Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2288a6d7dd0d9e6860ac8e0acee99e2cf343cec35c24fdf3cd5be8ce74b722e0
+oid sha256:57aa977d45153c3463856e66c16fa1e99ea23131f33ce947df37af305ee5fc8b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f4516aa318f0574d42b4b412aa4e98184e2b85a2b7f79dd8cdd1a764d084b9
+oid sha256:567942077b5bc24670bbaddccc3f562685ebc30536aab685800929dcc359ee21
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6691656f59836e679b0b16a9e5fb6259737616134b8601994c32a922f156d9a2
+oid sha256:7d66b1a8c16da8ebf7970425c7c306a82ffa223990ce4f0cb56084c069e08e81
 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": 2.506849527359009,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 2.4826207160949707,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 30.748,
       "eval_steps_per_second": 3.847,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.4756,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 2.4826207160949707,
+      "eval_runtime": 204.4447,
+      "eval_samples_per_second": 30.688,
+      "eval_steps_per_second": 3.84,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.277701378039808e+16,
+  "total_flos": 2.562316410028032e+16,
   "trial_name": null,
   "trial_params": null
 }