Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1beab8a142209279319747b6b52a644878e34c29d25b9e98e993815e07f89a56
+oid sha256:536a2d32fdb1cf190d2ab6a46cb586b2176b891f01f0d3e3d3f63ca983467fa8
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9a6e37810aa411da4aca5be45f1c9eabb94161e9bba7e3b1f1cff4f4295636
+oid sha256:285fc0090986e3eee754a341aba064551b1eaca98bb57ff5651ae11b3d57255a
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e73923f37ec7135161905afe711e033d5580982c1091005b6796522a09e1da71
+oid sha256:07800c1453f3f8d96a204751f34b7af7bad25585c6b9ac42ed58a2462a5ab9b2
 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": 0.9420929551124573,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 0.9371617436408997,
+  "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": 2.45,
       "eval_steps_per_second": 0.307,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.7546,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 0.9371617436408997,
+      "eval_runtime": 785.7561,
+      "eval_samples_per_second": 2.456,
+      "eval_steps_per_second": 0.308,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 4.9198271845933056e+17,
+  "total_flos": 5.1788857400991744e+17,
   "trial_name": null,
   "trial_params": null
 }