc39430954823c370dbeabbecf9999c7ef8bb520
 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": 0.008592910848549946,
+  "epoch": 0.017185821697099892,
   "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": 2.5556,
       "step": 9
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 1.1966177225112915,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.3944,
+      "step": 12
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 1.1105034351348877,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.4451,
+      "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "eval_loss": 2.342407703399658,
+      "eval_runtime": 41.2779,
+      "eval_samples_per_second": 11.871,
+      "eval_steps_per_second": 5.935,
+      "step": 16
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 0.9284036159515381,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.3047,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null