Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fae23706bad25e0293beaecefcf63be6cd4710c0c15155427e5040d50c5d56c
+oid sha256:0f37dc56b7df954a6cd0364326072bf1be7667174c65ce17ae49872579e0c55f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8742ecbdd911110974cc695fa914a66987e172634f25960593b86903789b92dd
+oid sha256:cd902a23bdf27aef7b905bc59aeb0143c42fb8221fb48e215497e2e5a1c6268d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab79c6a083337c9d9cd856b8d8248930e4cb230f6ea6bc6840ef563ef8c0e5cd
+oid sha256:7e878fc0fbc86334888140425f50a172daf0ca6c9b8e00f870566985c8b9eac8
 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": 2.4035205841064453,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 2.379911422729492,
+  "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": 30.677,
       "eval_steps_per_second": 3.838,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 2.3762,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 2.379911422729492,
+      "eval_runtime": 204.9943,
+      "eval_samples_per_second": 30.606,
+      "eval_steps_per_second": 3.829,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.700986147274752e+16,
+  "total_flos": 3.994021987006464e+16,
   "trial_name": null,
   "trial_params": null
 }