Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60dffad06923851c32be0c18b4577261fa6ba0880a465ef517ac8f2f942c4b6e
+oid sha256:73846cbe0ebf9596d831c55e5f624796fbdca57d56812761bf6e9e0bd9de0efc
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b1654212289388cef9cf0a2f9584a3df30d0417a9f45401e06e718d5847f03
+oid sha256:60a13594a7c481de2bb76cb1757cf01a136d11d369e964453ed15adae029df82
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2bef8370b39869b04d5472572b79193d75238118553765468e0683c74d1d45b
+oid sha256:082044c9ebc4d75fd1a91516a3ec97fa3a443503223b674e9f9e897d6e964942
 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": 0.00029405638531188353,
+  "epoch": 0.00044108457796782535,
   "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": 9.704,
       "eval_steps_per_second": 4.852,
       "step": 6
+    },
+    {
+      "epoch": 0.00034306578286386416,
+      "grad_norm": 0.9013888239860535,
+      "learning_rate": 0.00014,
+      "loss": 0.4894,
+      "step": 7
+    },
+    {
+      "epoch": 0.00039207518041584473,
+      "grad_norm": 0.6955869793891907,
+      "learning_rate": 0.00016,
+      "loss": 0.4859,
+      "step": 8
+    },
+    {
+      "epoch": 0.00044108457796782535,
+      "grad_norm": 0.5119171738624573,
+      "learning_rate": 0.00018,
+      "loss": 0.38,
+      "step": 9
+    },
+    {
+      "epoch": 0.00044108457796782535,
+      "eval_loss": NaN,
+      "eval_runtime": 885.7742,
+      "eval_samples_per_second": 9.7,
+      "eval_steps_per_second": 4.85,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2270596410900480.0,
+  "total_flos": 3537906035589120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null