Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa8a38a99adbb6b86d95a8e88bae913ce143e94b7424352e70d64006e97f8f7
+oid sha256:3df1f960a29c44061fce66ae401b18a75ac0738ee75c302a3eebb9ed3a0c763e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7f1f3770b40fd29e9fe2d8e8e6cb188fbc7927c7790a397e71ae90d8ab8dc9
+oid sha256:e6223ebb88b8579bea4e2ca04d51e383ef3b9142dca394ff972e89f98c62bb82
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fcf009a64a304dce1129b0fdc1b80a365b4ef48344321c5dfb03cba1db1c591
+oid sha256:d1b6db96b2a087280e0193508072347d81e3efb5dcab769c085a2a842cb52560
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9502108693122864,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.6988636363636362,
+  "best_metric": 0.946110725402832,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.840909090909091,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 11.973,
       "eval_steps_per_second": 1.501,
       "step": 1900
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 1.0644,
+      "step": 2000
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 0.946110725402832,
+      "eval_runtime": 124.5826,
+      "eval_samples_per_second": 11.976,
+      "eval_steps_per_second": 1.501,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0682272179726336e+17,
+  "total_flos": 1.1244470506924032e+17,
   "trial_name": null,
   "trial_params": null
 }