Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d170a77a907647e2b7da9f2a4e17dedc666b01503fa5bf3fea217588b6205ac2
+oid sha256:36030726c2f0c5e8424cc0ce28eb973a36c1e8716005ee0bcef160ddbfe90143
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cbc923e9f4f858eeef9bf25e3100d432e94a65ffa69278853ed42c83128cc4e
+oid sha256:58c61fffa7021b944ec8583beae844af45cfdddc404bd450f7f264d5849f2165
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332759cf7b5cf921f7c9ebfe29466512b01ff3dba8f0377398688b0a48981a95
+oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007659248542615208,
+  "epoch": 0.0015318497085230415,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 13.842,
       "eval_steps_per_second": 1.73,
       "step": 9
+    },
+    {
+      "epoch": 0.0010212331390153612,
+      "grad_norm": 4.338223934173584,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 5.0681,
+      "step": 12
+    },
+    {
+      "epoch": 0.0012765414237692013,
+      "grad_norm": 2.9977951049804688,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 4.8176,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015318497085230415,
+      "grad_norm": 3.106626272201538,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 4.7295,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015318497085230415,
+      "eval_loss": 1.1791139841079712,
+      "eval_runtime": 1428.3193,
+      "eval_samples_per_second": 13.856,
+      "eval_steps_per_second": 1.732,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656345471778816e+16,
+  "total_flos": 2.531269094355763e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null