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:dab9dcb3122711cded49b53eb09a1694454ea8a99c37a1f8cefb9403a51f140c
+oid sha256:285336f374782edb4dc7815d1f78bd38c5bee5b9c87c2d9cabc536b21e0685bf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6a0352830923efcc523c6a69b7e9858fa0ba133a4175cf0a7810cb63d51018
+oid sha256:378990590ff31f29eed477a6bb81dd76516a88e8109466cec6c2e01d796228d3
 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": 0.001692047377326565,
+  "epoch": 0.00338409475465313,
   "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": 1.1913,
       "step": 9
+    },
+    {
+      "epoch": 0.0020304568527918783,
+      "grad_norm": 1.1829664707183838,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.2896,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025380710659898475,
+      "grad_norm": 1.0036306381225586,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.0501,
+      "step": 15
+    },
+    {
+      "epoch": 0.0027072758037225042,
+      "eval_loss": 1.258029818534851,
+      "eval_runtime": 210.8297,
+      "eval_samples_per_second": 11.806,
+      "eval_steps_per_second": 5.905,
+      "step": 16
+    },
+    {
+      "epoch": 0.003045685279187817,
+      "grad_norm": 0.8435078859329224,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2201,
+      "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