Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd7ae9b4e134d12f0e54184c776c1bcd9cccc23d4a5ea7261fa1958727988cb
+oid sha256:764d1a51b50a4222f3efa56f983bbbbf7b6108efa642b5271ad3ea45d396493f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1eeee6afcf11fa4c7076151af55c88aad545697a5f32df799a439b3aa7f1393
+oid sha256:18be2e82ba4c9af05d64fe849281dfa3f91c21a27a3dc329b7ed7fba818c215a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9afaef5d5a881aad7a4d7f56dee797e2bfaf24e0e0195fec33bed705a83390f
+oid sha256:50e59e2d1a05f0e293c56fa96d2faf2d4759fe61e974b50396fc3dd56bba8fd6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
+oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010402219140083218,
+  "epoch": 0.020804438280166437,
   "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": 0.00027,
       "loss": 2.3984,
       "step": 9
+    },
+    {
+      "epoch": 0.012482662968099861,
+      "grad_norm": 1.7507294416427612,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 2.0437,
+      "step": 12
+    },
+    {
+      "epoch": 0.015603328710124827,
+      "grad_norm": 1.7595500946044922,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 1.9154,
+      "step": 15
+    },
+    {
+      "epoch": 0.016643550624133148,
+      "eval_loss": 1.8565841913223267,
+      "eval_runtime": 25.8222,
+      "eval_samples_per_second": 11.773,
+      "eval_steps_per_second": 5.886,
+      "step": 16
+    },
+    {
+      "epoch": 0.01872399445214979,
+      "grad_norm": 1.7496970891952515,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 1.9871,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2782077313351680.0,
+  "total_flos": 5564154626703360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null