Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fafee725863969525ce9a1ade86322503646e8539cc57f35ba1dcb37b845c0e3
+oid sha256:53ca8b58f9d0e308c27f737a31aff07b4d8ac62f3175769e32cb1dfebca19a0e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471d412a89155c38301fb5ac9a97943370b094484fa686d6fd18642182aeeadc
+oid sha256:9e36e660ef466eae1d1cfb6ab56ab764dfda0109e491dff9cd3b60c01e430552
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd5ac4d1c6dd28825a283ba1b7098c9c98ffe829df85be04e69129dfd8d2ebd
+oid sha256:08a54a26ce0fcc84bd0749d1220f1ab697ade521481c97d4b96f78fe5e1f43fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
+oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08654496281271129,
+  "epoch": 0.10818120351588911,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 8.955,
       "eval_steps_per_second": 4.478,
       "step": 36
+    },
+    {
+      "epoch": 0.0937570430471039,
+      "grad_norm": 1.216485619544983,
+      "learning_rate": 0.00017343225094356855,
+      "loss": 1.3575,
+      "step": 39
+    },
+    {
+      "epoch": 0.1009691232814965,
+      "grad_norm": 1.0345182418823242,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 1.316,
+      "step": 42
+    },
+    {
+      "epoch": 0.10818120351588911,
+      "grad_norm": 1.2272484302520752,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 1.3834,
+      "step": 45
+    },
+    {
+      "epoch": 0.10818120351588911,
+      "eval_loss": 1.199688196182251,
+      "eval_runtime": 156.5688,
+      "eval_samples_per_second": 8.955,
+      "eval_steps_per_second": 4.477,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1503751283644826e+17,
+  "total_flos": 2.6875026539230003e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null