Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd72a53cfa977a590464db572c54a6480a4174169ec1ff3a4a0701ab542a295
+oid sha256:9a2a55c1efa884e98e1b18cc28a5bc5f4a2a8f22946059813b063c3af93c22a3
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d87bd8c1f38100a35e4973dfd77aa474e226e409a8e5c0e0c1b39c596c6af4e
+oid sha256:49fbe0f142464fc6adfc16ee055e38bb979c38fffcea0cea5d4fa13867eae478
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5749fec47bc82d3908cbfade47ef367cd29345182846ddf764d7d941c8e224
+oid sha256:a6f87eeba1af718cddacd5d9616efe0fba785b21191a131136973f711b764cec
 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": 1.3718016147613525,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 1.3577570915222168,
+  "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": 15.035,
       "eval_steps_per_second": 1.881,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.3556,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.3577570915222168,
+      "eval_runtime": 417.5078,
+      "eval_samples_per_second": 15.027,
+      "eval_steps_per_second": 1.88,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.215187369036923e+17,
+  "total_flos": 4.539473771498373e+17,
   "trial_name": null,
   "trial_params": null
 }