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:aa6227e657c936d0a22bdab311102dbe56384550fd13387936eeff79cb6268f6
+oid sha256:db3534087f41de4279371254e1a272ab967c8f965b14c6fbd94a1510292d08a2
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f39613437d3dc114942316c37adb291aeffce2cd31919bcbdd2d3ec83ec1ae98
+oid sha256:cd8f1e867b5651b6f9d92b34a59ca3ba7533fed54d960314c79b5b2e33d85a39
 size 12611081

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225b583421d24eb621d9afb7a8350c8cc752e7fe95214cd43be011984e35bfc9
+oid sha256:914d66e5e379e4cfd8e3c151fb439a74f39ae2645cf3cf7ec31a3328442be621
 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": 1.3499459028244019,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.3190627098083496,
+  "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": 4.141,
       "eval_steps_per_second": 0.519,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.1034,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.3190627098083496,
+      "eval_runtime": 466.6597,
+      "eval_samples_per_second": 4.136,
+      "eval_steps_per_second": 0.519,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3328459744935936.0,
+  "total_flos": 6647423649644544.0,
   "trial_name": null,
   "trial_params": null
 }