Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c36cfa96ab970ee66392a6252997efced81c872ebf83b0943c8ce69895bfc61
+oid sha256:748db8e23f3a9ce9b48731561cd07fb81cdb255b67b06e980662a7edf381154f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f4214f2cb0f8c8b60b18d6cf928b57c69ff8a6cd9c41ff653c798b93dfcb72
+oid sha256:0e7f13c605c08917158fac2099cd418fc26178504be5b5b0e10761e05c32ac9a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
+oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004035648225996301,
+  "epoch": 0.006053472338994451,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 4.789,
       "eval_steps_per_second": 4.789,
       "step": 6
+    },
+    {
+      "epoch": 0.004708256263662351,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 2.541,
+      "step": 7
+    },
+    {
+      "epoch": 0.0053808643013284006,
+      "grad_norm": 4.99736213684082,
+      "learning_rate": 0.00012,
+      "loss": 2.5739,
+      "step": 8
+    },
+    {
+      "epoch": 0.006053472338994451,
+      "grad_norm": 4.587267875671387,
+      "learning_rate": 0.00014,
+      "loss": 2.1589,
+      "step": 9
+    },
+    {
+      "epoch": 0.006053472338994451,
+      "eval_loss": 2.139094829559326,
+      "eval_runtime": 124.0009,
+      "eval_samples_per_second": 2.532,
+      "eval_steps_per_second": 2.532,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 6676985552044032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null