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:b0b78beb7f549b78ae44b68bcda820483115f53a4644b1b2c877a6acd8cfbf1c
+oid sha256:db528b04fb1ed4e38a6bcfcaf50ea32c67f0b1a21f51549498ae570b1e8cfe84
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7959319e9ba216310d551e551da4c9833be90bb086dd846f68b089dca8af94fd
+oid sha256:2c3a7f7ef5d416388c64482a6b1353ec17ed545efbde3d66cb45495f6b125dc0
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f4699b11df86350ce746228bc86b78aa2b77e7bf6d49eda68bc3ebb21718be
+oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
 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": 0.014930944382232176,
+  "epoch": 0.029861888764464353,
   "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": 11.9316,
       "step": 9
+    },
+    {
+      "epoch": 0.01791713325867861,
+      "grad_norm": 0.13820531964302063,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.9282,
+      "step": 12
+    },
+    {
+      "epoch": 0.022396416573348264,
+      "grad_norm": 0.15883134305477142,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.9254,
+      "step": 15
+    },
+    {
+      "epoch": 0.023889511011571482,
+      "eval_loss": 11.924610137939453,
+      "eval_runtime": 6.3914,
+      "eval_samples_per_second": 44.278,
+      "eval_steps_per_second": 22.217,
+      "step": 16
+    },
+    {
+      "epoch": 0.026875699888017916,
+      "grad_norm": 0.16797775030136108,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9236,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4379821867008.0,
+  "total_flos": 8442265337856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null