Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f8269463b11b2f46583fe039a45dfd9ebd8ffca6ac4a0a25c3bcf78c691891
+oid sha256:54a4cdfe8e0c7797aa7c57c96550731ad9d42021cfaedb244e4aed3242ed4703
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76f07250c1d8f817071dbd53410c3bacb845b2f3bbe2e5e39c5f9e6dc8b115b
+oid sha256:e7b537fe08e3bd2d91fabd801c9bfd329d7b41b9f47ce7392a352be7bccb9544
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e78fca4663bc24e80d7e8f779d7b0c03678f0aafed4295ea283e96374bf926
+oid sha256:cff68ccfd4b7f7441d9d6f3e2f7132d2890a46c56e8f2f0a975fd95b0cd6b66c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
+oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0894112586975098,
-  "best_model_checkpoint": "./outputs/checkpoint-3700",
-  "epoch": 2.6958105646630237,
+  "best_metric": 2.081820011138916,
+  "best_model_checkpoint": "./outputs/checkpoint-3800",
+  "epoch": 2.768670309653916,
   "eval_steps": 100,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -525,13 +525,27 @@
       "eval_samples_per_second": 30.522,
       "eval_steps_per_second": 3.819,
       "step": 3700
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0002,
+      "loss": 2.0429,
+      "step": 3800
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 2.081820011138916,
+      "eval_runtime": 205.6367,
+      "eval_samples_per_second": 30.51,
+      "eval_steps_per_second": 3.817,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0533333313456128e+17,
+  "total_flos": 1.0818983291332608e+17,
   "trial_name": null,
   "trial_params": null
 }