Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a4fa94b63dc1733a36f8552f57e3cfee5eceffe5c940bfb37257d62e78332f
+oid sha256:c7619d6d9b7b1f98142754e0ee7aaa2fa78d7f616728b0937255be260419e6c6
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ce47169592764a8d5f4dd7781fbe1214f92060d52f9d76a4ac669025391ec2
+oid sha256:18fc6e3d69aefbf4310e5826e56b6e16d74b7498b13c46c2f777cf72f5709bb3
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d068296d3f9011b33a34c8187d97d4e5a695d49d324e8c6f6a7442a620b5590
+oid sha256:cfcfb7e12de9afeed6967cff0aeffa633fecf1b0469c1a40f3315ec78a50cc27
 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": 1.582713007926941,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 1.5626935958862305,
+  "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": 43.553,
       "eval_steps_per_second": 5.449,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.5638,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.5626935958862305,
+      "eval_runtime": 143.9538,
+      "eval_samples_per_second": 43.583,
+      "eval_steps_per_second": 5.453,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.750057637589811e+16,
+  "total_flos": 8.34624139321344e+16,
   "trial_name": null,
   "trial_params": null
 }