Training in progress, step 102, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da79dec41e9caaf2d20b580a1ac8be900b1e85557bca920a1c58e08451ac8e0
+oid sha256:ddc96c869e84d02f3d9fca584798f708f1ec256acf0fc2046f784f22bd75df4a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762a3d12f753b73f0c00d35f5b00752d21a8b8f5d0fc51ea2dcbe0f76a88c334
+oid sha256:41593cb66d0ade40fd58b3c15e0939e1fcdbe2ad92a21b6640acc77ded366dc4
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e478801f2cd9f8bd09cce418d420a98278e1a79e573fedc7ca263d51e55cf66
+oid sha256:047cafb3f6e46fce616fd6719483c734a62b1890d850060214a5a61bf44fb49d
 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": 0.021815848572345205,
+  "epoch": 0.026179018286814244,
   "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": 13.282,
       "eval_steps_per_second": 1.662,
       "step": 85
+    },
+    {
+      "epoch": 0.022329162656400385,
+      "grad_norm": 0.3209848403930664,
+      "learning_rate": 6.466250186922325e-05,
+      "loss": 2.3331,
+      "step": 87
+    },
+    {
+      "epoch": 0.023099133782483156,
+      "grad_norm": 0.31879422068595886,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 2.2655,
+      "step": 90
+    },
+    {
+      "epoch": 0.02386910490856593,
+      "grad_norm": 0.32777905464172363,
+      "learning_rate": 5.985585137257401e-05,
+      "loss": 2.2949,
+      "step": 93
+    },
+    {
+      "epoch": 0.0246390760346487,
+      "grad_norm": 0.3651144504547119,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 2.2816,
+      "step": 96
+    },
+    {
+      "epoch": 0.025409047160731474,
+      "grad_norm": 0.3634001910686493,
+      "learning_rate": 5.495227651252315e-05,
+      "loss": 2.2775,
+      "step": 99
+    },
+    {
+      "epoch": 0.026179018286814244,
+      "grad_norm": 0.3226020932197571,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 2.2755,
+      "step": 102
+    },
+    {
+      "epoch": 0.026179018286814244,
+      "eval_loss": 2.298733711242676,
+      "eval_runtime": 494.1645,
+      "eval_samples_per_second": 13.281,
+      "eval_steps_per_second": 1.661,
+      "step": 102
     }
   ],
   "logging_steps": 3,
@@ -270,7 +320,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2294651397747507e+17,
+  "total_flos": 1.4865650885748326e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null