Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65197b2776ba8f5576ea239a49cbac3f61722ee9a83cb70e6196492ca3fa3484
+oid sha256:dc4de6f6d17658dd72f2461617aecfd024007cd1b93ea77683602c9f67a1563e
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52b5fcb2cd49b2b430f62e066f6826b28c33d643013d0e98d09decf0b99983f
+oid sha256:66d21ffa3e97cd7669bdaf259176923ad31db8ae2b57062353c134282870d316
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96a582389e353e413577cf32a9dd9c3f569b7fd8a5bd42d698d00b47bfced1c
+oid sha256:10d88b02080a0ea2c4b84decc15320ceeac831f11b262b68b63536132f618e5a
 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": 1.2578654289245605,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.2557995319366455,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 15.303,
       "eval_steps_per_second": 1.919,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.0839,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.2557995319366455,
+      "eval_runtime": 126.5159,
+      "eval_samples_per_second": 15.255,
+      "eval_steps_per_second": 1.913,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.253905911733862e+16,
+  "total_flos": 4.608775905574502e+16,
   "trial_name": null,
   "trial_params": null
 }