Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234c6b078237ba767b54dc76d37e29f9cc37fc8c37448f5939ba7e6eee5ca9a7
+oid sha256:73bf06e4d9ed07e81652fe07ed7bd5a28f1dcfd590dcee949b0a5eca027fb461
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f4ca77e1a213647f1fe853c228c2321091e745307da28e2b242ecfc608b992
+oid sha256:c433727c4a4690398c5abd17c4a25bb5e5a60e44979b60269c2b2752a8b19035
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5db78c56f089acf08b8ff0deaa1e1dc172fca6cf86b0a06986d9598d306e782
+oid sha256:dbb1d9ed0a2d77b4e3624035b568611f0015a3733047f718195fa123e9b53862
 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": 0.0005853258801837923,
+  "epoch": 0.0011706517603675846,
   "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": 8.9495,
       "step": 9
+    },
+    {
+      "epoch": 0.0007023910562205508,
+      "grad_norm": 0.7852150201797485,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.3684,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008779888202756885,
+      "grad_norm": 1.0332019329071045,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 8.0357,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009365214082940678,
+      "eval_loss": 2.0277111530303955,
+      "eval_runtime": 725.6795,
+      "eval_samples_per_second": 9.913,
+      "eval_steps_per_second": 4.957,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010535865843308261,
+      "grad_norm": 1.1446038484573364,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.9552,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6982612958576640.0,
+  "total_flos": 1.444131316432896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null