Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57c6073377cdf61eebb94c15820ed547a7c1855a2d59f451ab38a529f1380b4
+oid sha256:ee1b7c213c32030066486b35c91853a2f2cb9de3a8640fee74b013ac73154356
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0203392aa75aba140282dbb264062a35e852a64a77cad6afffc48dda26d6a85
+oid sha256:564e105ace6c058e0808b8515b72744d892a36f2ef89694069d814a36071ab39
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abf1f5f142077ef268dd05bc1f31451ee03172c05cd015beffd3ed0ada56893
+oid sha256:82f0105b4caa76d7467df1c3cbd9c55d83debb9d83bf17a96e8ef99770cbc1b5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.007003903388977,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.0005298852920532,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 5.455,
       "eval_steps_per_second": 0.684,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.8555,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.0005298852920532,
+      "eval_runtime": 353.5757,
+      "eval_samples_per_second": 5.459,
+      "eval_steps_per_second": 0.684,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.545011713639301e+17,
+  "total_flos": 2.8274441850197606e+17,
   "trial_name": null,
   "trial_params": null
 }