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:bafdd52ab4e3f357f4182ff042632bbb52d0eb52934c558fb7f007bef39756bd
+oid sha256:3e35ac6d89af7a7e2a988ddf6b514bcc2c22ed41eb98693da93df800bc164da7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526b70c9c271cd544dc6753e2d07a666dda691dd3813a9ddb1051250e6ec7f56
+oid sha256:a7ad20ee4587f936caf062a16b9af986bc096691783a0effe2a7a5f7cf18f088
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c360d3fd521981afbe1dfe0d527be160f7b375ae97bb2c2e2d4d7405b0da8608
+oid sha256:7ae472d02b3de5b61691bbbd328158341b9b01fb8bb042f73ebc115b2c91abda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00028211729026342703,
+  "epoch": 0.00042317593539514055,
   "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": 4.987,
       "eval_steps_per_second": 4.987,
       "step": 6
+    },
+    {
+      "epoch": 0.00032913683864066484,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 9.5245,
+      "step": 7
+    },
+    {
+      "epoch": 0.0003761563870179027,
+      "grad_norm": 36.6467170715332,
+      "learning_rate": 6e-05,
+      "loss": 9.123,
+      "step": 8
+    },
+    {
+      "epoch": 0.00042317593539514055,
+      "grad_norm": 19.946910858154297,
+      "learning_rate": 8e-05,
+      "loss": 7.95,
+      "step": 9
+    },
+    {
+      "epoch": 0.00042317593539514055,
+      "eval_loss": 7.195590972900391,
+      "eval_runtime": 899.7507,
+      "eval_samples_per_second": 4.977,
+      "eval_steps_per_second": 4.977,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 6676985552044032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null