Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12baee0dfef7c3cfc3e0655d0b0b6fa314ecb22c11fc3f311ed21f35022038bf
+oid sha256:04b8159f90e0fb0529dc64284c408d30c78e5bc9ed9c6d5ecefd8bb1df0acac4
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5717b36c15f5ffac9d77e0a83f47d42a335b47c6f963c31e89b3d2d89322fce
+oid sha256:8386b1691fa827b578a195bfbee3e508bd4a3d9cf1b55db89e3cbe6f9f35180b
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d10776390e85f876ce76160f0ecaeb7317ea506724ffa1fef7e3f7d1c3ca45
+oid sha256:16006cc611fd889c0d864f6f5e5d6d91b7eac26910e15a1df02e9f538ddde678
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1052631578947367,
+  "epoch": 2.3157894736842106,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 23.369,
       "eval_steps_per_second": 2.921,
       "step": 90
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 2.6105287075042725,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 2.654,
+      "step": 93
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 2.9811198711395264,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 2.3742,
+      "step": 96
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 3.094942808151245,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 2.7658,
+      "step": 99
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "eval_loss": 2.814375400543213,
+      "eval_runtime": 3.0526,
+      "eval_samples_per_second": 23.587,
+      "eval_steps_per_second": 2.948,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.639179811697459e+16,
+  "total_flos": 4.001087196286157e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null