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:d8f85370e9209eb34dfc6be9b2ca3a641987d0d33811444707c620c807937bb9
+oid sha256:45f4b2413612ff9181690d2771b471f45308f449a468cb305ab3efcf8384a3b9
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e4cb77ef36a13e8f8660c0b55c1a91645c9543c5b3ad8721a81c2c2aee2199
+oid sha256:bd9cfe9a64fbec8d8094ee9fd69f79f78eeb20dc238ec50f7a1ce5656099ec0d
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4612851348ea2f565f3534d572d05b00304a1b55d6b94f91da7e9cfa5a932eda
+oid sha256:bb2ebc62e9336f8068d3625f8376b4f08343cd5fde08ca8c74f25b90076938b7
 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": 0.00211999152003392,
+  "epoch": 0.00423998304006784,
   "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": 7.3739,
       "step": 9
+    },
+    {
+      "epoch": 0.0025439898240407037,
+      "grad_norm": 0.8614652156829834,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 7.1525,
+      "step": 12
+    },
+    {
+      "epoch": 0.0031799872800508796,
+      "grad_norm": 0.9778960943222046,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 7.2018,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033919864320542717,
+      "eval_loss": 1.7460987567901611,
+      "eval_runtime": 236.067,
+      "eval_samples_per_second": 8.417,
+      "eval_steps_per_second": 4.211,
+      "step": 16
+    },
+    {
+      "epoch": 0.0038159847360610556,
+      "grad_norm": 1.2029049396514893,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.1342,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1051641029591040.0,
+  "total_flos": 2088258615902208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null