Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6094463d8f3e34728d2024f1bdec4545455bbc89dc9cc503bc96d9d69cd1b6a2
+oid sha256:25b37d84f8d48bacc9810276fcca7df2577a5e229f353f3f67b5361732237b1c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59df33b21c831cf61ef6eba6d0e24afc420e634af91c753d3305aaac3a21650e
+oid sha256:4bd6f1591924a2e931df4afe2d83d15acce2236a23ccd7eab590296d9797fd1d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f75cd7c3c03b14a8f1465fe7032461a4c10c13162d4c6f39cca0dfd22bbdfa
+oid sha256:44ebd16dfb37eb53aabe83521b38a6fc7f9ea39fe82f2fc4d4e55fe46f23b6ec
 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": 1.3437373638153076,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.3367496728897095,
+  "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": 30.746,
       "eval_steps_per_second": 3.856,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.45,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.3367496728897095,
+      "eval_runtime": 47.2517,
+      "eval_samples_per_second": 30.708,
+      "eval_steps_per_second": 3.852,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.023869613539328e+16,
+  "total_flos": 4.359244483657728e+16,
   "trial_name": null,
   "trial_params": null
 }