Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6370cb83caf6e238584ab5f9b580674a70edad8ea201c5d4b57c3721183dccd6
+oid sha256:2ffcc6cc4c2d0ca1a1d164f11c21f727fb1ccae9c9f781204fd047bfb151f74f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6113e581696b4e2a07566172b0ab0d773fa3874803adacbb9bf70f9d0f23b208
+oid sha256:fbf23ffb0e0e597928a4c0c22a519209d168f17ab41b7a6e2b1919c625e89635
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c460c6d5170c5ca51901a3283076152befcb7567f2f2de0b955f1db311a891
+oid sha256:6db130484859ac18bcc59d3f63a2034b920c3187ab4ad8631498050925a77bb9
 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": 2.6173269748687744,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.07285974499089254,
+  "best_metric": 2.566875696182251,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.14571948998178508,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,13 +21,27 @@
       "eval_samples_per_second": 29.806,
       "eval_steps_per_second": 3.729,
       "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 2.5807,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 2.566875696182251,
+      "eval_runtime": 206.05,
+      "eval_samples_per_second": 30.449,
+      "eval_steps_per_second": 3.81,
+      "step": 200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2937068351078400.0,
+  "total_flos": 5859971699097600.0,
   "trial_name": null,
   "trial_params": null
 }