Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261a03f4314fc938f4f3cc7bd2f1dfaf45e9b63c1f03f54c2a27355e907462cc
+oid sha256:db06861c32fdf8f5afd7618071885e49cb06a3db2fcb5f990f1abbbcb2be1c5b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44840a6e4401d3a65934711d4a887f445e33792cd77b48b466c0635301b9119f
+oid sha256:534d858f9c40e7dae737fa598234aca558790653aada7d358cf66a0b40ed831e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
 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": 0.005614035087719298,
+  "epoch": 0.011228070175438596,
   "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": 1.5925,
       "step": 9
+    },
+    {
+      "epoch": 0.006736842105263158,
+      "grad_norm": 3.1763784885406494,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.8336,
+      "step": 12
+    },
+    {
+      "epoch": 0.008421052631578947,
+      "grad_norm": 3.1489222049713135,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5045,
+      "step": 15
+    },
+    {
+      "epoch": 0.008982456140350877,
+      "eval_loss": 0.35977551341056824,
+      "eval_runtime": 63.2774,
+      "eval_samples_per_second": 11.853,
+      "eval_steps_per_second": 5.926,
+      "step": 16
+    },
+    {
+      "epoch": 0.010105263157894737,
+      "grad_norm": 1.5962499380111694,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.323,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null