Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a43dbde1d6e11da7b470680b9e6fd81caffe77be851a6224b3351b99f3abc28
+oid sha256:62550a8ff7ba5722e4964974e963a2fc60f10a75ec460ff4fd02ad7a0dc50895
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0460c1503dc185e164bbbe66afebc739e5d0d308985ced203d2b7f5b8ad76b
+oid sha256:71233b6a65f443dbc43f6db8e865f822cad43998bab83f28a2aeb5151abcec10
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd75cf3b809d1ad953986ea9c75f286af19a4850426c2af932b4978ec671eecb
+oid sha256:f6c4cf6994e46b5facbdf31ef32ec90c7c3528894a167d624af4755a9b984071
 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": 0.0002366449659946114,
+  "epoch": 0.0003549674489919171,
   "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": 3.668,
       "eval_steps_per_second": 3.668,
       "step": 6
+    },
+    {
+      "epoch": 0.00027608579366037995,
+      "grad_norm": 2.0494728088378906,
+      "learning_rate": 0.00014,
+      "loss": 3.8704,
+      "step": 7
+    },
+    {
+      "epoch": 0.0003155266213261485,
+      "grad_norm": 2.3501408100128174,
+      "learning_rate": 0.00016,
+      "loss": 3.7304,
+      "step": 8
+    },
+    {
+      "epoch": 0.0003549674489919171,
+      "grad_norm": 2.1949191093444824,
+      "learning_rate": 0.00018,
+      "loss": 3.1309,
+      "step": 9
+    },
+    {
+      "epoch": 0.0003549674489919171,
+      "eval_loss": 3.0262250900268555,
+      "eval_runtime": 5815.7762,
+      "eval_samples_per_second": 3.671,
+      "eval_steps_per_second": 3.671,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6776928639844352e+16,
+  "total_flos": 2.516539295976653e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null