Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4da1d93de07f6426eb36dad5df4d9f864458ec2b3b7300d7784eb0d32cb9c28
+oid sha256:1db5d3b56909838014e78af70c07add655a0319e697df0f691092ac2165d260c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c28cec03ab6548c85e674a5d153e3f9905a52c90df2dffc1b873e7a943b4409
+oid sha256:71c7f6bf18b1baaaae33f31a312ac736d5f56366591058a7485033f3af67ebc1
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffde39b50896bc17b78a0302958b86632bce20c81789b1dc8c76995d55dbbd05
+oid sha256:81dcba0e4b479b247d04028b523e2476c45b2a75dfdecaf64971d23daaffc32d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1256643533706665,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.1177093982696533,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 10.88,
       "eval_steps_per_second": 1.364,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.9171,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.1177093982696533,
+      "eval_runtime": 177.8498,
+      "eval_samples_per_second": 10.852,
+      "eval_steps_per_second": 1.361,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.96699552329728e+16,
+  "total_flos": 9.716923536703488e+16,
   "trial_name": null,
   "trial_params": null
 }