Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706c5832ee2924ae33f011b1b91ca3f2b2ee9b1b6300eb4a19edba353e157ed5
+oid sha256:608ea4fc6942e931a75f4aff05de4894fe9e941a0a8b071db74025a809a2f8b3
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac0648541335ca4e3d2df776f0556720eefce4ef972d392204b1088c1938ae7
+oid sha256:04369d0c9868c4838bc7eeb9b1396d13e3d53611d969f95e6bf9f06bb92053ee
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d235165de510ff0726cd98a164f0204996ff7e0ba0c0e785855b606d1a75815
+oid sha256:6e42983a0941a5ea3ab8dd356cda0bea564cad32d8e894b126d9bb07e48e1e57
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3364778757095337,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 2.185792349726776,
+  "best_metric": 1.3254159688949585,
+  "best_model_checkpoint": "./outputs/checkpoint-3100",
+  "epoch": 2.2586520947176685,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,27 @@
       "eval_samples_per_second": 43.564,
       "eval_steps_per_second": 5.451,
       "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002,
+      "loss": 1.2945,
+      "step": 3100
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 1.3254159688949585,
+      "eval_runtime": 143.9738,
+      "eval_samples_per_second": 43.577,
+      "eval_steps_per_second": 5.452,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.788278624988119e+17,
+  "total_flos": 1.847919861143716e+17,
   "trial_name": null,
   "trial_params": null
 }