Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368e3dd50843a82400c5aff72701fd69347bb1313e854d1a075415e07513a8d2
+oid sha256:8aee548989776a0d096ebb15b1c7f23d4a53c29832287572044a4ebe374dea1d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e433ee855f54f134e6b078e30ff18509879947f17fc71385bd439e6809b6d426
+oid sha256:ebc0e2f17c2a65600c105e685737acc5d8465065895e6490bfb6cd76c7836e57
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4b1b37e75be4b65b7642b3207f0ac6424318170e6fdb52189f43223d7c1de8
+oid sha256:d2511746767caf74ed2af043be349b91a9f9de694b3b61fb6953cef602c3b33a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3098464012145996,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 1.3114754098360657,
+  "best_metric": 2.2953364849090576,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 1.384335154826958,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,13 +259,27 @@
       "eval_samples_per_second": 30.67,
       "eval_steps_per_second": 3.837,
       "step": 1800
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002,
+      "loss": 2.2727,
+      "step": 1900
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 2.2953364849090576,
+      "eval_runtime": 204.8297,
+      "eval_samples_per_second": 30.63,
+      "eval_steps_per_second": 3.832,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.134876246112256e+16,
+  "total_flos": 5.419260380362752e+16,
   "trial_name": null,
   "trial_params": null
 }