Training in progress, step 3900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823cfd9d2d1909bcf3b307abfbe7616bd842c04a2738825218f7bb30b4bf8755
+oid sha256:d4669f1bf56ee68ec4365806d14a6e9d2d04350970f960e904c70d144f57fd59
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be78a2be92a3a93e9828cc4756afac3a9a398f10dd6b1cc886d7ef174b48e312
+oid sha256:232ded2cf3c1af9598827a28ed77441efe0deaec88172f55e1fd3662a8842a57
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0625d44593f9a35a65bd6a0c353b2ee783deaa835a908009e34809ad32c4166a
+oid sha256:33ac3d2b522a45fffa5206c5d7a821c451a2d4e38cb61393c89b930eaeff3109
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
+oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2480058670043945,
-  "best_model_checkpoint": "./outputs/checkpoint-3800",
-  "epoch": 2.768670309653916,
+  "best_metric": 1.235005497932434,
+  "best_model_checkpoint": "./outputs/checkpoint-3900",
+  "epoch": 2.841530054644809,
   "eval_steps": 100,
-  "global_step": 3800,
+  "global_step": 3900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,13 +539,27 @@
       "eval_samples_per_second": 43.748,
       "eval_steps_per_second": 5.474,
       "step": 3800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 1.2226,
+      "step": 3900
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.235005497932434,
+      "eval_runtime": 143.4509,
+      "eval_samples_per_second": 43.736,
+      "eval_steps_per_second": 5.472,
+      "step": 3900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2648457919379046e+17,
+  "total_flos": 2.3245805220581376e+17,
   "trial_name": null,
   "trial_params": null
 }