Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e40e748f90a6d7aac246c3b04deda24c5d339b4e6ebd0257e5d9c02d9d51d75
+oid sha256:38326b956bf807412da76b2b9c3dbfd3c8ee1dad8ef3a6709c505a2a080cbfa2
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b831cba96af8f43fc8358e60d4293bb4e0f8361a02b6257d2d7ecc72d6b837
+oid sha256:eae6f38c1c8b8ab03c44b6895ddbb2da06f52603a3e2dcce04433d34559bf24a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6de7f4a42b33795d5576dbfcbd59d460b4c2829c2dca4e78d73528861030ee0
+oid sha256:591a9c5e45bb1139399d3039b4c05dd34997d5462b11eb1ca1771e8044f4a6a1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5728731155395508,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 1.55287504196167,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.0200364298724955,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,13 +189,27 @@
       "eval_samples_per_second": 43.645,
       "eval_steps_per_second": 5.461,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.5528,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.55287504196167,
+      "eval_runtime": 143.8673,
+      "eval_samples_per_second": 43.61,
+      "eval_steps_per_second": 5.456,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.750875343424717e+16,
+  "total_flos": 8.347109656129536e+16,
   "trial_name": null,
   "trial_params": null
 }