Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16771a8f6dc3231c25a4a4ed51f3c486414f43414e0d8acfff251345166e77c9
+oid sha256:37384d561dffb8b410c2da855ae849c5daa85475c18a20b1f214bbfaefcb702b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a95beec4a16fdb41d57632dd65db748ed341dc3e972c11d9854556a2c49e76
+oid sha256:966aedc3d0430a230c824c013e4aae80381e2fb2234ef626452f942ef0b919ab
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d2c99dbd46a20a48c294132ab2d17f45afe77fd0e7fd574cf93295fea8e744
+oid sha256:3632eedca239f093acf9fef50ee1b2073b7130b77179cceb32827b1814399786
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.162501096725464,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 2.185792349726776,
+  "best_metric": 2.149629831314087,
+  "best_model_checkpoint": "./outputs/checkpoint-3100",
+  "epoch": 2.2586520947176685,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,27 @@
       "eval_samples_per_second": 30.614,
       "eval_steps_per_second": 3.83,
       "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002,
+      "loss": 2.1015,
+      "step": 3100
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 2.149629831314087,
+      "eval_runtime": 205.2556,
+      "eval_samples_per_second": 30.567,
+      "eval_steps_per_second": 3.825,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.542105612314624e+16,
+  "total_flos": 8.828952655767552e+16,
   "trial_name": null,
   "trial_params": null
 }