Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa54b4b7166161a6f06646e52ac7e6d821f3616aa042b366ac7d4e467a9030a4
+oid sha256:2f327e5ab2022652d0e4adaf08bfaca6d4b16bb909a343e9ed57c89637eb15d5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a695a50d569581f7d0018b06f6dc4cbc63cf971987aa7e844c53fd1ed04985ff
+oid sha256:3c5d477d90a6255d322631c99080b111a862467de276c9b78ed367eefd150fe0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:597a0b04dd0a0cc52d9ce583fedb956e33f0756a8bca7a040554f7370a939198
+oid sha256:b28ad40fa0c0353f4ef0255340ffadb1812eaa1e26c616580e4553bfaccb7edb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003264047872702133,
+  "epoch": 0.0036267198585579253,
   "eval_steps": 4,
-  "global_step": 36,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,42 @@
       "eval_samples_per_second": 8.22,
       "eval_steps_per_second": 8.22,
       "step": 36
+    },
+    {
+      "epoch": 0.003354715869166081,
+      "grad_norm": 0.4692092835903168,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.1626,
+      "step": 37
+    },
+    {
+      "epoch": 0.0034453838656300292,
+      "grad_norm": 0.4230363965034485,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.1752,
+      "step": 38
+    },
+    {
+      "epoch": 0.0035360518620939775,
+      "grad_norm": 0.5133092403411865,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.209,
+      "step": 39
+    },
+    {
+      "epoch": 0.0036267198585579253,
+      "grad_norm": 0.3762070834636688,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.1563,
+      "step": 40
+    },
+    {
+      "epoch": 0.0036267198585579253,
+      "eval_loss": 0.20195676386356354,
+      "eval_runtime": 282.3618,
+      "eval_samples_per_second": 8.223,
+      "eval_steps_per_second": 8.223,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -358,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3632415595495424e+16,
+  "total_flos": 1.5116215932420096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null