Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edea18ae66443a8035f366ebb2ac9da8fd22add01b6512115d3d7a1c44e9214b
+oid sha256:867173bcaddd4298f59f7d72b16f31a68f27518e15f271a9040271ca66f6319e
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858563c45842d04bee8f9f4105d998ae45a4054ac14ee163dfe7439c9a553588
+oid sha256:f4b1d6ed1999ea1b1bbcec41b01bea8534d890f34f41175ccb3137f2d3ef69cc
 size 25222277

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e717dc6db51b58831880174d0cd7165ccb71c459cbe946e496091fd8e9ce994
+oid sha256:85658496e06077f87b750aeb031c8edf46d72979c48ec879f8596b632cba3381
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1820014715194702,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.1465147733688354,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 9.094,
       "eval_steps_per_second": 1.14,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0116,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.1465147733688354,
+      "eval_runtime": 185.6672,
+      "eval_samples_per_second": 10.395,
+      "eval_steps_per_second": 1.303,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4142790021545984e+16,
+  "total_flos": 2.8242451495747584e+16,
   "trial_name": null,
   "trial_params": null
 }