Training in progress, step 102, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e8cfba5a77cad29d727a3166f26c38a84816c41c1f2515caa8a7adb4dcc8c4
+oid sha256:1de549ffe6cbda026938a42d1e2441221d0dd36aef338a55a6099f624dd35f95
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:689217aaa41feaaaeee9288107dd691977948d6c3a1d2a1df9bb651a1352b6aa
+oid sha256:4057eda53a53bed4869baaddd9a821cfa6574c2069db78e3e3ae3b090fa54119
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52126d43fca697f9a6daabc677f2c11c3e68cba9c6ff06167ebb9376aa2ac9b1
+oid sha256:d06b0e421df269e758dbad384e6a198d09f9dc2f79e06ddf32bd52cb423765ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24510621ac929102038dbb9557bac0e17f0ed52c36608ebab8e700d1b1464f1d
+oid sha256:fcbdf5cce354397b1cc7dbc75ae72cd1ce74fbf84991f656a8ae8c5ec4cf6c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18338727076591155,
+  "epoch": 0.22006472491909385,
   "eval_steps": 17,
-  "global_step": 85,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -251,6 +251,56 @@
       "eval_samples_per_second": 50.889,
       "eval_steps_per_second": 6.386,
       "step": 85
+    },
+    {
+      "epoch": 0.18770226537216828,
+      "grad_norm": 0.005217652302235365,
+      "learning_rate": 6.466250186922325e-05,
+      "loss": 0.0002,
+      "step": 87
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.2677434980869293,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 0.0004,
+      "step": 90
+    },
+    {
+      "epoch": 0.20064724919093851,
+      "grad_norm": 0.0085700498893857,
+      "learning_rate": 5.985585137257401e-05,
+      "loss": 0.0003,
+      "step": 93
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.0022312181536108255,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.0004,
+      "step": 96
+    },
+    {
+      "epoch": 0.21359223300970873,
+      "grad_norm": 0.008560556918382645,
+      "learning_rate": 5.495227651252315e-05,
+      "loss": 0.0026,
+      "step": 99
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.004689795430749655,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 0.0002,
+      "step": 102
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "eval_loss": 0.0012459141435101628,
+      "eval_runtime": 15.286,
+      "eval_samples_per_second": 51.093,
+      "eval_steps_per_second": 6.411,
+      "step": 102
     }
   ],
   "logging_steps": 3,
@@ -270,7 +320,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6596442068025344e+16,
+  "total_flos": 1.988669880454349e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null