Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b011a4c60534b932db042fd736d34e87af082176c079c6271cdbf3136a38ac8
+oid sha256:ed1b6f73d502882db71481cb2bd9301ca90f102a334c47d83a2fba5bd0da6457
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb1754679627bc12d4f937b9e502f31a2534b4e172c3cc865c7c598bca6d2e4
+oid sha256:374bbc3237cc7e7bd30285a95b75e5e70f7faf581aba5922c65f250ce697560d
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15979b93c5d9f4120bbd488b10f50e9f5e39387c20523984d041d80836523182
+oid sha256:1546821c54d8d437f890166fec8f3e617edf24a1bd79d91cb3ed48225d7bfa93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288483c81220cbf22f51f35045c4ef691c80220055a03dc4880f485f05c71ede
+oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005034929825665555,
+  "epoch": 0.006293662282081943,
   "eval_steps": 25,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,84 @@
       "learning_rate": 0.00015000000000000001,
       "loss": 0.2162,
       "step": 40
+    },
+    {
+      "epoch": 0.005160803071307194,
+      "grad_norm": 4.584814071655273,
+      "learning_rate": 0.00014694715627858908,
+      "loss": 0.8873,
+      "step": 41
+    },
+    {
+      "epoch": 0.005286676316948832,
+      "grad_norm": 0.006552003789693117,
+      "learning_rate": 0.00014383711467890774,
+      "loss": 0.0004,
+      "step": 42
+    },
+    {
+      "epoch": 0.005412549562590472,
+      "grad_norm": 3.2025034427642822,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 0.2046,
+      "step": 43
+    },
+    {
+      "epoch": 0.00553842280823211,
+      "grad_norm": 0.2174777388572693,
+      "learning_rate": 0.00013746065934159123,
+      "loss": 0.0041,
+      "step": 44
+    },
+    {
+      "epoch": 0.005664296053873749,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.005790169299515388,
+      "grad_norm": 2.011909246444702,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.052,
+      "step": 46
+    },
+    {
+      "epoch": 0.005916042545157027,
+      "grad_norm": 0.04959569871425629,
+      "learning_rate": 0.0001275637355816999,
+      "loss": 0.0016,
+      "step": 47
+    },
+    {
+      "epoch": 0.006041915790798665,
+      "grad_norm": 9.175588607788086,
+      "learning_rate": 0.00012419218955996676,
+      "loss": 0.4144,
+      "step": 48
+    },
+    {
+      "epoch": 0.006167789036440305,
+      "grad_norm": 1.922889232635498,
+      "learning_rate": 0.00012079116908177593,
+      "loss": 0.0746,
+      "step": 49
+    },
+    {
+      "epoch": 0.006293662282081943,
+      "grad_norm": 3.5199947357177734,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.092,
+      "step": 50
+    },
+    {
+      "epoch": 0.006293662282081943,
+      "eval_loss": NaN,
+      "eval_runtime": 3519.1151,
+      "eval_samples_per_second": 0.951,
+      "eval_steps_per_second": 0.475,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -322,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.63415360651264e+16,
+  "total_flos": 3.2926920081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null