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:fd4902b6467a8b7e0a449e68ca614e7dfc893207eb5d052f707daaafc19d51c5
+oid sha256:a7029204fedb775a410ae427cd284a6f0c0e5afc38b97b64ba6defdb4f521a59
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9e15fd69fbf25366906d2a246fba8cf24a65da5394f4b69e506bbe4427708e
+oid sha256:781ddf8a7ed6935bb868f9b9904dbc54ebdd81970a9964c965512f7138b2537a
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:394766abeb71b3ac957ff63483e6b61106ea18c3bab5d2ed9983de69c7990104
+oid sha256:9fc067d9dd1ea61d168a9551e2cbf618d70a938ff6fc85b276775a170824ac0e
 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": 1.3454769849777222,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.3380351066589355,
+  "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": 12.934,
       "eval_steps_per_second": 1.622,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.0964,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.3380351066589355,
+      "eval_runtime": 112.5152,
+      "eval_samples_per_second": 12.896,
+      "eval_steps_per_second": 1.618,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.72298056257536e+16,
+  "total_flos": 6.358273580703744e+16,
   "trial_name": null,
   "trial_params": null
 }