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:a539987f10d6fa6fbac3db5bc2c53db43379f8b99fb8372cae278b9af0c1cbd3
+oid sha256:1cd72a53cfa977a590464db572c54a6480a4174169ec1ff3a4a0701ab542a295
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216b188451a4c91b3ebfebdafcce35f1c00925b4f658c0fa5e222f4deaaff2a3
+oid sha256:6d87bd8c1f38100a35e4973dfd77aa474e226e409a8e5c0e0c1b39c596c6af4e
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81f8b442d09585da6fbfa683b01a53fc96a691c8e675b09a90a692efdaf54a4
+oid sha256:1c5749fec47bc82d3908cbfade47ef367cd29345182846ddf764d7d941c8e224
 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": 1.3857518434524536,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 1.3718016147613525,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,13 +175,27 @@
       "eval_samples_per_second": 15.023,
       "eval_steps_per_second": 1.88,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.3933,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.3718016147613525,
+      "eval_runtime": 417.2876,
+      "eval_samples_per_second": 15.035,
+      "eval_steps_per_second": 1.881,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.890658552378409e+17,
+  "total_flos": 4.215187369036923e+17,
   "trial_name": null,
   "trial_params": null
 }