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:d9524377ee5d4b3bcce89a67ebd975f6f3f260af775688b92228ede57453387d
+oid sha256:fc72c15dfcf5711fb70f2cb68d673c7895270b34b117d6132862ad3fb8844720
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd215fcbd800927e1199ba0e4ed9e6406c199fe450a002f5f63449266911938
+oid sha256:ae63a50b8ef2796c2e42054bfd7b04cb18331479058e64cec3b3f51f2b924764
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0f06add41f04254087e910e0c029b635008b5c3eb0d1e97de321c80184c521
+oid sha256:581654e7247b86e5cf537a4f388a8b452ef6efcbea66ae5b2507bf4e41fdff67
 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": 1.304863691329956,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.2992783784866333,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.6666666666666665,
   "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": 30.662,
       "eval_steps_per_second": 3.846,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 1.3918,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.2992783784866333,
+      "eval_runtime": 47.3036,
+      "eval_samples_per_second": 30.674,
+      "eval_steps_per_second": 3.847,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.370864876486656e+16,
+  "total_flos": 6.706239746605056e+16,
   "trial_name": null,
   "trial_params": null
 }