Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948826c9dd858709de0c2c4125273aa584338fafd27c1c959a6511d3d691e523
+oid sha256:48e813085bbb96737b0fbe42f68bca29a2ac0d065482f99d6dfa4099f7b6343a
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0712dc73021ad81a2097d1efa5660cb999e296e42a45af3f5b76980952d3aa52
+oid sha256:cce56cf73258e85f1f81f986fc1a9a97ea5f6afde72a10248d8104a9c3203457
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7ae3281f8a6cb460b1545701878c767c2d95ce91301108396f0564e1475c05
+oid sha256:493cdacaef2234b9e9529bd8dfaf2ef738c438d7569755b70d703d0f7e3210bc
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
+oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9287375211715698,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 2.9333333333333336,
+  "best_metric": 0.9274052381515503,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 3.066666666666667,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,6 +315,20 @@
       "eval_samples_per_second": 2.457,
       "eval_steps_per_second": 0.308,
       "step": 2200
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.0002,
+      "loss": 0.7409,
+      "step": 2300
+    },
+    {
+      "epoch": 3.07,
+      "eval_loss": 0.9274052381515503,
+      "eval_runtime": 779.2439,
+      "eval_samples_per_second": 2.477,
+      "eval_steps_per_second": 0.311,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
@@ -322,7 +336,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 5.6983487558086656e+17,
+  "total_flos": 5.957747193405542e+17,
   "trial_name": null,
   "trial_params": null
 }