Training in progress, step 3300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d732ffa9a782ca178aeb71ca69c72d2c38dfdddf501d4d8ae5b2df157244e815
+oid sha256:dd537153891e7d185e0d81b0c7c4520e46b21a784002f3f0f8719e9c47277e3f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a64819c9af09f81a158218e4865d0cdce42a41415dd07ea073c21b5890a8ee
+oid sha256:b3070a7891b7a52dbf791e23ef3b13f6ec33aec9b98a072e22cbbd8c297697fa
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d6b84dac6aaad6986d237806767d4c805191ba7fa488b63cf1a10b8e023e89
+oid sha256:03b32db0a2b713dd6b1e7016c32489b8ad860f5a342471d86c52b5af270bb99a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
+oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.043891668319702,
-  "best_model_checkpoint": "./outputs/checkpoint-3200",
-  "epoch": 2.3315118397085612,
+  "best_metric": 2.0311737060546875,
+  "best_model_checkpoint": "./outputs/checkpoint-3300",
+  "epoch": 2.4043715846994536,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,13 +455,27 @@
       "eval_samples_per_second": 15.136,
       "eval_steps_per_second": 1.894,
       "step": 3200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.989,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 2.0311737060546875,
+      "eval_runtime": 574.7464,
+      "eval_samples_per_second": 10.916,
+      "eval_steps_per_second": 1.366,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.398805406728192e+16,
+  "total_flos": 9.691971842875392e+16,
   "trial_name": null,
   "trial_params": null
 }