Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb21fc38b6e1a61b8c8cbf28a1ad57f09b3e5737d24f28b2a452d471ca5ca2e
+oid sha256:734330beaad492891ff5f7fc9df9a2e1b069f2c4211ce697c6855f1a02cdfc32
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16eb2dede13e2fdb04313cbb52f7e91a89c8d596d36cbaa70ec17303c83ff4c
+oid sha256:9df4a54290fafb95c4a6d1e942a73c358bc2ff92a9bc5868ee328e710dde0905
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5633f06ee7068396712f7cccd0b526b2f848878b47f6580e5d95109e7a8e98
+oid sha256:72f0bd9d86319639dfe9833d26a1acc00818f50c46f354bc07ae5eca24846d97
 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": 1.2911254167556763,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.2876315116882324,
+  "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": 12.716,
       "eval_steps_per_second": 1.595,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 1.0341,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.2876315116882324,
+      "eval_runtime": 151.8147,
+      "eval_samples_per_second": 12.713,
+      "eval_steps_per_second": 1.594,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2108220870201344e+17,
+  "total_flos": 1.2745693497470976e+17,
   "trial_name": null,
   "trial_params": null
 }