Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:093ea47c410b0a745b8e93693ed47be4d6992211962e673eb93e4686c8651607
+oid sha256:492482922737f774b1c554ae6b0df707f45da2ec1fea952f8d3cdc663975eaf9
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831d62fc929998f1d4d1b816364318aa8561a879a882fb1e8697e381cc4a0ee4
+oid sha256:8c7677d437b82578dbb78df01b1f16713302d84d2d5beb0bcf6fc95926b4f2e6
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13938e18b9d99cf7006feae297577a361a1a7e3a9e73718318c8b0eb4669c15e
+oid sha256:49762064c622a61f788bab27148eaa124166994071a98ad304aeda08b72320f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:79fd9663c22308e7cda458f2f27a3161480f323121be11ab10f5e1ea3f30fc6d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012587324564163887,
+  "epoch": 0.0025174649128327773,
   "eval_steps": 25,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,76 @@
       "learning_rate": 0.0002,
       "loss": 3.3169,
       "step": 10
+    },
+    {
+      "epoch": 0.0013846057020580275,
+      "grad_norm": 21.377635955810547,
+      "learning_rate": 0.0001999390827019096,
+      "loss": 1.0058,
+      "step": 11
+    },
+    {
+      "epoch": 0.0015104789476996663,
+      "grad_norm": 11.985687255859375,
+      "learning_rate": 0.00019975640502598244,
+      "loss": 0.8173,
+      "step": 12
+    },
+    {
+      "epoch": 0.0016363521933413054,
+      "grad_norm": 17.24648666381836,
+      "learning_rate": 0.00019945218953682734,
+      "loss": 0.3288,
+      "step": 13
+    },
+    {
+      "epoch": 0.0017622254389829443,
+      "grad_norm": 38.9212532043457,
+      "learning_rate": 0.00019902680687415705,
+      "loss": 1.7752,
+      "step": 14
+    },
+    {
+      "epoch": 0.001888098684624583,
+      "grad_norm": 12.58133316040039,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 1.7308,
+      "step": 15
+    },
+    {
+      "epoch": 0.002013971930266222,
+      "grad_norm": 5.521592617034912,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.1023,
+      "step": 16
+    },
+    {
+      "epoch": 0.002139845175907861,
+      "grad_norm": 1.7692532539367676,
+      "learning_rate": 0.00019702957262759965,
+      "loss": 0.0166,
+      "step": 17
+    },
+    {
+      "epoch": 0.0022657184215494996,
+      "grad_norm": 9.756790161132812,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.1932,
+      "step": 18
+    },
+    {
+      "epoch": 0.0023915916671911385,
+      "grad_norm": 8.156234741210938,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.3879,
+      "step": 19
+    },
+    {
+      "epoch": 0.0025174649128327773,
+      "grad_norm": 6.355808258056641,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.4888,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -104,7 +174,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6585384016281600.0,
+  "total_flos": 1.31707680325632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null