Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1b7c213c32030066486b35c91853a2f2cb9de3a8640fee74b013ac73154356
+oid sha256:6855c333ac1c697e6d06a877d9e75bb8a598912c0b6bd089af9789e465ca3dac
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564e105ace6c058e0808b8515b72744d892a36f2ef89694069d814a36071ab39
+oid sha256:4e8039c70b87ed8bb202c149c44024b2e5af04921eef6a357d9e91ca56ccf729
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f0105b4caa76d7467df1c3cbd9c55d83debb9d83bf17a96e8ef99770cbc1b5
+oid sha256:cf0a8d4e9a6653930f212c4ac0808e06254e1f11ce9e27417a57091c7e3e0282
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0005298852920532,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 0.9988044500350952,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.4666666666666668,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 5.459,
       "eval_steps_per_second": 0.684,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 0.8587,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.9988044500350952,
+      "eval_runtime": 354.8862,
+      "eval_samples_per_second": 5.438,
+      "eval_steps_per_second": 0.682,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.8274441850197606e+17,
+  "total_flos": 3.110486213260984e+17,
   "trial_name": null,
   "trial_params": null
 }