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:fbc0ebc5386acbbedd78e61d427d8c7df10e092e4fd9c5708bd894f553b4bd68
+oid sha256:4f6ee24688aeb3d2c93a06912041be2abd9025d40045580fcb4b26ea6818a091
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a837d0e0a9a8e5bb5b810d9a1d901f3e06467dcc9b0f583ad9acb3083c7a5a5
+oid sha256:1ae584bdb89a600f9fc921a16a87cf6e57498f30a1191fced914e969ad5453c5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b59a33673f726815018c41edcb801960111b887ff197503bf590a972c10248
+oid sha256:6d70c6d4108d09c3ca027b24128794370fd3c24d3d571630cd63800625c78dfd
 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": 0.00042446623371110827,
+  "epoch": 0.0008489324674222165,
   "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": 17.2526,
       "step": 9
+    },
+    {
+      "epoch": 0.0005093594804533299,
+      "grad_norm": 24.10533905029297,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 14.9313,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006366993505666624,
+      "grad_norm": 25.62902069091797,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 14.2183,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006791459739377732,
+      "eval_loss": 2.3047831058502197,
+      "eval_runtime": 2837.1932,
+      "eval_samples_per_second": 10.489,
+      "eval_steps_per_second": 2.622,
+      "step": 16
+    },
+    {
+      "epoch": 0.0007640392206799949,
+      "grad_norm": 18.13753890991211,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 13.969,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.054694248022016e+16,
+  "total_flos": 2.109388496044032e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null