Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed9faaac264e4441cfd4a3e95b97c89c1e30d8119f5e8a8bdf478127284b4ab
+oid sha256:fd4902b6467a8b7e0a449e68ca614e7dfc893207eb5d052f707daaafc19d51c5
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af14e3810a989c86d9cd1f1509eea0deeb1368c7649e64e86b966b1caa372132
+oid sha256:ef9e15fd69fbf25366906d2a246fba8cf24a65da5394f4b69e506bbe4427708e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60e0505be6747b50a677a0e3b039e2ad98d67bfaffddade49b1dc6f03872291
+oid sha256:394766abeb71b3ac957ff63483e6b61106ea18c3bab5d2ed9983de69c7990104
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3554208278656006,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.3454769849777222,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 12.9,
       "eval_steps_per_second": 1.618,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.1018,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.3454769849777222,
+      "eval_runtime": 112.189,
+      "eval_samples_per_second": 12.934,
+      "eval_steps_per_second": 1.622,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.087703920173056e+16,
+  "total_flos": 5.72298056257536e+16,
   "trial_name": null,
   "trial_params": null
 }