Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c76ad55ff1736a5c4a118b25c8c8d5fb7857523caffe30a8daf41a76f43b927
+oid sha256:a931c7d96a2af665221e4ccd802d78588c47fe3215b601c19b91d46580a39030
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad019f42c62c7b82025127000f444ec78d4564940c0ee60f74a535306787aed1
+oid sha256:e0902738def1e16fa12b1684634807d53d6d39c0764906376928107159753092
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d6bd701fca6e19968b0e9d9d7fe0c31a82f71b8340d6006477f972d51d1483
+oid sha256:cd1c0d2ccf1a93ffb1e0a3cfb7bafbf17824f03d4e0587e1b5b0cf8f6c02f622
 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": 1.3628050088882446,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 1.3481007814407349,
+  "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": 43.708,
       "eval_steps_per_second": 5.469,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 1.3156,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 1.3481007814407349,
+      "eval_runtime": 143.5887,
+      "eval_samples_per_second": 43.694,
+      "eval_steps_per_second": 5.467,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.6689897048172954e+17,
+  "total_flos": 1.728485277962158e+17,
   "trial_name": null,
   "trial_params": null
 }