Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68535f6f1447ab83d46d4ad846ad48afcf5639f7a698421f6918c724ce77b497
+oid sha256:de917f814dbdb867628c08292e9d8aa5025ffcaaa8ebcbcd2ca3438f6f169fae
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bef50ba737dbe2d3ec7220e9f909379009a79d8677a1908f6475a83a52b2971
+oid sha256:3a521ee7e0ef65b8c9c597f7360aac471893420b7c34cac1854227cde295038a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b1caa877f06ae036337ce6addb7ca1327a7a08a85655f6d3ea458052e94992
+oid sha256:9b1a95e9bd92d1040211b3273128d7ca9b48e309b30bde25b9fc65eda7d2b000
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11176267678509831,
+  "epoch": 0.12418075198344257,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 7.136,
       "eval_steps_per_second": 0.894,
       "step": 81
+    },
+    {
+      "epoch": 0.11590203518454639,
+      "grad_norm": 2.425291061401367,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.4991,
+      "step": 84
+    },
+    {
+      "epoch": 0.12004139358399447,
+      "grad_norm": 2.9057319164276123,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.4731,
+      "step": 87
+    },
+    {
+      "epoch": 0.12418075198344257,
+      "grad_norm": 3.536256790161133,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.6766,
+      "step": 90
+    },
+    {
+      "epoch": 0.12418075198344257,
+      "eval_loss": 0.16034354269504547,
+      "eval_runtime": 171.2352,
+      "eval_samples_per_second": 7.131,
+      "eval_steps_per_second": 0.894,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2781395757275546e+17,
+  "total_flos": 2.5312661952528384e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null