Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456c8071bb121d182d702081fbb4e6910a4c9546a8c06902bb5b5f22166cb4de
+oid sha256:4928efdbbd5aa110866a4550fbed482684cef52cf70ddd2abc0dc6aaef51935c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d24a12ccdde3348ad8f6d549d50c65136112300282d9ae5c9c73f4f2ceea4a8
+oid sha256:14fe84a5e07525f8f22ee24c3e0a0477c0777c448e80bbd4cfdaa2a718ff6aa3
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377ae46bc3cd5d05f1bb24b1b87ddef28bf7ad3d4f889ed296fbea929728c889
+oid sha256:e120a915f7acf0f917c5e62ffff73a270c236e2220dbb5ce0d14adfe3e96685b
 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": 0.9947501420974731,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2784090909090908,
+  "best_metric": 0.9894721508026123,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.4204545454545454,
   "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": 11.998,
       "eval_steps_per_second": 1.504,
       "step": 900
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 1000
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 0.9894721508026123,
+      "eval_runtime": 124.1464,
+      "eval_samples_per_second": 12.018,
+      "eval_steps_per_second": 1.506,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.058277149800448e+16,
+  "total_flos": 5.620616308242432e+16,
   "trial_name": null,
   "trial_params": null
 }