Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb26284d095a9a3c3f82a2a77828f741bd79ceccf1f2ce5977c946cc843a29d
+oid sha256:04335339b3a6583d45f4876d63070367923a36cca60ebedbe958864d796e1593
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e011a0b388ae393955ac989c67c540020e776eac88acea013e690431976c1500
+oid sha256:c88a60fac8369b1a81a40b1ee74772c6d9fd6a8ac6dd16580314695093985e4f
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39662c2dade98340d3d7fb3afc4f5b62c3c53384f72fb778999c33ccb1b7b28d
+oid sha256:6dacf26b3729f76f3909fd906769c9d833cf5b11043ea752bec18fd16c5c1873
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.529025673866272,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 1.511838436126709,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 1.238615664845173,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,13 +231,27 @@
       "eval_samples_per_second": 43.592,
       "eval_steps_per_second": 5.454,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 1.5148,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.511838436126709,
+      "eval_runtime": 143.9329,
+      "eval_samples_per_second": 43.59,
+      "eval_steps_per_second": 5.454,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.538236687109325e+16,
+  "total_flos": 1.0134801452620186e+17,
   "trial_name": null,
   "trial_params": null
 }