Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24064aa8683230a7b3a039fd81e1b05e0ff78db2e5bf584fe89728e9df23ffe5
+oid sha256:251cf16640aa3564cdee5e41c6f5500062bd4b6f1d41115b72735cd756e2f301
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7683c83debe0cae274d7783463a965c02eab380f24d7b8882509a86c4f8309
+oid sha256:a24c53fef925d59e0da2303aa4b226f15fad20c64038178e9fc38be37e32a006
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9386b4e0c43c2c20517e468db5aea4f7e38dafdd46988a182c3761eebc734402
+oid sha256:fb1f2a2abdd742820afd569c0937ce4ea89dc5b65d5f0e57158e0e9f700d2326
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1880aef90fa44f8fcb9d240241d2b9fce349526552d8adb6f96784c29ef5265
+oid sha256:1bfdba48dc1047970125a15e5ae1864b983ef41e32aac7742b3805e835d7aca1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.799406342758944,
+  "epoch": 3.9993750976409936,
   "eval_steps": 500,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,21 @@
       "learning_rate": 8.733333333333333e-05,
       "loss": 1.2946,
       "step": 1900
+    },
+    {
+      "epoch": 3.9993750976409936,
+      "grad_norm": 0.14230142533779144,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 1.2953,
+      "step": 2000
+    },
+    {
+      "epoch": 3.9993750976409936,
+      "eval_loss": 1.1589070558547974,
+      "eval_runtime": 780.349,
+      "eval_samples_per_second": 19.891,
+      "eval_steps_per_second": 2.487,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -183,7 +198,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.965396981964341e+18,
+  "total_flos": 3.121471953152508e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null