Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ef621c8b616e5e304df0bd7cf91f1573ff3c738f325bb909db08731d6b8772
+oid sha256:0328b2f069d53eddc742691dcf3eb0bd2e9cd8ccf1e058068e3f9206ed99f2b7
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90030f4ac1245cdf030cf76e09ab129dd56976981f9c1b26ec614206d195fea6
+oid sha256:f4ae13eb833f2ba132c67a9f50c538e52a5fdaf3608d9c1fc4660caa98bcdecc
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9e29ca9f1840ccec759292965b44b25e81d2b6f5643637c96ef211cfb804af
+oid sha256:975e2fef0ce023c45a0d7bbabf76a79358b37a1de8f82a4354020f8b97bfa2fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.740575992727037e-05,
+  "epoch": 0.00014610863989090555,
   "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": 7.697,
       "eval_steps_per_second": 7.697,
       "step": 6
+    },
+    {
+      "epoch": 0.0001136400532484821,
+      "grad_norm": 9.116958618164062,
+      "learning_rate": 0.00014,
+      "loss": 2.7834,
+      "step": 7
+    },
+    {
+      "epoch": 0.00012987434656969382,
+      "grad_norm": 6.480123996734619,
+      "learning_rate": 0.00016,
+      "loss": 2.6653,
+      "step": 8
+    },
+    {
+      "epoch": 0.00014610863989090555,
+      "grad_norm": 6.486927032470703,
+      "learning_rate": 0.00018,
+      "loss": 2.2272,
+      "step": 9
+    },
+    {
+      "epoch": 0.00014610863989090555,
+      "eval_loss": NaN,
+      "eval_runtime": 1684.8043,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 7.697,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1206357948628992.0,
+  "total_flos": 1809536922943488.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null