Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5d3379c612a24393fb4f05d705fa4a6b6ba97ee2b026093cadbe0ae49bbfe2
+oid sha256:505eece004e629a20f95167265c465ffeb9a06299cdcae203eed20ebb7de8992
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d238dadbf4fb4cbdc745cc9752e68c3075dec18ba8d86bb5d06c3bb51657e7
+oid sha256:5129cf74e5390e64e08f9eaf2c4da8d51ad268dcfcb96c4b9d593d4549d72b07
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82d5715858a6b453029f5e503f3f7b61d7408ce2719abf36d70ab6c90639243
+oid sha256:63aa9a735404dac131dfbc8da4c0d73a5c82d175792f71a6b89cddd41d8318a5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1133551597595215,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 2.099728584289551,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 20.071,
       "eval_steps_per_second": 2.511,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 2.0394,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 2.099728584289551,
+      "eval_runtime": 207.7011,
+      "eval_samples_per_second": 30.207,
+      "eval_steps_per_second": 3.779,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.16793378136064e+16,
+  "total_flos": 8.458768314114048e+16,
   "trial_name": null,
   "trial_params": null
 }