Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4519d44ce7cb246e6cd652647a985e4402690004f07f9f73ba9d99b7d442a0
+oid sha256:b6bd2bc512ee4b879274d0e429ac490ea9478616912b8b41ccfd3e8493782dad
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991b0027b4487635066d0fd231f965348ff0de499a8e60a23e44e83e071cbc42
+oid sha256:9828766169c2931047bd8fe079bd413068f496b660f2b139e113165e26e24e7e
 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": 1.1817998886108398,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.1461560726165771,
+  "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": 10.283,
       "eval_steps_per_second": 1.289,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0115,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.1461560726165771,
+      "eval_runtime": 186.2762,
+      "eval_samples_per_second": 10.361,
+      "eval_steps_per_second": 1.299,
+      "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
 }