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:c5bf62248420b1efb1022d25cfda8aa09744f27cae8adcfebcf0bdda01fa8f7a
+oid sha256:9d4ec839628739a86b262803631999848d351c9b63f09660c4dc8f610626c475
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d545020c7a1bd1e811c0ff546e5a58141d58340f65684cfb33a4b44f1b128b70
+oid sha256:b2fb6a596178dde6ec0dfd9480c47f7b15287b60719f259409633cbeb51e3ad5
 size 43122580

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 sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0103866128101558,
+  "epoch": 0.0207732256203116,
   "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": 13.971,
       "eval_steps_per_second": 1.751,
       "step": 9
+    },
+    {
+      "epoch": 0.013848817080207732,
+      "grad_norm": 4.61670446395874,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 7.7237,
+      "step": 12
+    },
+    {
+      "epoch": 0.017311021350259664,
+      "grad_norm": 4.776439666748047,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 7.5723,
+      "step": 15
+    },
+    {
+      "epoch": 0.0207732256203116,
+      "grad_norm": 3.863844394683838,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 7.8625,
+      "step": 18
+    },
+    {
+      "epoch": 0.0207732256203116,
+      "eval_loss": 1.938367247581482,
+      "eval_runtime": 104.6138,
+      "eval_samples_per_second": 13.956,
+      "eval_steps_per_second": 1.749,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2619236954341376e+16,
+  "total_flos": 2.523847390868275e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null