Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e24e09d9874cfe63e946a3885f4501b58eea3039e8d489d62c7a9c02175a6b0
+oid sha256:5d5ceb0d8f4e34240f67558feeb5b4ed3fc990ee825794b3e89d53d7d4f84d59
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e4a629669fe4871341593d23ba93a00020483850008a05512c6a86a10d25ad
+oid sha256:f3d57c5e8ff00233b92dd1ae20ab8a5995032fd1313a97a806e7e3dd6dc58cc9
 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": 1.3606998920440674,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 1.346933126449585,
+  "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": 43.567,
       "eval_steps_per_second": 5.451,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 1.3149,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 1.346933126449585,
+      "eval_runtime": 143.8935,
+      "eval_samples_per_second": 43.602,
+      "eval_steps_per_second": 5.455,
+      "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
 }